Prosecution Insights
Last updated: November 04, 2026
Application No. 18/895,538

IMAGE DATA PROCESSING METHOD, DEVICE, COMPUTER EQUIPMENT AND STORAGE MEDIUM

Final Rejection §103§112
Filed
Sep 25, 2024
Priority
Jan 30, 2024 — CN 202410125078.X
Examiner
ALLEN, LUCIUS CAMERON GREE
Art Unit
2673
Tech Center
2600 — Communications
Assignee
Beijing Liuyuan Space Information Technology Co. Ltd.
OA Round
2 (Final)
71%
Grant Probability
Favorable
3-4
OA Rounds
9m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 71% — above average
71%
Career Allowance Rate
34 granted / 48 resolved
+8.8% vs TC avg
Strong +30% interview lift
Without
With
+29.5%
Interview Lift
resolved cases with interview
Typical timeline
2y 10m
Avg Prosecution
19 currently pending
Career history
81
Total Applications
across all art units

Statute-Specific Performance

§101
10.8%
-29.2% vs TC avg
§103
52.7%
+12.7% vs TC avg
§102
9.5%
-30.5% vs TC avg
§112
24.9%
-15.1% vs TC avg
Black line = Tech Center average estimate • Based on career data from 48 resolved cases

Office Action

§103 §112
DETAILED ACTION Notice of AIA Status The present application is being examined under the AIA the first inventor to file provisions. Priority Receipt is acknowledged of certified copies of papers submitted under 35 U.S.C. 119(a)-(d), which papers have been placed of record in the file. Response to Arguments Applicant’s arguments see remarks, filed 07/29/2026, with respect to claims 1 and 3-10, have been fully considered but are not persuasive. The applicant argues on page 12, “Applicant respectfully submits that Bousmalis fails to disclose or render obvious the limitations of the present application. In particular, Bousmalis merely describes a shared encoder and a domain-specific encoder that generate a shared feature representation and a private feature representation for images from source and target domains, respectively. However, Bousmalis does not teach or suggest that the shared encoder is configured to extract image structure features, nor that the domain-specific encoder is configured to extract image texture features, as required by the present application.” In response, the office does not find this argument to be persuasive. Based on the breadth of the claim language the prior art by Bousmalis et al. (US 20190180136 A1), explicitly teaches wherein: the encoder comprises the shared encoder and a domain-specific encoder (Fig. 2, Paragraph [0033]- Bousmalis discloses to train the shared encoder neural network 110 and the classifier neural network 120, the neural network training system 200 also includes a private target encoder neural network 210, a private source encoder neural network 220, and a shared decoder neural network 230.); the extracting the image structure feature and the image texture feature in the image training set based on the encoder comprises: encoding a first image training set in the image training set based on the shared encoder to obtain a source image structure feature in the image structure feature (Fig. 2, Paragraph [0038]- Bousmalis discloses that is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein Fig. 2 shows using a shared encoder to create a shared feature Htc which is seen as the source image structure feature).); encoding a second image training set in the image training set based on the shared encoder to obtain a target image structure feature in the image structure feature (Fig. 2, Paragraph [0038]- Bousmalis discloses if the image is from the target domain, the combined feature representation is a combination of the private feature representation generated for the image by the private target encoder neural network 210 and the shared feature representation generated for the image by the shared encoder neural network 110.); and encoding the image training set according to the domain-specific encoder to obtain the image texture feature (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image.). The applicant argues on page 12, “Specifically, paragraph [0033] of Bousmalis discloses "to train the shared encoder neural network 110 and the classifier neural network 120, the neural network training system 200 also includes a private target encoder neural network 210, a private source encoder neural network 220, and a shared decoder neural network 230". It can be seen that Bousmalis merely lists the presence of a shared encoder, a shared decoder, and private source/target encoders as components of a neural network training system. This paragraph is purely structural and does not disclose any specific functional decomposition of image features into image structure features and image texture features as required by the present application.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 12-13, “Paragraph [0034] of Bousmalis discloses "the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image". It can be seen that Bousmalis describes that the private target encoder generates a private feature representation for images from the target domain.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 13, “Paragraph [0038] of Bousmalis discloses "the combined feature representation of an image is a combination, e.g., a concatenation, a sum, or an average, of the shared feature representation of the image and the private feature representation of the image. That is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110. If the image is from the target domain, the combined feature representation is a combination of the private feature representation generated for the image by the private target encoder neural network 210 and the shared feature representation generated for the image by the shared encoder neural network 110". It can be seen Bousmalis only discloses that the private encoder generates a private feature representation specific to a domain, and the shared encoder generates a shared feature representation, which are then combined to form a combined feature representation.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 13, “Accordingly, the mapping asserted by the Examiner between shared encoder and image structure feature, and domain-specific encoder and image texture feature is not supported by Bousmalis, either explicitly or inherently. Bousmalis is therefore silent with respect to the specific feature decomposition defined in the present application, and does not anticipate or render obvious the claimed encoding and feature extraction scheme.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 13-14, “In the present application, the image training set is processed through a shared encoder to obtain image structure feature, and the image training set is processed through a domain-specific encoder to obtain the image texture feature, which clarifies that the image training set includes the domain-invariant image structure feature and the domain-specific image texture feature, thereby facilitating subsequent reconstruction processing on the image texture feature and the image structure feature.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 14, “Therefore, Applicant respectfully submits that the reference documents fail to disclose the distinguishing technical features of the present application: wherein the encoder comprises the shared encoder and a domain-specific encoder; the extracting the image structure feature and the image texture feature in the image training set based on the encoder comprises: encoding a first image training set in the image training set based on the shared encoder to obtain a source image structure feature in the image structure feature; encoding a second image training set in the image training set based on the shared encoder to obtain a target image structure feature in the image structure feature; and encoding the image training set according to the domain- specific encoder to obtain the image texture feature.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 14, “Since independent claim 8 recites similar features as independent claim 1, independent claim 8 should also be allowable for the same reason as discussed in claim 1.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. The applicant argues on page 14, “Other dependent claims should also be considered as being eligible by sharing same features with independent claim 1. Withdrawal of the rejections and allowance of those claims are respectfully requested.” In response, the office does not find this argument to be persuasive base on the same reasons set forth above and the rejection below. Drawing objections The drawings are objected to under 37 CFR 1.83(a). The drawings must show every feature of the invention specified in the claims. Therefore, the first processing sub-module, second processing sub-module, and third processing sub-module must be shown or the feature(s) canceled from the claim(s). No new matter should be entered. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance. Claim Interpretation The following is a quotation of 35 U.S.C. 112(f): (f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof. The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph: An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof. The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked. As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph: (A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function; (B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and (C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function. Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function. Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function. Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Claim 8, recites limitations that use words like “means” (or “step”) or similar terms with functional language and do invoke 35 U.S.C. 112(f): Claim 8; recites the limitation, “an obtaining module, configured to” [Line 2]. Claim 8; recites the limitation, “a reconstruction module, configured to” [Line 4]. Claim 8; recites the limitation, “a classification module, configured to” [Line 7]. Claim 8; recites the limitation, “a determination module, configured to” [Line 10]. Claim 8; recites the limitation, “a first processing sub-module configured to encode” [Line 24]. Claim 8; recites the limitation, “a second processing sub-module configured to encode” [Line 28]. Claim 8; recites the limitation, “a third processing sub-module configured to encode” [Line 32]. Because these claim limitation(s) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. After a careful analysis, as disclosed above, and a careful review of the specification the following limitations in claim 8: “obtaining module” (Fig. 10, #1001. Paragraph [0196]- Each module in the above-mentioned image data processing device can be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules can be embedded in or independent of the processor in the computer equipment in the form of hardware, or can be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. (wherein the obtaining module has sufficient structure wherein is any kind of hardware, software stored on and executed by hardware, or combination of both.).)). “a reconstruction module” (Fig. 10, #1002. Paragraph [0196]- Each module in the above-mentioned image data processing device can be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules can be embedded in or independent of the processor in the computer equipment in the form of hardware, or can be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. (wherein the reconstruction module has sufficient structure wherein is any kind of hardware, software stored on and executed by hardware, or combination of both.).)). “a classification module” (Fig. 10, #1003. Paragraph [0196]- Each module in the above-mentioned image data processing device can be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules can be embedded in or independent of the processor in the computer equipment in the form of hardware, or can be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. (wherein the classification module has sufficient structure wherein is any kind of hardware, software stored on and executed by hardware, or combination of both.).)). “a determination module” (Fig. 10, #1004. Paragraph [0196]- Each module in the above-mentioned image data processing device can be implemented in whole or in part by software, hardware, and combinations thereof. Each of the above modules can be embedded in or independent of the processor in the computer equipment in the form of hardware, or can be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules. (wherein the determination module has sufficient structure wherein is any kind of hardware, software stored on and executed by hardware, or combination of both.).)). “a first processing sub-module configured to encode” (Paragraph [0170]- a first processing sub-module configured to encoding the first image training set in the image training set to obtain the source image structure feature in the image structure feature. (wherein no drawing shows the first processing sub-module therefore has no structure associated with it.).)). “a second processing sub-module configured to encode” (Paragraph [0173]- a second processing sub-module configured to encode the second image training set in the image training set based on the shared encoder to obtain the target image structure feature in the image structure feature. (wherein no drawing shows the second processing sub-module therefore has no structure associated with it.).)). “a third processing sub-module configured to encode” (Paragraph [0174]- a third processing sub-module configured to encode the image training set according to the domain-specific encoder to obtain the image texture feature. (wherein no drawing shows the third processing sub-module therefore has no structure associated with it.).)). If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. Claim Rejections - 35 USC § 112 The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claim 8 along with its dependent claims, are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention. Claim 8 recites limitations: Claim 8; recites the limitation, “a first processing sub-module configured to encode” [Line 24]. Claim 8; recites the limitation, “a second processing sub-module configured to encode” [Line 28]. Claim 8; recites the limitation, “a third processing sub-module configured to encode” [Line 32]. Claim 8 respectively invokes 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. However, the written description fails to disclose the corresponding structure, material, or acts for performing the entire claimed function and to clearly link the structure, material, or acts to the function. The specification is devoid of adequate structure to perform the claimed functions. The specification does not provide sufficient details such that one of the ordinary skill in the art would understand which structure performed(s) the claimed function. The following is a quotation of the first paragraph of 35 U.S.C. 112(a): (a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention. The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112: The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention. Claims 8 along with its dependent claims, are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. As described above, the disclosure does not provide adequate structure to perform the claimed function in the recited limitation Claims 8 recites limitations: Claim 8; recites the limitation, “a first processing sub-module configured to encode” [Line 24]. Claim 8; recites the limitation, “a second processing sub-module configured to encode” [Line 28]. Claim 8; recites the limitation, “a third processing sub-module configured to encode” [Line 32]. The specification does not demonstrate that applicant has made an invention that achieves the claimed function because the invention is not described with sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor had possession of the claimed invention. Claim Rejections - 35 USC § 103 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claims 1, 3 and 8-10 are rejected under 35 U.S.C 103 as being unpatentable over Bousmalis et al. (US 20190180136 A1) hereafter referenced as Bousmalis in view of Goforth et al. (US 20210150228 A1) hereafter referenced as Goforth. Regarding claim 1, Bousmalis teaches an image data processing method (Fig. 4, Paragraph [0049]- Bousmalis discloses FIG. 4 is a flow diagram of an example process 400 for performing an iteration of training a shared encoder neural network and a classifier neural network.), comprising: obtaining an image training set (Fig. 2, Paragraph [0032]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 on labeled images from the source domain and unlabeled images from the target domain and trains the classifier neural network 120 only on the labeled images from the source domain.), and extracting an image structure feature (Fig. 2, Paragraph [0040]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to (i) generate shared feature representations for input images from the target domain that are similar to shared feature representations for input images from the source domain.) and an image texture feature in the image training set based on an encoder (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image.); reconstructing the image structure feature and the image texture feature to obtain a reconstruction image feature (Fig. 2, Paragraph [0037]- Bousmalis discloses the shared decoder neural network 230 is configured to receive a combined feature representation of an image and to process the combined feature representation to generate a reconstruction of the image.), and decoding, by a shared decoder, the reconstruction image feature to obtain a reconstruction loss value set (Fig. 2, Paragraph [0037]- Bousmalis discloses the shared decoder neural network 230 is configured to receive a combined feature representation of an image and to process the combined feature representation to generate a reconstruction of the image (wherein Fig. 2, shows the shared decoder 230 outputting Reconstruction loss L_recon).); classifying, by a classifier, the image structure feature to obtain a classification loss value set (Fig. 2, Paragraph [0039]- Bousmalis discloses during the training, the neural network training system 200 adjusts the values of the parameters of the shared encoder neural network 110, the classifier neural network 120, the private target encoder neural network 210, the private source encoder neural network 220, and the shared decoder neural network 230 to determine trained values of the parameters of each of the networks (wherein Fig. 2 shows the classifier 120 outputting a classification loss L_class).), and updating parameters of the encoder and the shared decoder based on the reconstruction loss value set and the classification loss value set (Fig. 2, Paragraph [0057-58]- Bousmalis discloses the system adjusts the current values of the parameters of the private target encoder neural network, the shared encoder neural network, the private source encoder neural network, the shared decoder neural network, and the classifier neural network to reduce a loss resulting from the outputs generated by the neural networks (step 416). In particular, the system performs an iteration of a machine learning training technique, e.g., stochastic gradient with momentum, to minimize a loss that depends on a classification loss, a reconstruction loss, a difference loss, and a similarity loss.); wherein the feature extraction model is configured to extract an image structure feature in an image (Fig. 1, paragraph [0040]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to (i) generate shared feature representations for input images from the target domain that are similar to shared feature representations for input images from the source domain). wherein: the encoder comprises the shared encoder and a domain-specific encoder (Fig. 2, Paragraph [0033]- Bousmalis discloses to train the shared encoder neural network 110 and the classifier neural network 120, the neural network training system 200 also includes a private target encoder neural network 210, a private source encoder neural network 220, and a shared decoder neural network 230.); the extracting the image structure feature and the image texture feature in the image training set based on the encoder comprises: encoding a first image training set in the image training set based on the shared encoder to obtain a source image structure feature in the image structure feature (Fig. 2, Paragraph [0038]- Bousmalis discloses that is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein Fig. 2 shows using a shared encoder to create a shared feature Htc which is seen as the source image structure feature).); encoding a second image training set in the image training set based on the shared encoder to obtain a target image structure feature in the image structure feature (Fig. 2, Paragraph [0038]- Bousmalis discloses if the image is from the target domain, the combined feature representation is a combination of the private feature representation generated for the image by the private target encoder neural network 210 and the shared feature representation generated for the image by the shared encoder neural network 110.); and encoding the image training set according to the domain-specific encoder to obtain the image texture feature (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image.). Although Bousmalis explicitly teaches determining the shared encoder in the encoder as a feature extraction model Bousmalis fails to explicitly teach determining the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition. However, Goforth explicitly teaches determining the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition (Fig. 4, Paragraph [0055]- Goforth discloses since the code generated by the shared encoder also capture information about poses, the code may be decoded by the pose decoder without retraining the shared encoder. As such, the system may freeze the weights (or parameters) of the shared encoder (as determined in step 404), and train the pose decoder to estimate poses of the partial observations or inputs using codes from the frozen shared encoder (i.e., frozen codes) (wherein the stop condition is seen as the decoder being trained).), Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Goforth of determining the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein determining the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition. The motivation behind the modification would have been to increased efficiency and accuracy of estimation, since both Bousmalis and Goforth are both systems that use encoders and decoders. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Goforth’s system improves accuracy and efficiency of estimations done by the network. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Goforth et al. (US 20210150228 A1) Paragraph [0068]. Regarding claim 3, Bousmalis in view of Goforth teaches the method of claim 1, Bousmalis further teaches wherein: the domain-specific encoder comprises a source domain-specific encoder (Fig. 2, Paragraph [0035]- Bousmalis discloses the private source encoder neural network 220 is specific to the source domain and is configured to receive images from the source domain and to generate, for each received image, a private feature representation of the image.) and a target domain-specific encoder (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image.), and the image texture feature comprises a source image texture feature (Fig. 2, Paragraph [0035]- Bousmalis discloses the private source encoder neural network 220 is specific to the source domain and is configured to receive images from the source domain and to generate, for each received image, a private feature representation of the image (wherein the private feature representation created by the private source encoder is seen as the source image texture feature).) and a target image texture feature (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image (wherein the private feature representation created by the private target encoder is seen as the target image texture feature).); the encoding the image training set according to the domain-specific encoder to obtain the image texture feature comprises: encoding the first image training set according to the source domain-specific encoder to obtain the source image texture feature(Fig. 2, Paragraph [0035]- Bousmalis discloses the private source encoder neural network 220 is specific to the source domain and is configured to receive images from the source domain and to generate, for each received image, a private feature representation of the image (wherein the private feature representation created by the private source encoder is seen as the source image texture feature).); and encoding the second image training set according to the target domain-specific encoder to obtain the target image texture feature (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image (wherein the private feature representation created by the private target encoder is seen as the target image texture feature).). Regarding claim 8, Bousmalis teaches an image data processing device (Fig. 1 Paragraph [0004]- Bousmalis discloses for a system of one or more computers to be configured to perform particular operations or actions means that the system has installed on it software, firmware, hardware, or a combination of them that in operation cause the system to perform the operations or actions.), comprising: an obtaining module, configured to obtain an image training set (Fig. 2, Paragraph [0032]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 on labeled images from the source domain and unlabeled images from the target domain and trains the classifier neural network 120 only on the labeled images from the source domain.), and extract an image structure feature (Fig. 2, Paragraph [0040]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to (i) generate shared feature representations for input images from the target domain that are similar to shared feature representations for input images from the source domain.) and an image texture feature in the image training set based on the encoder (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image.); a reconstruction module, configured to reconstruct the image structure feature and the image texture feature to obtain a reconstruction image feature (Fig. 2, Paragraph [0037]- Bousmalis discloses the shared decoder neural network 230 is configured to receive a combined feature representation of an image and to process the combined feature representation to generate a reconstruction of the image.), and decode the reconstruction image feature through a shared decoder to obtain a reconstruction loss value set (Fig. 2, Paragraph [0037]- Bousmalis discloses the shared decoder neural network 230 is configured to receive a combined feature representation of an image and to process the combined feature representation to generate a reconstruction of the image (wherein Fig. 2, shows the shared decoder 230 outputting Reconstruction loss L_recon).); a classification module, configured to classify the image structure feature through a classifier to obtain a classification loss value set (Fig. 2, Paragraph [0039]- Bousmalis discloses during the training, the neural network training system 200 adjusts the values of the parameters of the shared encoder neural network 110, the classifier neural network 120, the private target encoder neural network 210, the private source encoder neural network 220, and the shared decoder neural network 230 to determine trained values of the parameters of each of the networks (wherein Fig. 2 shows the classifier 120 outputting a classification loss L_class).), and update parameters of the encoder and the shared decoder based on the reconstruction loss value set and the classification loss value set (Fig. 2, Paragraph [0057-58]- Bousmalis discloses the system adjusts the current values of the parameters of the private target encoder neural network, the shared encoder neural network, the private source encoder neural network, the shared decoder neural network, and the classifier neural network to reduce a loss resulting from the outputs generated by the neural networks (step 416). In particular, the system performs an iteration of a machine learning training technique, e.g., stochastic gradient with momentum, to minimize a loss that depends on a classification loss, a reconstruction loss, a difference loss, and a similarity loss.); wherein the feature extraction model is configured to extract an image structure feature in an image (Fig. 1, paragraph [0040]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to (i) generate shared feature representations for input images from the target domain that are similar to shared feature representations for input images from the source domain). wherein: the encoder comprises the shared encoder and a domain-specific encoder (Fig. 2, Paragraph [0033]- Bousmalis discloses to train the shared encoder neural network 110 and the classifier neural network 120, the neural network training system 200 also includes a private target encoder neural network 210, a private source encoder neural network 220, and a shared decoder neural network 230.), and the obtaining module comprises a first obtaining sub-module comprising: a first processing sub-module configured to encode a first image training set in the image training set to obtain a source image structure feature in the image structure feature (Fig. 2, Paragraph [0038]- Bousmalis discloses that is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein Fig. 2 shows using a shared encoder to create a shared feature Htc which is seen as the source image structure feature).); a second processing sub-module configured to encode a second image training set in the image training set based on the shared encoder to obtain a target image structure feature in the image structure feature (Fig. 2, Paragraph [0038]- Bousmalis discloses if the image is from the target domain, the combined feature representation is a combination of the private feature representation generated for the image by the private target encoder neural network 210 and the shared feature representation generated for the image by the shared encoder neural network 110.); a third processing sub-module configured to encode the image training set according to the domain-specific encoder to obtain the image texture feature (Fig. 2, Paragraph [0034]- Bousmalis discloses the private target encoder neural network 210 is specific to the target domain and is configured to receive images from the target domain and to generate, for each received image, a private feature representation of the image.). Although Bousmalis teaches a determination module, configured to determine the shared encoder in the encoder as a feature extraction model Bousmalis fails to explicitly teach a determination module, configured to determine the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition. However, Goforth explicitly teaches a determination module, configured to determine the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition (Fig. 4, Paragraph [0055]- Goforth discloses since the code generated by the shared encoder also capture information about poses, the code may be decoded by the pose decoder without retraining the shared encoder. As such, the system may freeze the weights (or parameters) of the shared encoder (as determined in step 404), and train the pose decoder to estimate poses of the partial observations or inputs using codes from the frozen shared encoder (i.e., frozen codes) (wherein the stop condition is seen as the decoder being trained).), Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Goforth of determining the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein determining the shared encoder in the encoder as a feature extraction model in response to that an updated encoder meets a training stop condition. The motivation behind the modification would have been to increased efficiency and accuracy of estimation, since both Bousmalis and Goforth are both systems that use encoders and decoders. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Goforth’s system improves accuracy and efficiency of estimations done by the network. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Goforth et al. (US 20210150228 A1) Paragraph [0068]. Regarding claim 9, Bousmalis in view of Goforth teaches the method of claim 1 is implemented, Bousmalis further teaches a computer equipment, comprising a memory (Fig. 1, Paragraph [0066]- Bousmalis discloses the computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.) and a processor (Fig. 1, Paragraph [0070]- Bousmalis discloses computers suitable for the execution of a computer program include, by way of example, can be based on general or special purpose microprocessors or both, or any other kind of central processing unit.), wherein the memory stores a computer program (Fig. 1, Paragraph [0070]- Bousmalis discloses computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and CD ROM and DVD-ROM disks.), and when the computer program is executed by the processor (Fig. 1, Paragraph [0070]- Bousmalis discloses generally, a central processing unit will receive instructions and data from a read only memory or a random access memory or both.), Regarding claim 10, Bousmalis in view of Goforth teaches the method of claim 1 is implemented, Bousmalis further teaches A non-transitory computer-readable storage medium (Fig. 1, Paragraph [0070]- Bousmalis discloses computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.), storing a computer program thereon (Fig. 1, Paragraph [0070]- Bousmalis discloses computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto optical disks; and CD ROM and DVD-ROM disks.), wherein when the computer program is executed by a processor (Fig. 1, Paragraph [0070]- Bousmalis discloses generally, a central processing unit will receive instructions and data from a read only memory or a random access memory or both.). Claim 4 is rejected under 35 U.S.C 103 as being unpatentable over Bousmalis et al. (US 20190180136 A1) hereafter referenced as Bousmalis in view of Goforth et al. (US 20210150228 A1) hereafter referenced as Goforth and Yang et al. (US 20210064907 A1) hereafter referenced as Yang. Regarding claim 4, Bousmalis in view of Goforth teaches the method of claim 1, Bousmalis further teaches wherein: the reconstruction image feature comprises a source image feature (Fig. 2, Paragraph [0038]- Bousmalis discloses the combined feature representation of an image is a combination, e.g., a concatenation, a sum, or an average, of the shared feature representation of the image and the private feature representation of the image. That is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein concatenation and summing of the Private and shared feature representation of the source is seen as the source image feature).), a target image feature (Fig. 2, Paragraph [0038]- Bousmalis discloses if the image is from the target domain, the combined feature representation is a combination of the private feature representation generated for the image by the private target encoder neural network 210 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein concatenation and summing of the Private and shared feature representation of the target is seen as the target image feature).),.), the image structure feature comprises a source image structure feature and a target image structure feature and the image texture feature comprises a source image texture feature and a target image texture feature (Fig. 2, Paragraph [0038]- Bousmalis discloses the combined feature representation of an image is a combination, e.g., a concatenation, a sum, or an average, of the shared feature representation of the image and the private feature representation of the image. That is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110.); the reconstructing the image structure feature and the image texture feature to obtain the reconstruction image feature comprises: splicing the source image structure feature and the source image texture feature to obtain the source image feature (Fig. 2, Paragraph [0038]- Bousmalis discloses the combined feature representation of an image is a combination, e.g., a concatenation, a sum, or an average, of the shared feature representation of the image and the private feature representation of the image. That is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein concatenation and summing are both seen as splicing).); splicing the target image structure feature and the target image texture feature to obtain the target image feature (Fig. 2, Paragraph [0038]- Bousmalis discloses if the image is from the target domain, the combined feature representation is a combination of the private feature representation generated for the image by the private target encoder neural network 210 and the shared feature representation generated for the image by the shared encoder neural network 110.); Bousmalis in view of Goforth fails to explicitly teach and a mixed image feature, splicing the source image structure feature and the target image texture feature to obtain a first mixed image feature in the mixed image feature; and splicing the target image structure feature and the source image texture feature to obtain the second mixed image feature in the mixed image feature. However, Yang explicitly teaches and a mixed image feature (Fig. 4, paragraph [0042]- Yang discloses Cross-domain cycle-consistency image generation is introduced to enforce disentangling between appearance and structure features. Given a pair of source and target images, their appearance or structure codes are swapped to synthesize new images. Since there exists no ground-truth supervision for the synthetic images, cycle-consistency self-supervision is used to reconstruct the two real images by swapping the appearance or structure codes extracted from the synthetic images. As demonstrated in the neural network 400, given a source image x.sub.s(i) and a target image x.sub.t(j), the synthesized images x.sub.t(j).sup.s(i)=G.sup.t(v.sub.s(i), T.sub.t(j) and x.sub.s(i).sup.t(j)= G.sup.s(v.sub.t(j), T.sub.s(i) are required to respectively preserve the corresponding appearance and structure codes from x.sub.s(i) and x.sub.t(j) to be able to reconstruct the two original real images: x.sub.t(j).sup.t(j) (wherein Fig. 4 shows the combination of a source structure being E^s_str and target texture feature E_app is seen as the mixed image feature).); splicing the source image structure feature and the target image texture feature to obtain a first mixed image feature in the mixed image feature (Fig. 4, paragraph [0042]- Yang discloses Cross-domain cycle-consistency image generation is introduced to enforce disentangling between appearance and structure features. Given a pair of source and target images, their appearance or structure codes are swapped to synthesize new images. Since there exists no ground-truth supervision for the synthetic images, cycle-consistency self-supervision is used to reconstruct the two real images by swapping the appearance or structure codes extracted from the synthetic images. As demonstrated in the neural network 400, given a source image x.sub.s(i) and a target image x.sub.t(j), the synthesized images x.sub.t(j).sup.s(i)=G.sup.t(v.sub.s(i), T.sub.t(j) and x.sub.s(i).sup.t(j)= G.sup.s(v.sub.t(j), T.sub.s(i) are required to respectively preserve the corresponding appearance and structure codes from x.sub.s(i) and x.sub.t(j) to be able to reconstruct the two original real images: x.sub.t(j).sup.t(j) (wherein Fig. 4 shows the combination of a source structure being E^s_str and target texture feature E_app being combined to create image X^t(j)_s(i))).); and splicing the target image structure feature and the source image texture feature to obtain the second mixed image feature in the mixed image feature (Fig. 4, paragraph [0042]- Yang discloses Cross-domain cycle-consistency image generation is introduced to enforce disentangling between appearance and structure features. Given a pair of source and target images, their appearance or structure codes are swapped to synthesize new images. Since there exists no ground-truth supervision for the synthetic images, cycle-consistency self-supervision is used to reconstruct the two real images by swapping the appearance or structure codes extracted from the synthetic images. As demonstrated in the neural network 400, given a source image x.sub.s(i) and a target image x.sub.t(j), the synthesized images x.sub.t(j).sup.s(i)=G.sup.t(v.sub.s(i), T.sub.t(j) and x.sub.s(i).sup.t(j)= G.sup.s(v.sub.t(j), T.sub.s(i) are required to respectively preserve the corresponding appearance and structure codes from x.sub.s(i) and x.sub.t(j) to be able to reconstruct the two original real images: x.sub.t(j).sup.t(j) (wherein Fig. 4 shows the combination of a target structure being E^t_str and source texture feature E_app being combined to create image X^s(i)_t(j)).). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis in view of Goforth of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Yang of a mixed image feature, splicing the source image structure feature and the target image texture feature to obtain a first mixed image feature in the mixed image feature; and splicing the target image structure feature and the source image texture feature to obtain the second mixed image feature in the mixed image feature. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein a mixed image feature, splicing the source image structure feature and the target image texture feature to obtain a first mixed image feature in the mixed image feature; and splicing the target image structure feature and the source image texture feature to obtain the second mixed image feature in the mixed image feature. The motivation behind the modification would have been to improve performance of the model in a target domain, since both Bousmalis and Yang are both systems that use encoders and decoders. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Yang’s system to improves performance of the model in a target domain. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Yang et al. (US 20210064907 A1) Paragraph [0004-5]. Claim 5 is rejected under 35 U.S.C 103 as being unpatentable over Bousmalis et al. (US 20190180136 A1) hereafter referenced as Bousmalis in view of Goforth et al. (US 20210150228 A1) hereafter referenced as Goforth, Yang et al. (US 20210064907 A1) hereafter referenced as Yang, and Shao et al. (US 20250225771 A1) hereafter referenced as Shao. Regarding claim 5, Bousmalis in view of Goforth and Yang teaches the method of claim 4, Bousmalis further teaches wherein: the reconstruction loss value comprises a source reconstruction loss value (Fig. 2, Paragraph [0041]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to generate a shared feature representation for an input image from the target domain that, when combined with a private feature representation for the same input image generated by the private target encoder neural network 210, can be used to accurately reconstruct the input image by the shared decoder neural network 230 and to generate a shared feature representation for an input image from the source domain that, when combined with a private feature representation for the same input image generated by the private source encoder neural network 220, can be used to accurately reconstruct the input image by the shared decoder neural network 230 (wherein Fig. 2, shows the source image being input into the shared decoder to create a L_recon value which is seen as the source reconstruction loss value).), a target reconstruction loss value (Fig. 2, Paragraph [0041]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to generate a shared feature representation for an input image from the target domain that, when combined with a private feature representation for the same input image generated by the private target encoder neural network 210, can be used to accurately reconstruct the input image by the shared decoder neural network 230 and to generate a shared feature representation for an input image from the source domain that, when combined with a private feature representation for the same input image generated by the private source encoder neural network 220, can be used to accurately reconstruct the input image by the shared decoder neural network 230 (wherein Fig. 2, shows the target image being input into the shared decoder to create a L_recon value which is seen as the target reconstruction loss value).), the decoding, by the shared decoder, the reconstruction image feature to obtain the reconstruction loss value set comprises: decoding, by the shared decoder, the source image feature to obtain a source image, and determining a source reconstruction loss value corresponding to the source image (Fig. 2, Paragraph [0041]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to generate a shared feature representation for an input image from the target domain that, when combined with a private feature representation for the same input image generated by the private target encoder neural network 210, can be used to accurately reconstruct the input image by the shared decoder neural network 230 and to generate a shared feature representation for an input image from the source domain that, when combined with a private feature representation for the same input image generated by the private source encoder neural network 220, can be used to accurately reconstruct the input image by the shared decoder neural network 230 (wherein Fig. 2, shows the source image being input into the shared decoder to create a L_recon value which is seen as the source reconstruction loss value).); decoding, by the shared decoder, the target image feature to obtain a target image, and determining a target reconstruction loss value corresponding to a target image (Fig. 2, Paragraph [0041]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 to generate a shared feature representation for an input image from the target domain that, when combined with a private feature representation for the same input image generated by the private target encoder neural network 210, can be used to accurately reconstruct the input image by the shared decoder neural network 230 and to generate a shared feature representation for an input image from the source domain that, when combined with a private feature representation for the same input image generated by the private source encoder neural network 220, can be used to accurately reconstruct the input image by the shared decoder neural network 230 (wherein Fig. 2, shows the target image being input into the shared decoder to create a L_recon value which is seen as the target reconstruction loss value).); Bousmalis in view of Goforth and Yang fails to explicitly teach a first mixed structure loss value, a first mixed texture loss value, a second mixed structure loss value, and a second mixed texture loss value; decoding, by the shared decoder, a first mixed image feature to obtain a first mixed image, and determining a first mixed structure loss value and a first mixed texture loss value corresponding to the first mixed image; and decoding, by the shared decoder, the second mixed image feature to obtain a second mixed image, and determining a second mixed structure loss value. However, Shao explicitly teaches a first mixed structure loss value (Fig. 9, Paragraph [0124]- Shao discloses a feature contrastive loss is determined based on the first sample image, the second sample image, the first decoded image, and the second decoded image Further in Fig. 9, paragraph [0125]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image (wherein the first feature contrastive loss is the first mixed structure loss value).), a first mixed texture loss value (Fig. 9, Paragraph [0124]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image, and a second feature contrastive loss of the second sample image and the second decoded image; and the non-similar feature contrastive loss includes at least one of: a third feature contrastive loss of the first sample image and the second decoded image, and a fourth feature contrastive loss of the second sample image and the first decoded image (wherein the fourth feature contrastive loss is seen as the first mixed texture loss).), a second mixed structure loss value (Fig. 9, Paragraph [0124]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image, and a second feature contrastive loss of the second sample image and the second decoded image; and the non-similar feature contrastive loss includes at least one of: a third feature contrastive loss of the first sample image and the second decoded image, and a fourth feature contrastive loss of the second sample image and the first decoded image (wherein the second feature contrastive loss is seen as the second mixed structure loss).), and a second mixed texture loss value (Fig. 9, Paragraph [0124]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image, and a second feature contrastive loss of the second sample image and the second decoded image; and the non-similar feature contrastive loss includes at least one of: a third feature contrastive loss of the first sample image and the second decoded image, and a fourth feature contrastive loss of the second sample image and the first decoded image (wherein the third feature contrastive loss is seen as the second mixed texture loss).); decoding, by the shared decoder, a first mixed image feature to obtain a first mixed image (Fig. 9, Paragraph [0120]- Shao discloses first decoding processing and second decoding processing are performed on the sample fused feature data by using a feature decoder to obtain a first decoded image corresponding to the first sample image and a second decoded image corresponding to the second sample image.), and determining a first mixed structure loss value (Fig. 9, Paragraph [0124]- Shao discloses a feature contrastive loss is determined based on the first sample image, the second sample image, the first decoded image, and the second decoded image Further in Fig. 9, paragraph [0125]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image (wherein the first feature contrastive loss is the first mixed structure loss value).) and a first mixed texture loss value corresponding to the first mixed image (Fig. 9, Paragraph [0124]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image, and a second feature contrastive loss of the second sample image and the second decoded image; and the non-similar feature contrastive loss includes at least one of: a third feature contrastive loss of the first sample image and the second decoded image, and a fourth feature contrastive loss of the second sample image and the first decoded image (wherein the fourth feature contrastive loss is seen as the first mixed texture loss).); and decoding, by the shared decoder, the second mixed image feature to obtain a second mixed image (Fig. 9, Paragraph [0120]- Shao discloses first decoding processing and second decoding processing are performed on the sample fused feature data by using a feature decoder to obtain a first decoded image corresponding to the first sample image and a second decoded image corresponding to the second sample image.), and determining a second mixed structure loss value (Fig. 9, Paragraph [0124]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image, and a second feature contrastive loss of the second sample image and the second decoded image; and the non-similar feature contrastive loss includes at least one of: a third feature contrastive loss of the first sample image and the second decoded image, and a fourth feature contrastive loss of the second sample image and the first decoded image (wherein the second feature contrastive loss is seen as the second mixed structure loss).) and a second mixed texture loss value corresponding to the second mixed image (Fig. 9, Paragraph [0124]- Shao discloses the similar feature contrastive loss includes at least one of: a first feature contrastive loss of the first sample image and the first decoded image, and a second feature contrastive loss of the second sample image and the second decoded image; and the non-similar feature contrastive loss includes at least one of: a third feature contrastive loss of the first sample image and the second decoded image, and a fourth feature contrastive loss of the second sample image and the first decoded image (wherein the third feature contrastive loss is seen as the second mixed texture loss).). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis in view of Goforth and Yang of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Shao of a first mixed structure loss value, a first mixed texture loss value, a second mixed structure loss value, and a second mixed texture loss value; decoding, by the shared decoder, a first mixed image feature to obtain a first mixed image, and determining a first mixed structure loss value and a first mixed texture loss value corresponding to the first mixed image; and decoding, by the shared decoder, the second mixed image feature to obtain a second mixed image, and determining a second mixed structure loss value. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein a first mixed structure loss value, a first mixed texture loss value, a second mixed structure loss value, and a second mixed texture loss value; decoding, by the shared decoder, a first mixed image feature to obtain a first mixed image, and determining a first mixed structure loss value and a first mixed texture loss value corresponding to the first mixed image; and decoding, by the shared decoder, the second mixed image feature to obtain a second mixed image, and determining a second mixed structure loss value. The motivation behind the modification would have been to improve feature detection ability, since both Bousmalis and Shao are both systems that use encoders and decoders. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Shao’s system to improves feature detection performance. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Shao et al. (US 20250225771 A1) Paragraph [0114]. Claim 6 is rejected under 35 U.S.C 103 as being unpatentable over Bousmalis et al. (US 20190180136 A1) hereafter referenced as Bousmalis in view of Goforth et al. (US 20210150228 A1) hereafter referenced as Goforth, Gouws et al. (US 20200342643 A1) hereafter referenced as Gouws, Yamada et al. (US 20160110656 A1) hereafter referenced as Yamada, and Shao et al. (US 20250225771 A1) hereafter referenced as Shao. Regarding claim 6, Bousmalis in view of Goforth the method of claim 1, Bousmalis further teaches wherein: the classification loss value set comprises a label transfer loss value (Fig. 2, Paragraph [0057-58]- Bousmalis discloses the system adjusts the current values of the parameters of the private target encoder neural network, the shared encoder neural network, the private source encoder neural network, the shared decoder neural network, and the classifier neural network to reduce a loss resulting from the outputs generated by the neural networks (step 416). In particular, the system performs an iteration of a machine learning training technique, e.g., stochastic gradient with momentum, to minimize a loss that depends on a classification loss, a reconstruction loss, a difference loss, and a similarity loss.), and the classifier comprises a first classifier and a second classification (fig. 2, Paragraph [0020]- Bousmalis discloses the image processing neural network system 100 includes a shared encoder neural network 110 and a classifier neural network 120.); the classifying, by the classifier, the image structure feature to obtain the classification loss value set comprises: classifying, by the first classifier, the image structure feature to obtain the label transfer loss value (Fig. 2, Paragraph [0057-58]- Bousmalis discloses the system adjusts the current values of the parameters of the private target encoder neural network, the shared encoder neural network, the private source encoder neural network, the shared decoder neural network, and the classifier neural network to reduce a loss resulting from the outputs generated by the neural networks (step 416). In particular, the system performs an iteration of a machine learning training technique, e.g., stochastic gradient with momentum, to minimize a loss that depends on a classification loss, a reconstruction loss, a difference loss, and a similarity loss.), classifying, by the second classifier, the image structure feature (fig. 2, Paragraph [0020]- Bousmalis discloses the image processing neural network system 100 includes a shared encoder neural network 110 and a classifier neural network 120 (wherein the first and second classifier are the same).), Bousmalis in view of Goforth fails to explicitly teach wherein a gradient of the first classifier is an inversion gradient. However, Gouws explicitly teaches wherein a gradient of the first classifier is an inversion gradient (Fig. 4, Paragraph [0060]- Gouws discloses during training, the system maximizes the loss with respect to the classifier parameters to improve the accuracy of the classifier and minimizes the loss with respect to the encoder network parameters to decrease the accuracy of the classifier. This maximization-minimization scheme can be realized by including a gradient reversal layer as the input layer of the classifier 406 and minimizing the overall loss.); Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis in view of Goforth of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Gouws wherein a gradient of the first classifier is an inversion gradient. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein a gradient of the first classifier is an inversion gradient. The motivation behind the modification would have been to improve training of transfer images from one domain to another, since both Bousmalis and Gouws are both systems that use encoders and decoders. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Gouws’s system to improves training of the components used to improve accuracy. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Gouws et al. (US 20200342643 A1) Paragraph [0036 and 0060]. Bousmalis in view of Goforth and Gouws fails to explicitly teach the image structure feature, and optimizing a classified image structure feature based on the Hilbert Schmidt independent criterion optimization method to obtain an optimized image structure feature. However, Yamada explicitly teaches and optimizing a classified image structure feature based on the Hilbert Schmidt independent criterion optimization method to obtain an optimized image structure feature (Fig. 7, Paragraph [0084]- Yamada discloses following for the respective feature signal vectors in the set of feature signal vectors may be determined: a normalized version of Hilbert-Schmidt Independence between a respective feature signal vector of the set of feature signal vectors and an output signal array, and a normalized version of Hilbert-Schmidt Independence between the respective feature signal vector of the set of feature signal vectors and the remaining feature signal vectors of the set of feature signal vectors.); Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis in view of Goforth, and Gouws of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Yamada the image structure feature, and optimizing a classified image structure feature based on the Hilbert Schmidt independent criterion optimization method to obtain an optimized image structure feature. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein the image structure feature, and optimizing a classified image structure feature based on the Hilbert Schmidt independent criterion optimization method to obtain an optimized image structure feature. The motivation behind the modification would have been to improve feature extraction performance, since both Bousmalis and Yamada are both systems that use machine learning for feature extraction. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Yamada’s system to improves feature selection performance. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Yamada et al. (US 20160110656 A1) Paragraph [0041-42]. Bousmalis in view of Goforth, Gouws, and Yamada fails to explicitly teach a source segmentation loss value and a target segmentation loss value, and weighting the optimized image structure feature, and determining the source segmentation loss value and the target segmentation loss value based on a weighted image structure feature. However, Shao explicitly teaches a source segmentation loss value and a target segmentation loss value (Fig. 9, Paragraph [0124]- Shao discloses a feature contrastive loss is determined based on the first sample image, the second sample image, the first decoded image, and the second decoded image; and the feature encoder to be trained and the feature reweighting device to be trained are updated based on the feature contrastive loss to obtain the feature encoder and the feature reweighting device (wherein Fig. 9 shows weighting of structure feature being the combination of the outputs of the first and second feature encoders and the of a target segmentation loss being the first feature contrastive loss and source segmentation loss being the second feature contrastive loss).), and weighting the optimized image structure feature, and determining the source segmentation loss value and the target segmentation loss value based on a weighted image structure feature (Fig. 9, Paragraph [0118]- Shao discloses sample feature selection weights respectively corresponding to the first sample feature and the second sample feature are determined by using the feature reweighting device to be trained, and feature fusion is performed on the first sample feature and the second sample feature based on the sample feature selection weights respectively corresponding to the first sample feature and the second sample feature, to obtain sample fused feature data. Further in Fig. 9, paragraph [0120]- Shao discloses first decoding processing and second decoding processing are performed on the sample fused feature data by using a feature decoder to obtain a first decoded image corresponding to the first sample image and a second decoded image corresponding to the second sample image. Further in fig. 9, Paragraph [0124]- Shao discloses a feature contrastive loss is determined based on the first sample image, the second sample image, the first decoded image, and the second decoded image; and the feature encoder to be trained and the feature reweighting device to be trained are updated based on the feature contrastive loss to obtain the feature encoder and the feature reweighting device (wherein Fig. 9 shows weighting of structure feature being the combination of the outputs of the first and second feature encoders and the of a target segmentation loss being the first feature contrastive loss and source segmentation loss being the second feature contrastive loss).) Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis in view of Goforth, Gouws, and Yamada of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Shao a source segmentation loss value and a target segmentation loss value, and weighting the optimized image structure feature, and determining the source segmentation loss value and the target segmentation loss value based on a weighted image structure feature. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein a source segmentation loss value and a target segmentation loss value, and weighting the optimized image structure feature, and determining the source segmentation loss value and the target segmentation loss value based on a weighted image structure feature. The motivation behind the modification would have been to improve feature detection ability, since both Bousmalis and Shao are both systems that use encoders and decoders. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Shao’s system to improves feature detection performance. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Shao et al. (US 20250225771 A1) Paragraph [0114]. Claim 7 is rejected under 35 U.S.C 103 as being unpatentable over Bousmalis et al. (US 20190180136 A1) hereafter referenced as Bousmalis in view of Goforth et al. (US 20210150228 A1) hereafter referenced as Goforth and Burangulov et al. (US 20190034830 A1) hereafter referenced as Burangulov. Regarding claim 7, Bousmalis in view of Goforth teaches the method of claim 1, Bousmalis further teaches performing the obtaining the image training set (Fig. 2, Paragraph [0032]- Bousmalis discloses the neural network training system 200 trains the shared encoder neural network 110 on labeled images from the source domain and unlabeled images from the target domain and trains the classifier neural network 120 only on the labeled images from the source domain.), and extracting the image structure feature and the image texture feature in the image training set based on the encoder (Fig. 2, Paragraph [0038]- Bousmalis discloses that is, if the image is from the source domain, the combined feature representation is a combination of the private feature representation generated for the image by the private source encoder neural network 220 and the shared feature representation generated for the image by the shared encoder neural network 110 (wherein Fig. 2 shows using a shared encoder to create a shared feature Htc which is seen as the source image structure feature).). Bousmalis in view of Goforth fails to explicitly teach wherein before the determining the shared encoder in the encoder as the feature extraction model in response to that the updated encoder meets the training stop condition, the method further comprises: obtaining an image verification set and determining whether the encoder reaches an overfitting equilibrium point based on the image verification set determining that the encoder meets a preset training stop condition in response to that the encoder reaches the overfitting equilibrium point and determining that the encoder does not meet the training stop condition in response to that the encoder does not reach the overfitting equilibrium point. However, Burangulov explicitly teaches wherein before the determining the shared encoder in the encoder as the feature extraction model in response to that the updated encoder meets the training stop condition, the method further comprises: obtaining an image verification set (Fig. 3, Paragraph [0064]- Burangulov discloses the manner in which the portion 304 and the another portion 306 of the first set of training samples 302 are chosen is not limited, and the portion 304 and the another portion 306 may be chosen dynamically for training and validation.) and determining whether the encoder reaches an overfitting equilibrium point based on the image verification set (Fig. 4, Paragraph [0099]- Burangulov discloses Generally, the objective of cross-validation is to estimate the accuracy of a predictive model by training the predictive model on a set of training data, and validate the model on a set of verification data, in order to have an accurate predictive model and to limit problems such as overfitting.) determining that the encoder meets a preset training stop condition in response to that the encoder reaches the overfitting equilibrium point (Fig. 3, Paragraph [0083]- Burangulov discloses the learner 320 may stop the training of the first predictive model 335 after M iterations. The learner 320 may analyze each respective first prediction error indicator 336 at an associated iteration to detect an overfitting point 410, the overfitting point 410 corresponding to a given iteration after which a trend in the first prediction error indicator 336 changes from generally decreasing to generally increasing. The overfitting point 410 may indicate that from the given iteration corresponding to the overfitting point 410, the respective first prediction error indicator 336 (corresponding to the MSE) of the first predictive model 335 may start to increase, and the training of the first predictive model 335 should cease.) and determining that the encoder does not meet the training stop condition in response to that the encoder does not reach the overfitting equilibrium point (Fig. 4, Paragraph [0088]- Burangulov discloses the number of retrained first predictive models 334 may be determined empirically, such that the number of retrained first predictive models 334 is statistically significant, and the results obtained by the retrained first predictive models 334 are not due to noise or other fluctuations. The learner 320 may iteratively retrain the retrained first predictive model 334 to obtain a plurality of retrained first predictive models 334 from the evaluation starting point 412 to the overfitting point 410 (wherein it is shown in fig. 4 that 412 is determined not to be a overfitting point thus continues training until the overfitting point 410 is reached).). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings of Bousmalis in view of Goforth of having an image data processing method, comprising: obtaining an image training set, and extracting an image structure feature and an image texture feature in the image training set based on an encoder with the teachings of Burangulov of wherein before the determining the shared encoder in the encoder as the feature extraction model in response to that the updated encoder meets the training stop condition, the method further comprises: obtaining an image verification set and determining whether the encoder reaches an overfitting equilibrium point based on the image verification set determining that the encoder meets a preset training stop condition in response to that the encoder reaches the overfitting equilibrium point and determining that the encoder does not meet the training stop condition in response to that the encoder does not reach the overfitting equilibrium point. Wherein having Bousmalis’ system for processing images using and training a shared encoder wherein before the determining the shared encoder in the encoder as the feature extraction model in response to that the updated encoder meets the training stop condition, the method further comprises: obtaining an image verification set and determining whether the encoder reaches an overfitting equilibrium point based on the image verification set determining that the encoder meets a preset training stop condition in response to that the encoder reaches the overfitting equilibrium point and determining that the encoder does not meet the training stop condition in response to that the encoder does not reach the overfitting equilibrium point. The motivation behind the modification would have been to reduce computational resources needed, since both Bousmalis and Burangulov are both systems train machine learning models. Wherein Bousmalis’ system wherein improved the accuracy of network outputs, while Burangulov’s system to improves the performance of a machine learning model saving computational resources. Please see Bousmalis et al. (US 20190180136 A1), Paragraph [0024] and Burangulov et al. (US 20190034830 A1) Paragraph [0015]. Conclusion Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant`s disclosure. Chang et al. (All About Structure: Adapting Structural Information Across Domains for Boosting Semantic Segmentation)- In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without any annotation. With the hypothesis that the structural content of images is the most informative and decisive factor to semantic segmentation and can be readily shared across domains, we propose a Domain Invariant Structure Extraction (DISE) framework to disentangle images into domain-invariant structure and domain-specific texture representations, which can further realize image-translation across domains and enable label transfer to improve segmentation performance. Extensive experiments verify the effectiveness of our proposed DISE model and demonstrate its superiority over several state-of-the-art approaches......................Please see Fig. 1. Abstract. Xie et al. (Unsupervised Domain Adaptation for Medical Image Segmentation by Disentanglement Learning and Self-Training)- Unsupervised domain adaption (UDA), which aims to enhance the segmentation performance of deep models on unlabeled data, has recently drawn much attention. In this paper, we propose a novel UDA method (namely DLaST) for medical image segmentation via disentanglement learning and self-training. Disentanglement learning factorizes an image into domain-invariant anatomy and domain-specific modality components. To make the best of disentanglement learning, we propose a novel shape constraint to boost the adaptation performance. The self-training strategy further adaptively improves the segmentation performance of the model for the target domain through adversarial learning and pseudo label, which implicitly facilitates feature alignment in the anatomy space. Experimental results demonstrate that the proposed method outperforms the state-of-the-art UDA methods for medical image segmentation on three public datasets, i.e., a cardiac dataset, an abdominal dataset and a brain dataset. The code will be released soon......................Please see Fig. 1. Abstract. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to LUCIUS C.G. ALLEN whose telephone number is (703)756-5987. The examiner can normally be reached Mon - Fri 8-5pm (EST). Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Chineyere Wills-Burns can be reached at (571)272-9752. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /LUCIUS CAMERON GREEN ALLEN/Examiner, Art Unit 2673 /CHINEYERE WILLS-BURNS/ Supervisory Patent Examiner, Art Unit 2673
Read full office action

Prosecution Timeline

Sep 25, 2024
Application Filed
Jun 01, 2026
Non-Final Rejection mailed — §103, §112
Jul 29, 2026
Response Filed
Sep 16, 2026
Final Rejection mailed — §103, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12784266
INTERACTIVE BEHAVIOR UNDERSTANDING METHOD FOR POSTURE RECONSTRUCTION BASED ON FEATURES OF SKELETON AND IMAGE
2y 4m to grant Granted Nov 03, 2026
Patent 12725267
BOTTOM-UP INSTANCE SEGMENTATION METHOD AND DEVICE
2y 3m to grant Granted Sep 01, 2026
Patent 12711772
SYSTEMS AND METHODS FOR TRAFFIC MONITORING USING MONOCULAR DEPTH ESTIMATION
2y 6m to grant Granted Aug 18, 2026
Patent 12705821
RADIANT AND VOLUMETRIC LATENT SPACE ENCODING FOR VOLUMETRIC RENDERING
3y 0m to grant Granted Aug 11, 2026
Patent 12694712
INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING METHOD
2y 9m to grant Granted Jul 28, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
71%
Grant Probability
99%
With Interview (+29.5%)
2y 10m (~9m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 48 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month