DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claims 1-20 are currently pending in U.S. Patent Application No. 18/929,938 and an Office action on the merits follows.
Claim Objections
Claim(s) 1, 9 and 17 are objected to because of the following informalities:
Independent claim(s) 1/9/17, at that compar[ing] limitation as performed by the fine-tuning module/third plurality of programming instructions, approximately lines 25-26, feature an apparent typographical error that is redundant/repeated language “compare the reconstructed multi-channel image to the multi-channel input image by computing one or more similarity metrics between the reconstructed multi-channel image and the muti-channel input image . Similarly, at approximately line 30, there appears to be a typographical error omitting ‘image’ – “to minimize distortion between the reconstructed multi-channel image and the multi-channel input image.”
Appropriate correction is required.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are rejected on the grounds of nonstatutory double patenting as being unpatentable and/or obvious over one or more claims of:
1) U.S. Patent No. 12,190,573 to parent Application No. 18/627,451.
Although the claims at issue are not identical, they are not patentably distinct from each other because claims of reference anticipate and/or render obvious one or more claim(s) of the instant application with limitations in common being as illustrated in the table(s) below. The conflicting claims are also not patentably distinct from each other for at least the following reasons:
• Instant claims and claims of reference recite common subject matter, and recite the open ended transitional phrase “comprising” which does not preclude any additional elements recited by claims of reference;
• Language/terminology of instant claim(s) constituting minor/slight variations from the claims of reference, if/where present, (e.g. “enhanced image generation” vs. hyperspectral image generation, “spectral analysis” vs. spectral band grouping, “spectral features” vs. spectral bands, “special relationship metric” vs. correlation coefficient, one or more “parameters” vs. weights etc.,) require interpretations under Broadest Reasonable Interpretation in view of plain meaning definitions (MPEP 2173.01 and 2111.01) equivalent to/met by language of the reference claims in view of that corresponding/ shared Specification. While the disclosure of reference may not be used as prior art (Double Patenting concerns the claims of reference), portions of the specification which provide support for reference claims may also be examined and considered when addressing the scope of claim(s) of reference and the issue of whether an instant claim defines an obvious variation or falls within the scope of an invention claimed in the claim(s) of reference. See MPEP 804 with reference to In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970).
Instant Claims 18/929,938
Claims of Reference US 12,190,573 B1
Claim(s) 1/9/17
A system for enhanced image generation, comprising:
Claim 1
A system for hyperspectral image generation, comprising:
a computing device comprising at least a memory and a processor;
a computing device comprising at least a memory and a processor;
a spectral analysis module comprising a first plurality of programming instructions that, when operating on the processor, cause the computing device to:
a spectral band grouping module comprising a first plurality of programming instructions that, when operating on the processor, cause the computing device to:
obtain a training multi-channel image;
obtain a training hyperspectral image;
identify a plurality of spectral features in the training multi-channel image;
identify a plurality of spectral bands in the training hyperspectral image;
compute a special relationship metric between spectral features; and
compute a correlation coefficient of each spectral band of the plurality of spectral bands to at least one other spectral band of the plurality of spectral bands; and
form a plurality of spectral domain groups based on the computed special relationship metrics;
form a plurality of spectral domain groups based on the computed correlation coefficients;
a decomposition module comprising a second plurality of programming instructions that,
when operating on the processor, cause the computing device to:
a decomposition module comprising a second plurality of programming instructions that,
when operating on the processor, cause the computing device to:
obtain the plurality of spectral domain groups from the spectral analysis module;
obtain the plurality of spectral domain groups from the spectral band grouping module;
obtain a multi-channel input image;
obtain an RGB (red-green-blue) input image;
provide the multi-channel input image and plurality of spectral domain groups to a
first machine learning model; and
provide the RGB input image and plurality of spectral domain groups to a first neural network, wherein the first neural network includes at least one convolutional block, and at least one residual block; and
obtain as an output of the first machine learning model, a spectrally enhanced output image, based on the multi-channel input image; and
obtain as an output of the first neural network, a reconstructed hyperspectral image, based on the RGB input image; and
a fine-tuning module comprising a third plurality of programming instructions that, when operating on the processor, cause the computing device to:
a fine-tuning module comprising a third plurality of programming instructions that, when operating on the processor, cause the computing device to:
provide the spectrally enhanced output image to an image reconstruction module;
provide the reconstructed hyperspectral image to a second neural network, wherein the second neural network includes at least one convolutional block, and at least one residual block;
obtain as an output of the image reconstruction module, a reconstructed multichannel image;
obtain as an output of the second neural network, a reconstructed RGB image;
compare the reconstructed multi-channel image to the multi-channel input image by computing one or more similarity metrics between the reconstructed multi-channel image and the muti-channel input image
corresponding features of the images; and
compare the reconstructed RGB image to the RGB input image by computing a spectral similarity metric between the reconstructed RGB image and the RGB input image, wherein the spectral similarity metric is based on correlation coefficients between corresponding spectral bands of the images; and
adjust one or more parameters of the first machine learning model based on the computed image similarity metrics to minimize distortion between the reconstructed multi-channel image and the multi-channel input image.
adjust one or more weights of the first neural network based on the comparison of computed spectral similarity metric to minimize spectral distortion between the reconstructed RGB image to the RGB input image.
Instant Claims 18/929,938
Claims of Reference US 12,190,573 B1
Claim(s) 1/9/17 see table above
Claim(s) 1/9/17 see table above
Claim(s) 2/10 wherein the first machine learning model comprises at least one feature
extraction block and at least one feature processing block
Claim 2/10 wherein the at least one residual block of the first neural network comprises at least two convolutional layers.
Claim(s) 3/11 wherein for each feature extraction block, a corresponding feature extraction parameter is configurable to adjust the level of detail extracted.
Claim(s) 3/11 wherein for each convolutional layer, a corresponding kernel size for the convolutional layer is set to 3 x 3.
Claim(s) 4/12 wherein the first machine learning model further comprises at least one non-linear transformation function
Claim(s) 4/12 wherein the first neural network further comprises an activation function.
Claim(s) 5/13 wherein the non-linear transformation function comprises a ReLU,
sigmoid function, hyperbolic tangent function, or a leaky ReLU.
Claim(s) 5/13 wherein the activation function comprises a ReLU layer.
Claim(s) 6/14 wherein the image reconstruction module comprises a self-supervised learning algorithm.
Claim(s) 6/14 wherein the second neural network comprises a self-supervised network.
Claim(s) 7/15 wherein a first feature extraction block is configured to identify spectral or spatial features in the multi-channel input image.
Claim(s) 7/15 wherein a first convolutional layer from the at least two convolutional layers is configured to perform feature extraction.
Claim(s) 8/16 wherein a feature processing block is configured to perform dimensionality reduction on the identified features.
Claim(s) 8/16 wherein a second convolutional layer from the at least two convolutional layers is configured to perform feature map dimension reduction.
Claim 18 implement a feature extraction component within the first machine learning model, configured to identify relevant characteristics in the multi-channel input image.
Claim 18 use a first convolutional layer that is
configured to perform feature extraction.
Claim 19 implement a dimensionality reduction component within the first machine learning model, configured to compress the feature representation of the input image.
Claim 19 to use a second convolutional layer that is configured to perform feature map dimension reduction.
Claim 20 to configure the image reconstruction module as a self-supervised network.
Claim 20 to configure the second neural network as a self-supervised network.
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 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.
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(s) 9-20 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 applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 9 recites, at approximately line 9, the limitation “the spectral analysis module". There is insufficient antecedent basis for this limitation in the claim. Claim 9 (method claim) begins with an ‘obtaining’ that is understood by the Examiner to be performed by such a module (see claim 1 (system claim), which does set forth required antecedent basis), however omits establishing basis for the spectral analysis module being referenced. Similarly, the claim recites at approximately line 8, “while operating on the processor” and “cause the computing device to”, which also lack required antecedent basis. Examiner does not understand the claim in question to give rise to indefiniteness in view of any rationale similar to that in e.g. MPEP 2173.05(p) (claim 9 is clearly a computer implemented method, congruent in scope to system claim 1 and CRM claim 17). The abovementioned instances are non-exhaustive, and Examiner requests Applicant’s assistance in review for/identifying any others that may exist.
Claim 17 (corresponding non-transitory CRM), features similar instances of omitted antecedents as those identified above for the case of method claim 9 (structured based on the system of claim 1). Dependent claim(s) 10-16 and 18-20 inherit and fail to cure that/those deficiencies identified above for independent claim(s) 9/17.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
1. Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Hang et al. “Spectral super-resolution network guided by intrinsic properties of hyperspectral imagery” (2021).
As to claim 9, Hang discloses a method for enhanced image generation (Abs “As an alternative method, spectral super-resolution aims at reconstructing HSI from its corresponding RGB image”), comprising steps of:
obtaining a training multi-channel image (page 7258 Section III A. “and a HSI as Y”, Fig. 2 “the correlation matrix derived from its training samples”, CAVE HSI samples, NUS, NTIRE2018 datasets, page 7259 “Taking Fig. 2 as an instance, the averaged correlation matrix is derived from training samples in the CAVE data”, etc.,);
identifying a plurality of spectral features in the training multi-channel image (page 7258 “and l represents the number of spectral bands in HSI”, page 7257 “The first one is the spectral correlation property. To demonstrate this point, we take CAVE data [23] as an example and calculate the correlations between any two spectral bands. Fig. 2 shows some image instances and the derived correlation matrix, where brighter colors represent higher correlations. It can be observed that adjacent spectral bands are correlated to each other. Based on this property, we propose a decomposition subnetwork to reconstruct HSI”, etc.,);
computing a special relationship metric between spectral features (Fig. 2 correlation matrix, page 7257, page 7259 Section B. Decomposition Subnetwork “1) Band Grouping: The decomposition subnetwork is conducted upon the result of band grouping, whose goal is to divide the whole spectral bands into different groups. A lot of methods can realize this goal. In this paper, we adopt a simple one named correlation coefficient to derive a correlation matrix”, etc.,); and
forming a plurality of spectral domain groups based on the computed special relationship metrics (page 7258 Section III “Fig. 3 shows the flowchart of our proposed model, which is mainly comprised of three stages. The first stage is band grouping. According to the correlations between different bands in HSI, the original spectral bands are divided into different groups”, page 7259 Section B., etc.,);
PNG
media_image1.png
806
1344
media_image1.png
Greyscale
a decomposition module comprising a second plurality of programming instructions that, when operating on the processor, cause the computing device to (Fig. 3 Stage 2 Decomposition subnetwork):
obtaining the plurality of spectral domain groups from the spectral analysis module (page 7259 Section B “The decomposition subnetwork is conducted upon the result of band grouping”);
obtaining a multi-channel input image (Fig. 3, Input RGB input to Stage 2 Decomposition subnetwork);
providing the multi-channel input image and plurality of spectral domain groups to a first machine learning model (Fig. 3 ‘first’ being e.g. the top/uppermost ‘branch’, page 7259 “2) Network Structure: As shown in Fig. 3, our decomposition subnetwork is comprised of m branches, where m equals to the number of decoupled groups … Each branch has two convolutional layers and two residual blocks. The first convolutional layer aims to extract features and project the low-dimensional RGB image into a high-dimensional space. The last convolutional layer attempts reducing the dimension of the feature maps to the desired one, which depends on the number of spectral bands in the corresponding group”); and
obtaining as an output of the first machine learning model, a spectrally enhanced output image, based on the multi-channel input image (Fig. 3 lower right corner “Reconstructed Hyperspectral”, page 7260 “Combining all the outputs of the decomposition subnetwork together will generate a reconstructed HSI”, etc.,); and
a fine-tuning module comprising a third plurality of programming instructions that, when operating on the processor, cause the computing device to (Fig. 3 Stage 3 self-supervised subnetwork, page 7260 Section C “Combining all the outputs of the decomposition subnetwork together will generate a reconstructed HSI. However, the decomposition subnetwork mainly focuses on reconstructing each spectral group separately, while ignoring their relations between different groups”):
provide the spectrally enhanced output image to an image reconstruction module (Fig. 3 reconstructed HSI as processed by the self-supervised fine-tuning subnetwork, page 7260 Section C);
obtain as an output of the image reconstruction module, a reconstructed multichannel image (Fig. 3 Reconstructed RGB);
compare the reconstructed multi-channel image to the multi-channel input image by computing one or more similarity metrics between the reconstructed multi-channel image and the muti-channel input image (comparison between “Input RGB” and “Reconstructed RGB” for the generation of e.g. LSE, in further view of LDE, etc.,), wherein the image similarity metrics are based on quantitative relationships between corresponding features of the images (Section D, ‘based on’ illustrated also in Fig. 3, page 7257 “In this paper, we take advantage of two intrinsic properties of HSI to construct an end-to-end spectral super-resolution network. The first one is the spectral correlation property”, Abs “In this paper, we attempt to design a spectral super-resolution network by taking advantage of two intrinsic properties of HSI. The first one is the spectral correlation. Based on this property, a decomposition subnetwork is designed to reconstruct HSI. The other one is the projection property, i.e., RGB image can be regarded as a three-dimensional projection of HSI. Inspired from it, a self-supervised subnetwork is constructed as a constraint to the decomposition subnetwork”, etc.,); and
adjust one or more parameters of the first machine learning model based on the computed image similarity metrics (page 7260 Section D, Fig. 3, “By combining Equation (9) and Equation (10) together, our new decomposition loss Lde is updated as … For the other self-supervised loss Lse, we use the same function as that in [34]:” etc.,) to minimize distortion between the reconstructed multi-channel image and the multi-channel input image (page 7260 Section C “At the training phase, the self-supervised subnetwork can be regarded as a constraint to fine-tune the learning process of the decomposition subnetwork. During the test phase, the self-supervised subnetwork is no longer needed, and the decomposition subnetwork will output the final reconstruction result”, Section D in view of LDE and LSE, etc.,).
As to claim 10, Hang discloses the method of claim 9.
Hang further discloses the method wherein the first machine learning model comprises at least one feature extraction block and at least one feature processing block (Fig. 3, page 7259 “Each branch has two convolutional layers and two residual blocks. The first convolutional layer aims to extract features and project the low-dimensional RGB image into a high-dimensional space. The last convolutional layer attempts reducing the dimension of the feature maps to the desired one, which depends on the number of spectral bands in the corresponding group. The middle blocks focus on leaning the residual between the first and the last convolutional layer. For each convolutional layer, the kernel size is set to 3 × 3”, Fig. 4, etc.,).
As to claim 11, Hang discloses the method of claim 10.
Hang further discloses the method wherein for each feature extraction block, a corresponding feature extraction parameter is configurable to adjust the level of detail extracted (see mapping for claim 10, e.g. kernel size).
As to claim 12, Hang discloses the method of claim 10.
Hang further discloses the method wherein the first machine learning model further comprises at least one non-linear transformation function (Hang page 7258 Section A, Problem Formulation, Equation(s) 1, 5, in further view of “the relationship between X and Y nonlinear”, corresponding Res blocks, in view of the Examiner’s understanding that residual blocks in nearly all instances incorporate an activation function/block/layer, page 7260 “Besides the last convolutional layer, each convolutional layer is followed by a ReLU operator”, etc.,).
As to claim 13, Hang discloses the method of claim 12.
Hang further discloses the method wherein the non-linear transformation function comprises a ReLU, sigmoid function, hyperbolic tangent function, or a leaky ReLU (page 7260 “Besides the last convolutional layer, each convolutional layer is followed by a ReLU operator”).
As to claim 14, Hang discloses the method of claim 9.
Hang further discloses the method wherein the image reconstruction module comprises a self-supervised learning algorithm (Fig. 3 stage 3, page 7259 “Similar to [12], our proposed self-supervised subnetwork is expected to address these issues by simulating the spectral response function S via a convolutional neural network”, page 7260 Section C, etc.,).
As to claim 15, Hang discloses the method of claim 10.
Hang further discloses the method wherein a first feature extraction block is configured to identify spectral or spatial features in the multi-channel input image (page 7259 “Each branch has two convolutional layers and two residual blocks. The first convolutional layer aims to extract features”, page 7257 Section B. Spectral Super-Resolution With Conventional Models “In contrast, our proposed model is able to explore spectral and spatial information simultaneously via convolutional operators”).
As to claim 16, Hang discloses the method of claim 10.
Hang further discloses the method wherein a feature processing block is configured to perform dimensionality reduction on the identified features (page 7259 “The last convolutional layer attempts reducing the dimension of the feature maps to the desired one, which depends on the number of spectral bands in the corresponding group”).
As to claim 17, this claim is the non-transitory CRM claim corresponding to computer implemented method claim 9, is rejected accordingly.
As to claim 18, this claim is the non-transitory CRM claim substantially incorporating the limitation(s) of computer implemented method claim(s) 10/15 and is rejected accordingly.
As to claims 19-20, these claims are the non-transitory CRM claims corresponding to computer implemented method claims 16 and 14 respectively, and are rejected accordingly.
As to claims 1-6, these claims are the system claims corresponding to computer implemented method claims 9-16 respectively, and are rejected accordingly.
Additional References
Prior art made of record and not relied upon that is considered pertinent to applicant's disclosure:
Additionally cited references (see attached PTO-892) otherwise not relied upon above have been made of record in view of the manner in which they evidence the general state of the art. PTO-892 page 1 Citation V Zhang et al. “A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging” (2022) discloses a known/recognized problem in the context of RGB to HSI reconstruction – known as the metamer problem, that may be addressed in part by means of loss functions accounting for spectral accuracy, complementary to those concerning spatial accuracy, and for exemplary spectral information associated losses, ‘among-channels LMRAE’ functions may be effective. See pertinent portion reproduced below:
PNG
media_image2.png
246
950
media_image2.png
Greyscale
Hang et al. “Prinet: A prior driven spectral super-resolution network” (2020) (attached PTO-892 at page 4, NPL Citation U) appears to anticipate claims 1-20 as an alternative to Hang et al. “Spectral super-resolution network guided by intrinsic properties of hyperspectral imagery” (2021) – sharing in common e.g. Fig. 2 and Fig. 3 respectively, illustrating three-stage 1) band grouping, 2) decomposition, and 3) self-supervised fine-tuning, conv and res architecture, LSE and LDE, etc.. Between the two prior art references Examiner understands LDE to have been updated (see Hang as relied upon above Eqn. 11) in addition to changes to residual block(s) (Fig. 4).
Inquiry
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IAN L LEMIEUX whose telephone number is (571)270-5796. The examiner can normally be reached Mon - Fri 9:00 - 6:00 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, Chan Park can be reached on 571-272-7409. 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.
/IAN L LEMIEUX/Primary Examiner, Art Unit 2669
Prosecution Insights