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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. RU2020141817 filed in Russian Federation on 12/17/2020.
Information Disclosure Statement
The information disclosure statement (IDS) submitted is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Objections
Claims 1, 3, 4, 6, 11, 13, 14, and 16 are objected to because of the following informalities:
Claim 1, add “and” at the end of third limitation.
Claim 3, add “and” at the end of first limitation.
Claim 4, add “and” at the end of second limitation.
Claim 6, add “and” at the end of first limitation.
Claim 11, add “and” at the end of third limitation.
Claim 13, add “and” at the end of first limitation.
Claim 14, add “and” at the end of second limitation.
Claim 16, add “and” at the end of first limitation. 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 – 4 and 11 – 14 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1 – 4 and 14 – 17 of U.S. Patent No. US 12118692.
Regarding Claim 1, US 12118692 teaches:
A computer-implemented method comprising: receiving input image data of a low-resolution image, having an input size, to generate output image data for a high-resolution image having an output size, the output size being greater than the input size; interpolating the input image data to match the output size, thereby generating an interpolated image data for an interpolated image of the output size; determining residual image data based on the input image data; combining the interpolated image data with the residual image data to generate the output image data for the high-resolution image of the output size (Claim 1, A computer-implemented method comprising: receiving input image data of a low-resolution image, having an input size, to generate output image data for a high-resolution image having an output size, the output size being greater than the input size; interpolating the input image data to match the output size, thereby generating interpolated image data for an interpolated image of the output size; determining residual image data based on the input image data; combining the interpolated image data with the residual image data to generate the output image data for the high-resolution image of the output size”).
Regarding Claim 2, US 12118692 teaches: wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate the residual image data (claim 2, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate the residual image data”).
Regarding Claim 3, US 12118692 teaches, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate a plurality of intermediate indexes; decoding the plurality of intermediate indexes to generate the residual image data (Claim 3, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate a plurality of intermediate indexes; decoding the plurality of intermediate indexes to generate the residual image data).
Regarding Claim 4, US 12118692 teaches, wherein determining the residual image data based on the input image data further comprises: providing the input image data to a probability density estimation model to generate an estimated probability density of intermediate indexes; based on the estimated probability density of intermediate indexes, selecting a plurality of intermediate indexes; decoding, by a decoder model, the plurality of intermediate indexes to generate the residual image data (claim 4, wherein determining the residual image data based on the input image data further comprises: providing the input image data to a probability density estimation model to generate the estimated probability density of intermediate indexes; based on the estimated probability density of intermediate indexes, selecting a plurality of intermediate indexes; decoding the plurality of intermediate indexes to generate the residual image data”).
Regarding Claim 11, US 12118692 teaches:
A system comprising one or more processors and one or more storage media storing one or more computer programs for execution by the one or more processors, the one or more computer programs configured to perform a method comprising: receiving input image data of a low-resolution image, having an input size, to generate output image data for a high-resolution image having an output size, the output size being greater than the input size; interpolating the input image data to match the output size, thereby generating an interpolated image data for an interpolated image of the output size; determining residual image data based on the input image data; combining the interpolated image data with the residual image data to generate the output image data for the high-resolution image of the output size (Claim 14, A system comprising one or more processors and one or more storage media storing one or more computer programs for execution by the one or more processors, the one or more computer programs configured to perform a method comprising: receiving input image data of a low-resolution image, having an input size, to generate output image data for a high-resolution image having an output size, the output size being greater than the input size; interpolating the input image data to match the output size, thereby generating interpolated image data for an interpolated image of the output size; determining residual image data based on the input image data; combining the interpolated image data with the residual image data to generate the output image data for the high-resolution image of the output size”).
Regarding Claim 12, US 12118692 teaches, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate the residual image data (Claim 15, “wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate the residual image data”).
Regarding Claim 13, US 12118692 teaches, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate a plurality of intermediate indexes; decoding the plurality of intermediate indexes to generate the residual image data (Claim 16, “wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate a plurality of intermediate indexes; decoding the plurality of intermediate indexes to generate the residual image data”).
Regarding Claim 14, US 12118692 teaches, wherein determining the residual image data based on the input image data further comprises: providing the input image data to a probability density estimation model to generate an estimated probability density of intermediate indexes; based on the estimated probability density of intermediate indexes, selecting a plurality of intermediate indexes; decoding, by a decoder model, the plurality of intermediate indexes to generate the residual image data (Claim 17, wherein determining the residual image data based on the input image data further comprises: providing the input image data to a probability density estimation model to generate the estimated probability density of intermediate indexes; based on the estimated probability density of intermediate indexes, selecting a plurality of intermediate indexes; decoding the plurality of intermediate indexes to generate the residual image data”).
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 (i.e., changing from AIA to pre-AIA ) 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, 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.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1 – 4 and 11 – 14 are rejected under 35 U.S.C. 103 as being unpatentable over Dong et al. (Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307; hereafter referred to as Dong) in view of Zimmer et al. (US 20200250794 A1; hereafter referred to as Zimmer).
Regarding Claim 1, Dong teaches:
A computer-implemented method comprising:
receiving input image data of a low-resolution image, having an input size, to generate output image data for a high-resolution image having an output size, the output size being greater than the input size (Dong, page 297, 3 Convolutional Neural Networks for Super Resolution, 3.1. Formulation, “a single low-resolution image, first upscale it to the desired size… recover from Y an image Y that is as similar as possible to the ground truth high resolution image X”);
interpolating the input image data to match the output size, thereby generating an interpolated image data for an interpolated image of the output size (Dong, page 297, 3 Convolutional Neural Networks for Super Resolution, 3.1. Formulation,” a single low-resolution image, we first upscale it to the desired size using bicubic interpolation”);
determining residual image data based on the input image data (Dong, page 297, 3 Convolutional Neural Networks for Super Resolution, 3.1. Formulation, “Patch extraction and representation. this operation extracts (overlapping) patches from the low-resolution image Y and represents each patch as a high dimensional vector. These vectors comprise a set of feature maps”);
combining the interpolated image data with the residual image data to generate the output image data for the high-resolution image of the output size (Dong, page 298, Fig. 2, 3.1.2 Non-Linear Mapping, 3.1.3 Reconstruction, final high-resolution image (output) is produced by using non-linear mapping of the feature maps which is a type of interpolation and performs reconstruction on the non-linear mapping of the feature maps of the high-resolution image and updating the high-resolution images).
However, Dong does not explicitly teach:
the output size being greater than the input size.
In the same field of endeavor, Zimmer teaches:
the output size being greater than the input size (Zimmer, [0132] “that result in feature maps of doubling size”).
Dong and Zimmer are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong by modifying the same size images with different size images as taught by Zimmer to make the invention that receives low-resolution images and modifies the low-resolution images with feature maps using a neural network to increase the size of the output high-resolution image; thus, one of the ordinary skill in the art would have been motivated to combine the references since there is a need to improve the reconstruction of dense super-resolution images from raw images obtained by single molecule localization microscopy to decrease the overall process time and in particular the time needed for acquiring the raw images that are used to reconstruct the dense super-resolution images (Zimmer [0016]); thus one of the ordinary skill the art would have been motivated to combine the references.
Regarding Claim 2, Dong in view of Zimmer teaches the method of claim 1, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate the residual image data (Dong, page 298, 3.1.2 Non-linear mapping, high-resolution patches are generated by non-linear mapping of the feature maps of the input image, convolution layers are added to increase non-linearity).
Regarding Claim 3, Dong in view of Zimmer teaches the method of claim 1, wherein determining the residual image data based on the input image data further comprises:
providing the input image data to one or more models to generate a plurality of intermediate indexes (Zimmer, [0163] – [0169]); and
decoding the plurality of intermediate indexes to generate the residual image data (Zimmer, [0144] – [0146]).
Regarding Claim 4, Dong in view of Zimmer teaches the method of claim 1, wherein determining the residual image data based on the input image data further comprises:
providing the input image data to a probability density estimation model to generate an estimated probability density of intermediate indexes (Zimmer, [0163 – [0173]);
based on the estimated probability density of intermediate indexes, selecting a plurality of intermediate indexes (Zimmer, [0163 – [0173]);
decoding, by a decoder model, the plurality of intermediate indexes to generate the residual image data (Zimmer, [0135] “The decoder network contains multiple convolutional layers…The U-net is approximately symmetric and the last layer of the decoder network produces an output image of identical size as the input image fed to the encoder network”; Zimmer, [0142] – [0145]).
Regarding Claim 11, Dong teaches:
A system comprising one or more processors and one or more storage media storing one or more computer programs for execution by the one or more processors, the one or more computer programs configured to perform a method comprising:
receiving input image data of a low-resolution image, having an input size, to generate output image data for a high-resolution image having an output size, the output size being greater than the input size (Dong, page 297, 3 Convolutional Neural Networks for Super Resolution, 3.1. Formulation, “a single low-resolution image, first upscale it to the desired size… recover from Y an image Y that is as similar as possible to the ground truth high resolution image X”);
interpolating the input image data to match the output size, thereby generating an interpolated image data for an interpolated image of the output size (Dong, page 297, 3 Convolutional Neural Networks for Super Resolution, 3.1. Formulation,” a single low-resolution image, we first upscale it to the desired size using bicubic interpolation”);
determining residual image data based on the input image data (Dong, page 297, 3 Convolutional Neural Networks for Super Resolution, 3.1. Formulation, “Patch extraction and representation. this operation extracts (overlapping) patches from the low-resolution image Y and represents each patch as a high dimensional vector. These vectors comprise a set of feature maps”);
combining the interpolated image data with the residual image data to generate the output image data for the high-resolution image of the output size (Dong, page 298, Fig. 2, 3.1.2 Non-Linear Mapping, 3.1.3 Reconstruction, final high-resolution image (output) is produced by using non-linear mapping of the feature maps which is a type of interpolation and performs reconstruction on the non-linear mapping of the feature maps of the high-resolution image and updating the high-resolution images).
However, Dong does not explicitly teach:
the output size being greater than the input size.
In the same field of endeavor, Zimmer teaches:
the output size being greater than the input size (Zimmer, [0132] “that result in feature maps of doubling size”).
Dong and Zimmer are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong by modifying the same size images with different size images as taught by Zimmer to make the invention that receives low-resolution images and modifies the low-resolution images with feature maps using a neural network to increase the size of the output high-resolution image; thus, one of the ordinary skill in the art would have been motivated to combine the references since there is a need to improve the reconstruction of dense super-resolution images from raw images obtained by single molecule localization microscopy to decrease the overall process time and in particular the time needed for acquiring the raw images that are used to reconstruct the dense super-resolution images (Zimmer [0016]); thus one of the ordinary skill in the art would have been motivated to combine the references.
Regarding Claim 12, Dong in view of Zimmer teaches the system of claim 11, wherein determining the residual image data based on the input image data further comprises: providing the input image data to one or more models to generate the residual image data (Dong, page 298, 3.1.2 Non-linear mapping, high-resolution patches are generated by non-linear mapping of the feature maps of the input image, convolution layers are added to increase non-linearity).
Regarding Claim 13, Dong in view of Zimmer teaches the system of claim 11, wherein determining the residual image data based on the input image data further comprises:
providing the input image data to one or more models to generate a plurality of intermediate indexes (Zimmer, [0163] – [0169]); and
decoding the plurality of intermediate indexes to generate the residual image data (Zimmer, [0144] – [0146]).
Regarding Claim 14, Dong in view of Zimmer teaches the system of claim 11, wherein determining the residual image data based on the input image data further comprises:
providing the input image data to a probability density estimation model to generate an estimated probability density of intermediate indexes (Zimmer, [0163 – [0173]);
based on the estimated probability density of intermediate indexes, selecting a plurality of intermediate indexes (Zimmer, [0163 – [0173]);
decoding, by a decoder model, the plurality of intermediate indexes to generate the residual image data (Zimmer, [0135] “The decoder network contains multiple convolutional layers…The U-net is approximately symmetric and the last layer of the decoder network produces an output image of identical size as the input image fed to the encoder network”; Zimmer, [0142] – [0145]).
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Dong et al. (Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307; hereafter referred to as Dong) in view of Zimmer et al. (US 20200250794 A1; hereafter referred to as Zimmer) further in view of Wen et al. (US 20200372686 A1; hereafter referred to as Wen).
Regarding Claim 7, Dong in view of Zimmer teaches the method of claim 4, but does not explicitly teach:
training, by a probability density estimation (PDE) logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the probability density estimation model.
In the same field of endeavor, Wen teaches:
training, by a probability density estimation (PDE) logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the probability density estimation model (Wen [0037] “ The probability model generating apparatus 102 is used to predict probability distribution of the latent representation to obtain a probability model of the latent representation”; Wen, [0045] “the probability model generating apparatus 102 includes a context model and an entropy model, wherein the context model obtains content-based prediction based on the output (latent representation) of the quantizer 104, and the entropy model is responsible for learning the probability model of the latent representation”).
Dong, Zimmer and Wen are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong in view of Zimmer by generating probability density estimation model as taught by Wen to make the invention that trains an untrained data set of parameters to generate the probability density estimation model; doing so can result in accurately extracting features of images and obtaining more effective latent representations to reconstruct images precisely (less distortion) (Wen Abstract, [0004]); thus one of the ordinary skill in the art would have been motivated to combine the references.
Regarding Claim 17, Dong in view of Zimmer teaches the system of claim 14, but does not explicitly teach:
training, by a probability density estimation (PDE) logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the probability density estimation model.
In the same field of endeavor, Wen teaches:
training, by a probability density estimation (PDE) logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the probability density estimation model (Wen [0037] “ The probability model generating apparatus 102 is used to predict probability distribution of the latent representation to obtain a probability model of the latent representation”; Wen, [0045] “the probability model generating apparatus 102 includes a context model and an entropy model, wherein the context model obtains content-based prediction based on the output (latent representation) of the quantizer 104, and the entropy model is responsible for learning the probability model of the latent representation”).
Dong, Zimmer and Wen are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong in view of Zimmer by generating probability density estimation model as taught by Wen to make the invention that trains an untrained data set of parameters to generate the probability density estimation model; doing so can result in accurately extracting features of images and obtaining more effective latent representations to reconstruct images precisely (less distortion) (Wen Abstract, [0004]); thus one of the ordinary skill in the art would have been motivated to combine the references.
Claims 8 – 10 and 18 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Dong et al. (Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307; hereafter referred to as Dong) in view of Zimmer et al. (US 20200250794 A1; hereafter referred to as Zimmer) further in view of Hong et al. (Hong, S. H., Park, R. H., Yang, S., & Kim, J. Y. (2008). Image interpolation using interpolative classified vector quantization. Image and Vision Computing, 26(2), 228-239; hereafter referred to as Hong).
Regarding Claim 8, Dong in view of Zimmer teaches the method of claim 4, but does not explicitly teach:
wherein the decoder model is a vector-quantized (VQ) decoder model.
In the same field of endeavor, Hong teaches:
wherein the decoder model is a vector-quantized (VQ) decoder model (Hong, page 229, 2. Proposed interpolation algorithm using ICVQ, 2.1. VQ, Hong teaches using vector quantization for image enhancement and image reconstruction (decoding)).
Dong, Zimmer and Hong are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong in view of Zimmer by using a vector-quantized (VQ) decoder model as taught by Hong to make the invention that decodes using a vector-quantized (VQ) decoder model to generate the residual image data; doing so can reduce computational load and small quantization error (Hong, page 229, col. 1); thus one of the ordinary skill in the art would have been motivated to combine the references.
Regarding Claim 9, Dong in view of Zimmer teaches the method of claim 4, but does not explicitly teach:
training, by a decoder logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the decoder model.
In the same field of endeavor, Hong teaches:
training, by a decoder logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the decoder model (Hong, page 232, col. 1, “Fig. 1 shows the block diagram of the proposed algorithm, in which VQ training with a number of (LR and HR) example images and prediction of the HF image with two types of (LR and HR) codebooks are illustrated”).
Dong, Zimmer and Hong are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong in view of Zimmer by training the decoder model as taught by Hong to make the invention that decodes using a trained decoder model to generate the residual image data; doing so can reduce computational load and small quantization error (Hong, page 229, col. 1); thus one of the ordinary skill in the art would have been motivated to combine the references.
Regarding Claim 10, Dong in view of Zimmer further in view of Hong teaches the method of claim 9, providing features extracted from low-res image data set for the training, by the decoder logic, the untrained set of learning parameters to the trained set of learning parameters, thereby generating the decoder model (Hong, page 235, 3. Experimental results and discussions, Hong teaches the training data sets as features extracted from low resolution image).
Regarding Claim 18, Dong in view of Zimmer teaches the system of claim 14, but does not explicitly teach:
wherein the decoder model is a vector-quantized (VQ) decoder model.
In the same field of endeavor, Hong teaches:
wherein the decoder model is a vector-quantized (VQ) decoder model (Hong, page 229, 2. Proposed interpolation algorithm using ICVQ, 2.1. VQ, Hong teaches using vector quantization for image enhancement and image reconstruction (decoding)).
Dong, Zimmer and Hong are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong in view of Zimmer by using a vector-quantized (VQ) decoder model as taught by Hong to make the invention that decodes using a vector-quantized (VQ) decoder model to generate the residual image data; doing so can reduce computational load and small quantization error (Hong, page 229, col. 1); thus one of the ordinary skill in the art would have been motivated to combine the references.
Regarding Claim 19, Dong in view of Zimmer teaches the system of claim 14, but does not explicitly teach:
training, by a decoder logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the decoder model.
In the same field of endeavor, Hong teaches:
training, by a decoder logic, an untrained set of learning parameters to a trained set of learning parameters, thereby generating the decoder model (Hong, page 232, col. 1, “Fig. 1 shows the block diagram of the proposed algorithm, in which VQ training with a number of (LR and HR) example images and prediction of the HF image with two types of (LR and HR) codebooks are illustrated”).
Dong, Zimmer and Hong are considered analogous art as they are reasonably pertinent to the same field of endeavor of super-resolution image processing. Therefore, it would have been obvious to one of the ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Dong in view of Zimmer by training the decoder model as taught by Hong to make the invention that decodes using a trained decoder model to generate the residual image data; doing so can reduce computational load and small quantization error (Hong, page 229, col. 1); thus one of the ordinary skill in the art would have been motivated to combine the references.
Regarding Claim 20, Dong in view of Zimmer further in view of Hong teaches the system of claim 19, providing features extracted from low-res image data set for the training, by the decoder logic, the untrained set of learning parameters to the trained set of learning parameters, thereby generating the decoder model (Hong, page 235, 3. Experimental results and discussions, Hong teaches the training data sets as features extracted from low resolution image).
Allowable Subject Matter
Claims 5 – 6 and 15 – 16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20210303243 A1 Super-Resolution Convolutional Neural Network With Gradient Image Detection: teaches the functions that include obtaining an image associated with a print job, and providing the image as input to a convolutional neural network. The convolutional neural network includes a residual network, upscaling layers, and classification layers configured to detect whether the image is an artificial image having a computer-generated image gradient. The functions also include determining, based on an output of the classification layers, that the image is an artificial image having a computer-generated image gradient
CN 111179177 B Image Reconstruction Model Training Method, Image Reconstruction Method, Device And Medium: The invention claims an image reconstruction model training method, image reconstruction method, device and medium. The method comprises: obtaining original high resolution image and original low resolution image; inputting the original low-resolution image into the first generation network for image super-resolution reconstruction to obtain a pseudo-high-resolution image; inputting the original high-resolution image and the pseudo-high-resolution image into a first distinguishing network for distinguishing to obtain a first distinguishing result; inputting the original high-resolution image and the pseudo-high-resolution image into the sensing loss network to obtain the sensing loss value; updating model parameters of the first generation network and the first discrimination network based on the perceptual loss value and the first discrimination result, and obtaining a target generation network based on super-resolution reconstruction. The target generation network can reconstruct images with high resolution including texture characteristics and structure characteristics of different scales, and has high perception quality.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VAISALI RAO KOPPOLU whose telephone number is (571)270-0273. The examiner can normally be reached Monday - Friday 8:30 - 5.
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, Jennifer Mehmood can be reached at (571) 272-2976. 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.
VAISALI RAO. KOPPOLU
Examiner
Art Unit 2664
/VAISALI RAO KOPPOLU/Examiner of Art Unit 2664
Prosecution Insights