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
This application claims benefit of foreign priority under 35 U.S.C. 119(a)-(d) of KR10-2022-0056193, filed in Korea on 5/6/2022.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/6/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered and attached by the examiner.
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, 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 factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claims 1-10 are rejected under 35 U.S.C. 103 as being unpatentable over Djelouah (U.S. Patent Pub. No. 2023/0153952) in view of Wang (U.S. Patent Pub. No. 2018/0122048).
Regarding Claim 1, Djelouah teaches an image quality enhancement method optimized for distortion characteristics of a target image, the image quality enhancement method comprising:
generating one or more training datasets with one or more distortions (¶20 FIG. 1 is a flowchart of a training method for an image denoising model; ¶21 In step S11, multiple sample image groups are collected through a shooting device; each sample image group includes multiple frames of sample images with the same photographic sensitivity and sample images in different sample image groups have different photographic sensitivities.)
obtaining training distortion characteristic values respectively by inputting the one or more training datasets into a degradation encoder neural network (DEN) (Fig. 2; ¶23 the degradation encoder 210 may be trained to produce a latent vector 215 that discriminatively characterizes the degradation present in an input video y 205;)
obtaining a service distortion characteristic value by inputting a service dataset comprising image patches of the target image into the degradation encoder neural network (¶35 Image contents representing consecutive frames of y.sub.p are encoded 210, resulting in corresponding representations of the degradation present in the video;)
Djelouah does not explicitly disclose computing a similarity between each of the training distortion characteristic values and the service distortion characteristic value; and selecting the training dataset having a highest similarity to the service distortion characteristic value.
Wang is in the same field of art of image analysis. Further, Wang teaches computing a similarity between each of the training distortion characteristic values and the service distortion characteristic value; and selecting the training dataset having a highest similarity to the service distortion characteristic value (¶25 Comparing one or more characteristics of the processed data to one or more characteristics of at least a section of a reference dataset may comprise matching a distribution of processed data (which may comprise reconstructed visual data) to a distribution of the reference dataset (which may comprise high resolution visual data). In some implementations, comparing the one or more characteristics of the processed data to the one or more characteristics of at least a section of the reference dataset may comprise evaluating pixel-to-pixel differences, or evaluating differences (or similarities) at some feature level. Since the set of processed data is used in training it may be referred to herein as a “set of training data”.)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Djelouah by computing a similarity and determining a training dataset that is taught by Wang; thus, one of ordinary skilled in the art would be motivated to combine the references for more accurate image reconstruction (Wang ¶55).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 2, Djelouah in view of Wang discloses the image quality enhancement method of claim 1, further comprising: training a super-resolution neural network (SRN) based on the selected training dataset; and converting the target image to a high-quality image by using the super-resolution neural network (Djelouah, ¶35 the super-resolution network 250, denoted R.sub.SR. In an aspect, the R.sub.DN and the R.sub.SR networks are task-specific networks that branch from a shared R.sub.B network. In this way, feature maps, generated by the R.sub.B network, can be simultaneously learned for different restoration tasks, while features specific for denoising and super-resolution can be learned by the R.sub.DN and the R.sub.SR networks, respectively.); (Wang ¶19 Some aspects and/or implementations provide for improved super-resolution of lower quality images to produce super-resolution images with improved characteristics (e.g. less blur, less undesired smoothing) compared to other super-resolution techniques.)
Regarding Claim 3, Djelouah in view of Wang discloses the image quality enhancement method of claim 1, wherein the training distortion characteristic value is an average of outputs of the degradation encoder neural network for at least one or more samples selected from each training dataset, and wherein the service distortion characteristic value is an average of outputs of the degradation encoder neural network for at least one or more samples selected from the service dataset (Djelouah, Fig. 4; ¶29 FIG. 4 illustrates this process of generating encoded pairs of degraded video samples; ¶00014 In a contrastive learning, the objective is to optimize for ψpij and ψqij that are similar, since they share the same degradation (in spite of the different video contents) and to optimize for ψpij and ψpkl that are dissimilar, since they do not share the same degradations. To achieve that objective, a cost metric L.sub.c is minimized 440, such as the InfoNCE loss function)
Regarding Claim 4, Djelouah in view of Wang discloses the image quality enhancement method of claim 1, wherein the similarity is calculated based on a difference between each of the training distortion characteristic values and the service distortion characteristic value (Wang, ¶25 Comparing one or more characteristics of the processed data to one or more characteristics of at least a section of a reference dataset may comprise matching a distribution of processed data (which may comprise reconstructed visual data) to a distribution of the reference dataset (which may comprise high resolution visual data). In some implementations, comparing the one or more characteristics of the processed data to the one or more characteristics of at least a section of the reference dataset may comprise evaluating pixel-to-pixel differences, or evaluating differences (or similarities) at some feature level. Since the set of processed data is used in training it may be referred to herein as a “set of training data”.)
The reasons for combining Djelouah and Wang are similar to that stated in the rejection of claim 1.
Regarding Claim 5, Djelouah in view of Wang discloses a computer-readable recording medium storing instructions for causing, when executed by a computer, the computer to perform the image quality enhancement method according to claim 1 (Djelouah, ¶16 a non-transitory computer-readable medium comprising instructions executable by at least one processor to perform methods.)
Regarding Claim 6, Djelouah teaches a image quality enhancement method optimized for distortion characteristics of a target image, the image quality enhancement method comprising:
training, by using training datasets with different distortions, one or more super-resolution neural networks (SRNs) to be respectively optimized for a certain distortion (Djelouah, ¶35 the super-resolution network 250, denoted R.sub.SR. In an aspect, the R.sub.DN and the R.sub.SR networks are task-specific networks that branch from a shared R.sub.B network. In this way, feature maps, generated by the R.sub.B network, can be simultaneously learned for different restoration tasks, while features specific for denoising and super-resolution can be learned by the R.sub.DN and the R.sub.SR networks, respectively;)
computing, by using a degradation encoder neural network (DEN), distortion characteristic values (Fig. 2; ¶23 the degradation encoder 210 may be trained to produce a latent vector 215 that discriminatively characterizes the degradation present in an input video y 205;)
converting the target image into a high-quality image by using the selected super-resolution neural network (Fig. 2, 255; ¶2 To restore the input video 205, based on the feature maps 235, the denoising network 240 may generate a denoised version 245 of the input video 205, and the super-resolution network 250 may generate a denoised and upscaled version 255 of the input video 205.)
Djelouah does not explicitly disclose Computing a similarity between a service dataset and each of the training datasets that are applied respectively to the one or more super-resolution neural networks; selecting, among the one or more super-resolution neural networks, a super-resolution neural network trained with a training dataset having a highest similarity.
Wang is in the same field of art of image analysis. Further, Wang teaches Computing a similarity between a service dataset and each of the training datasets that are applied respectively to the one or more super-resolution neural networks; selecting, among the one or more super-resolution neural networks, a super-resolution neural network trained with a training dataset having a highest similarity (¶25 Comparing one or more characteristics of the processed data to one or more characteristics of at least a section of a reference dataset may comprise matching a distribution of processed data (which may comprise reconstructed visual data) to a distribution of the reference dataset (which may comprise high resolution visual data). In some implementations, comparing the one or more characteristics of the processed data to the one or more characteristics of at least a section of the reference dataset may comprise evaluating pixel-to-pixel differences, or evaluating differences (or similarities) at some feature level. Since the set of processed data is used in training it may be referred to herein as a “set of training data”; ¶19 Some aspects and/or implementations provide for improved super-resolution of lower quality images to produce super-resolution images with improved characteristics (e.g. less blur, less undesired smoothing) compared to other super-resolution techniques;)
Therefore, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Djelouah by computing a similarity and determining a training dataset that is taught by Wang; thus, one of ordinary skilled in the art would be motivated to combine the references for more accurate image reconstruction (Wang ¶55).
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention.
Regarding Claim 7, Djelouah in view of Wang discloses the image quality enhancement method of claim 6, wherein the computing of the similarity comprises: obtaining, by using the degradation encoder neural network, training distortion characteristic values each represent a characteristic of distortion of each training dataset that is applied to each of the super-resolution neural networks (Djelouah, Fig. 2; ¶23 the degradation encoder 210 may be trained to produce a latent vector 215 that discriminatively characterizes the degradation present in an input video y 205; This is input into super resolution network 250) and a service distortion characteristic value that is a value represent a characteristic of distortion of the service dataset (Djelouah, ¶35 Image contents representing consecutive frames of y.sub.p are encoded 210, resulting in corresponding representations of the degradation present in the video;) and calculating the similarity based on a difference between each of the training distortion characteristic values and the service distortion characteristic value (Wang,¶25 Comparing one or more characteristics of the processed data to one or more characteristics of at least a section of a reference dataset may comprise matching a distribution of processed data (which may comprise reconstructed visual data) to a distribution of the reference dataset (which may comprise high resolution visual data). In some implementations, comparing the one or more characteristics of the processed data to the one or more characteristics of at least a section of the reference dataset may comprise evaluating pixel-to-pixel differences, or evaluating differences (or similarities) at some feature level. Since the set of processed data is used in training it may be referred to herein as a “set of training data”.)
Claim 8 recites limitations similar to claim 3 and is rejected under the same rationale and reasoning.
Claim 9 recites limitations similar to claim 5 and is rejected under the same rationale and reasoning
Regarding claim 10, claim 10 has been analyzed with regard to claim 6 and is rejected for the same reasons of obviousness as used above as well as in accordance with Djelouah further teaching on: A image quality enhancement device optimized for distortion characteristics of a target image, the image quality enhancement device comprising: a memory configured to store one or more instructions; and a processor, wherein the processor is configured to execute the one or more instructions for performing the steps (Fig. 1; ¶15 The systems comprise at least one processor and memory storing instructions)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DUSTIN BILODEAU whose telephone number is (571)272-1032. The examiner can normally be reached 9am-5pm.
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.
/DUSTIN BILODEAU/Examiner, Art Unit 2664
/JENNIFER MEHMOOD/Supervisory Patent Examiner, Art Unit 2664
Prosecution Insights