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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/12/24 and 11/7/25 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 103
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 1-4, 6, 10 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Kadu et al. (WO2020061172A1 using US2021/0350512 for citations) in view of Szegedy et al. (US 9,715,642).
Regarding claim 1, Kadu teaches a method for generating trim-pass metadata of pictures in a video sequence, wherein the trim-pass metadata are configured to perform adjustments of a tone-mapping curve that is applied to an input picture when being displayed on a target display (Figs. 1 and 4A-4B), the method comprising:
receiving the input picture (Fig. 4A, receive input images in step 402);
providing a feature extraction network, the feature extraction network comprising a convolutional neural network for feature extraction that is trained to identify high-level image features of the input picture (Fig. 4A, steps 402 and 404 teaches extracting image features from the images. However, Kadu fails to teach a CNN for feature extraction);
applying the feature extraction network to the input picture to generate the image features (Fig. 4A, steps 402 and 404 teaches extracting image features from the images);
providing a fully connected network, the fully connected network comprising a plurality of cascaded linear neural networks that are trained to map the image features to output trim-pass metadata values for the input picture (Fig. 4A, provides prediction model which is a trained model to process the “image features” in above steps to generate an output. However, Kadu fails to teach a fully connected network comprising a plurality of cascaded linear neural networks); and
applying the fully connected network to the image features to map the image features to the output trim-pass metadata values for the input picture (Fig. 4A, steps 408 teaches wherein the image features are mapped to optimize one or more image metadata parameters output by the process).
In an analogous neural networking art, it is well known and a predictable configuration to process the image through an initial feature extraction network and then to follow the process up with a fully connected network comprising a plurality of cascaded linear neural networks. Szegedy teaches in Fig. 1 of an image being input first into a Subnetwork A 104 followed by a fully connected network of a plurality of cascading convolutional layers (e.g. 110 to 112 to 130 to 108). Col. 2, lines 48-52 teaches “consists of one or more convolutional neural network layers”.
Szegedy highlights the flexible nature in which the layered neural network can be utilized in image processing. Col. 2, line 1-24 recites that the system “can be configured to receive input image data and to generate any kind of score or classification output based on the input image, i.e., can be configured to perform any kind of image processing task” and col. 2, lines 25-63 also recites “Similarly, the type of output layer 152 used to generate the output from the alternative representation also depends on the task. In particular, the output layer 152 is an output layer that is appropriate for the task, i.e., that generates the kind of output that is necessary for the image processing task”. Overall, the system can be utilized in many different ways to process any type of image processing task.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to incorporate the teachings of Kadu into Szegedy’s neural network based system because said incorporation allows for the benefit of maintaining improved performance and for improved speed and efficiency in incorporating such systems (col. 1, lines 33-48).
Regarding claim 2, Kadu teaches the claimed wherein the input picture is a high-dynamic range (HDR) picture coded using PQ encoding in the ICtCp color space (paragraph 193).
Regarding claim 3, Szegedy teaches the claimed wherein the feature extraction network comprises four cascaded convolutional networks (Szegedy in Fig. 1 shows a cascading convolutional networks).
Regarding claim 4, Szegedy teaches the claimed wherein the fully connected network comprises three cascaded linear networks (Szegedy in Fig. 1 shows a cascading convolutional networks).
Regarding claim 6, Szegedy teaches the claimed wherein the fully connected network comprises three cascaded linear networks (Szegedy in Fig. 1 shows a cascading convolutional networks).
Apparatus claim 10 and medium claim 11 are rejected for the same reasons as stated in method claim 1 above and furthermore, paragraphs 200-202 teaches that the system’s hardware include the claims processor and medium for storing the instructions that are to be executed by the processor.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Kadu et al. (WO2020061172A1, using US2021/0350512 for citations) in view of Szegedy et al. (US 9,715,642) and further in view of Aliamiri et al. (US 2021/0142068).
Regarding claim 5, Kadu and Szegedy teaches that the network accepts inputs with non square aspect ratios (see images for television, which includes non square aspect ratios as discussed in claim 1 above), however fails to teach, but Aliamiri teaches the claimed wherein the feature extraction network comprises a modified MobileNetV3 neural network (paragraphs 59 and 80).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the current application to incorporate the teachings of Aliamiri into the system of Kadu and Szegedy because said incorporation allows for the benefit of improving computational efficiency.
Allowable Subject Matter
Claims 7-9 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.
Regarding claim 7, the closest prior art as discussed above teaches the ability to train neural networks however fails to explicitly teach the following limitations in view of the limitations inherited from its chain of dependency: “further comprising: receiving input training trim-pass parameters corresponding to the input picture; applying an error loss unit to generate an error metric based on the input training trim- pass parameters and the output trim-pass metadata; and training the feature extraction network and the fully connected network by minimizing the error metric”. While prior arts teaches non neural network that minimizes a difference between a target tone curve and calculated trim pass functions, does not teach the specific nature of the limitations above with reference to the training of the feature extraction network and the fully connected network.
Claims 8-9 due to its dependency on claim 7 are also objected as well as being dependent upon a rejected base claim 1.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Choudhury et al. (US 2021/0076042) teaches neural network that minimizes a difference between a target tone curve and calculated trim pass functions.
Su et al. (US 2021/0150812) teaches a system that performs mapping images from a first dynamic range to a second dynamic range using a set of reference color-graded images and neural networks.
Wen et al. (US 10,264,287) teaches a system that performs inverse luma/chroma mappings with histogram transfer and approximation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GELEK W TOPGYAL whose telephone number is (571)272-8891. The examiner can normally be reached M-F (9:30-6 PST).
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, William Vaughn can be reached at 571-272-3922. 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.
/GELEK W TOPGYAL/ Primary Examiner, Art Unit 2481