DETAILED ACTION
This action is in response to the application filed on November 21, 2024. Claims 1-20 are pending and have been examined.
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 November 21, 2024, is being considered by the examiner.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement.
Independent claims 1 and 20 contain the limitation, “configuration selection data.” Subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Examiner has read through Paragraph [0043], there is not support for the limitation of “configuration selection data.” In Paragraph [0043], the specification describes “the image enhancement configurer 140 generates a configuration command 141 based on the image compression quality 139 and sends the configuration command 141 to the image enhancer 108 to configure the image enhancer 108, as further described with reference to FIG. 4. In some examples, the configuration command 141 selects an image enhancement network (IEN) 110A from the one or more image enhancement networks 110, to be used to process the image 105A. In another example, the configuration command 141 sets a particular enhancement level of a “tunable” image enhancement network 110A to be used to process the image 105A. To illustrate, the configuration command 141 may adjust one or more weights of the image enhancement network 110A based on the image compression quality 139.” A configuration command 141 selects an image enhancement network from the one or more image enhancement networks 110. The configuration command selects an image enhancement network. It is unclear whether the configuration command 141 is the configuration selection data or if the configuration selection data is the one or more image enhancement networks. The dependent claims do not alleviate the issues and are also rejected under 35 U.S.C. 112(a).
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.
Claims 1-20 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.
The limitations of independent claims 1 and 20, include “configuration selection data.” The limitation is interpretated as there are image enhancement networks stored and selected. It is unclear given the current limitation what, “configuration selection data” is referring to. The dependent claims do not alleviate the issues of the independent claim and are also rejected under 35 U.S.C. 112(b).
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)(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.
Claim(s) 1, 17, and 20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Wang et al, 20230410269.
Regarding claim 1, Wang teaches a device comprising:
a memory configured to store configuration selection data associated with an image enhancer; and one or more processors configured to (see Wang Paragraph [0030], “an electronic device, comprising at least one memory and at least one processor, the memory stores one or more computer instructions, wherein one or more computer instructions are executed by the processor to implement the display driving method provided by the embodiments of the present disclosure,” and Paragraph [0026], “the up-sampling unit is configured to up-sample the down-sampled image of the current frame and the down-sampled image of the previous frame by bilinear interpolation algorithm, bicubic interpolation algorithm, or Lanczos interpolation algorithm”):
decompress an encoded pre-processed image to generate a decompressed image, wherein the pre-processed image is a downsampled version of a pre-compression image (see Wang, Paragraph [0043], “step S120: acquiring and decompressing a compressed down-sampled image of an image of a previous frame to obtain a down-sampled image of the previous frame”);
predict, based on the decompressed image, an image compression quality of the decompressed image (see Wang, Paragraph [0042], “generate corresponding pre-overdrive display data on the basis of the obtained restored image of the current frame and the restored image of the previous frame, since the restored image of the previous frame is obtained after the high-frequency detail restoration of the up-sampled image of the previous frame, the image quality reduction caused by the loss of high-frequency detail in the restored image of the previous frame can be avoided, thereby the quality of the presented picture can be improved and the user's experience can be improved,” the quality of the presented picture is improved therefore, in order to improve the quality of the presented image the quality must be predicted);
and process, using an image enhancement network of the image enhancer, the decompressed image to generate an output image, wherein the image enhancer is configured based on the predicted image compression quality and the configuration selection data (see Wang, Paragraph [0043], “step S130: up-sampling the down-sampled image of the current frame and the down-sampled image of the previous frame respectively to obtain an up-sampled image of the current frame and an up-sampled image of the previous frame”).
Regarding claim 17, Wang teaches the device of claim 1, further comprising
a display device configured to display the output image (see Wang, Paragraph [0018], “a pre-overdrive unit configured to generate corresponding pre-overdrive display data on the basis of the obtained restored image of the current frame and the restored image of the previous frame”).
As per claim 20, Claim 20 claims a non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to complete the same limitations as Claim 1. Therefore, the rejection and rationale are analogous to that made in Claim 1.
Wang further teaches a non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to (see Wang, Paragraph [0132], “Memory 03 may include high-speed RAM, and may also include non-volatile memory (NVM), such as at least one disk memory”).
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, 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.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Kennett et al, US 20200389672.
Regarding claim 2, Wang does not expressively teach the device of claim 1,
wherein the decompressed image includes compression artifacts.
However, Kennett in a similar invention in the same field of endeavor teaches
wherein the decompressed image includes compression artifacts (see Kennett, Paragraph [0035], “the denoising system 202 may be trained to approximate or estimate how a digital image having a variety of different compression artifacts would appear prior to introducing the compression artifacts via the compression and decompression processes”).
The combination of Wang and Kennett are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for a digital image to have a variety of different compression artifacts as taught in the method of Kennett in the method of Wang to more efficiently enhance digital video content (Kennett, Paragraph [0016]).
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Tanchenko et al, US 20130089150.
Regarding claim 3, Wang does not expressively teach the device of claim 1,
wherein the one or more processors are configured to predict the image compression quality independently of the pre-compression image.
However, Tanchenko in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to predict the image compression quality independently of the pre-compression image (see Tanchenko, Paragraph [0071], “As a result, it is possible to produce an estimate of image visual quality 160 prior to or independent of encoder 300 receiving the original image 100 for encoding”).
The combination of Wang and Tanchenko are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to produce an estimate of image visual quality as taught in the method of Tanchenko in the method of Tanchenko to alter the processing of subsequent images in a video sequence (Tanchenko, Paragraph [0008]).
Claim(s) 4 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Kim et al, US 20200162751.
Regarding claim 4, Wang does not expressively teach the device of claim 1,
wherein the predicted image compression quality corresponds to a predicted difference between the decompressed image and the pre-compression image.
However, Kim in a similar invention in the same field of endeavor teaches
wherein the predicted image compression quality corresponds to a predicted difference between the decompressed image and the pre-compression image (see Kim, Paragraph [0164], “the third lossy information 918 may indicate an L1-norm value indicating a difference between the original image 900 and the reconstructed image 916”).
The combination of Wang and Kim are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to indicate a difference between the original image and the reconstructed image as taught in the method of Kim in the method of Wang to improve encoding and decoding efficiencies (Kim, Paragraph [0002]).
Regarding claim 9, Wang does not expressively teach the device of claim 1,
wherein the one or more processors are configured to process, using a neural network, the decompressed image to predict the image compression quality.
However, Kim in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to process, using a neural network, the decompressed image to predict the image compression quality (see Kim, Paragraph [0045], “an image compressing method may include determining a compressed image by performing downsampling using a deep neural network (DNN) on an image; determining a prediction signal by performing prediction based on the compressed image”).
The combination of Wang and Kim are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to determine a compressed image by performing downsampling using a deep neural network (DNN) on an image and determine a prediction signal by performing prediction based on the compressed image as taught in the method of Kim in the method of Wang to improve encoding and decoding efficiencies (Kim, Paragraph [0002]).
Claim(s) 5-6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Li et al, CN 101459850.
Regarding claim 5, Wang does not expressively teach the device of claim 1,
wherein, to predict the image compression quality, the one or more processors are configured to generate an image compression quality metric based on the decompressed image and independently of the pre-compression image.
However, Li in a similar invention in the same field of endeavor teaches
wherein, to predict the image compression quality, the one or more processors are configured to generate an image compression quality metric based on the decompressed image and independently of the pre-compression image (see Li, Paragraph [0011], “Calculate the peak signal-to-noise ratio (PSNR) based on the input compression ratio (CR) and the IAMx, and predict the image compression quality”).
The combination of Wang and Li are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to calculate the peak signal-to-noise ratio (PSNR) and predict the image compression quality as taught in the method of Li in the method of Wang to predict the compression quality of any component of the reconstructed image without encoding and is applicable to any encoding standard or encoder. (Li, Paragraph [0008]).
Regarding claim 6, Wang does not expressively teach the device of claim 1,
wherein the one or more processors are configured to generate a predicted peak-signal-to-noise ratio (PSNR) based on the decompressed image and independently of the pre-compression image, wherein the predicted image compression quality is based on the predicted PSNR.
However, Kim in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to generate a predicted peak-signal-to-noise ratio (PSNR) based on the decompressed image and independently of the pre-compression image, wherein the predicted image compression quality is based on the predicted PSNR (see Li, Paragraph [0011], “Calculate the peak signal-to-noise ratio (PSNR) based on the input compression ratio (CR) and the IAMx, and predict the image compression quality”).
The combination of Wang and Li are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to calculate the peak signal-to-noise ratio (PSNR) and predict the image compression quality as taught in the method of Li in the method of Wang to predict the compression quality of any component of the reconstructed image without encoding and is applicable to any encoding standard or encoder. (Li, Paragraph [0008]).
Claim(s) 7 and 11-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Zhou et al, CN 111182301.
Regarding claim 7, Wang does not expressively teach the device of claim 1,
wherein the one or more processors are configured to generate a predicted structural similarity index measure (SSIM) based on the decompressed image and independently of the pre-compression image, wherein the predicted image compression quality is based on the predicted SSIM.
However, Zhou in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to generate a predicted structural similarity index measure (SSIM) based on the decompressed image and independently of the pre-compression image, wherein the predicted image compression quality is based on the predicted SSIM (see Zhou, Paragraph [0078], “In another embodiment provided in this specification, structural similarity (SSIM) can be used to evaluate image compression quality,” SSIM is a well-known quality metric and widely used in the art).
The combination of Wang and Zhou are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for structural similarity (SSIM) to be used to evaluate image compression quality as taught in the method of Zhou in the method of Wang to quickly select the optimal quantization parameter while meeting the code length threshold and ensuring the image compression quality (Zhou, Paragraph [0008]).
Regarding claim 11, Wang does not expressively teach the device of claim 1,
wherein the configuration selection data maps metric criteria to respective configurations of the image enhancer, and wherein the one or more processors are configured to:
determine, based on the predicted image compression quality, whether a metric criterion is satisfied;
based on determining that the metric criterion is satisfied, select a corresponding configuration from the configuration selection data; and configure the image enhancer to have the selected configuration.
However, Zhou in a similar invention in the same field of endeavor teaches
wherein the configuration selection data maps metric criteria to respective configurations of the image enhancer, and wherein the one or more processors are configured to (see Zhou, Paragraph [0034], “selecting optimal quantization parameters during image compression, including a processor and a memory for storing processor-executable instructions, wherein the instructions, when executed by the processor, implement the following steps”):
determine, based on the predicted image compression quality, whether a metric criterion is satisfied (see Zhou, Paragraph [0028], “The calculation module is used to calculate the image content features of the image to be compressed and obtain the prediction quantization parameters of the image to be compressed based on the regression model function”);
based on determining that the metric criterion is satisfied, select a corresponding configuration from the configuration selection data; and configure the image enhancer to have the selected configuration (see Zhou, Paragraph [0029], “The selection module is used to take the range of preset data with the predicted quantization parameter as the center as the quantization parameter range, and select the quantization parameter with the highest compression quality evaluation index of the image to be compressed as the optimal quantization parameter within the quantization parameter range").
The combination of Wang and Zhou are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to select optimal quantization parameters including a processor; to obtain the prediction quantization parameters of the image to be compressed; and select the quantization parameter with the highest compression quality evaluation index of the image to be compressed as the optimal quantization parameter within the quantization parameter range as taught in the method of Zhou in the method of Wang to quickly select the optimal quantization parameter while meeting the code length threshold and ensuring the image compression quality (Zhou, Paragraph [0008]).
Regarding claim 12, Wang does not expressively teach the device of claim 1,
wherein, to configure the image enhancer, the one or more processors are configured to select the image enhancement network from a plurality of image enhancement networks, select particular configuration settings of the image enhancement network, or a combination thereof. wherein, to configure the image enhancer, the one or more processors are configured to select the image enhancement network from a plurality of image enhancement networks, select particular configuration settings of the image enhancement network, or a combination thereof.
However, Zhou in a similar invention in the same field of endeavor teaches
wherein, to configure the image enhancer, the one or more processors are configured to select the image enhancement network from a plurality of image enhancement networks, select particular configuration settings of the image enhancement network, or a combination thereof (see Zhou, Paragraph [0128], “Within the range of quantization parameters, the quantization parameter with the highest quality compression evaluation index is selected as the optimal quantization parameter. The quality compression evaluation index includes any one of the following: peak signal-to-noise ratio (as shown in Formula 3), structural similarity (as shown in Formula 6), and mean squared error (as shown in Formula 7)”).
The combination of Wang and Zhou are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for the quantization parameter with the highest quality compression evaluation index is selected as the optimal quantization parameter; quality compression evaluation index includes any one of the following: peak signal-to-noise ratio (as shown in Formula 3), structural similarity (as shown in Formula 6), and mean squared error (as shown in Formula 7) as taught in the method of Zhou in the method of Wang to quickly select the optimal quantization parameter while meeting the code length threshold and ensuring the image compression quality (Zhou, Paragraph [0008]).
Regarding claim 13, Wang does not expressively teach the device of claim 12,
wherein the plurality of image enhancement networks is stored in the memory, the one or more processors are configured to retrieve the plurality of image enhancement networks from another device, or both.
However, Zhou in a similar invention in the same field of endeavor teaches
wherein the plurality of image enhancement networks is stored in the memory, the one or more processors are configured to retrieve the plurality of image enhancement networks from another device, or both (see Zhou, Paragraph [0217], “The device embodiments described above are merely illustrative. For example, the division of the units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed”).
The combination of Wang and Zhou are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for multiple units or components to be combined or integrated into another system as taught in the method of Zhou in the method of Wang to quickly select the optimal quantization parameter while meeting the code length threshold and ensuring the image compression quality (Zhou, Paragraph [0008]).
Regarding claim 14, Wang does not expressively teach the device of claim 12,
wherein the plurality of image enhancement networks is associated with image content types, and wherein the one or more processors are configured to select the image enhancement network from the plurality of image enhancement networks based on an image content type of the decompressed image.
However, Zhou in a similar invention in the same field of endeavor teaches
wherein the plurality of image enhancement networks is associated with image content types, and wherein the one or more processors are configured to select the image enhancement network from the plurality of image enhancement networks based on an image content type of the decompressed image (see Zhou, Paragraph [0092], “In one embodiment provided in this specification, the image content feature may be the texture feature of the image, and a regression model function between the image content feature and the optimal quantization parameter is established based on the texture feature of each static image in the static image set.”).
The combination of Wang and Zhou are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for a regression model function between the image content feature and the optimal quantization parameter to be established as taught in the method of Zhou in the method of Wang to quickly select the optimal quantization parameter while meeting the code length threshold and ensuring the image compression quality (Zhou, Paragraph [0008]).
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Ding et al, CN 106937117.
Regarding claim 8, Wang does not expressively teach the device of claim 1,
wherein the one or more processors are configured to adjust the predicted image compression quality based on high frequency information of the decompressed image, wherein the image enhancer is configured based on the adjusted predicted image compression quality.
However, Ding in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to adjust the predicted image compression quality based on high frequency information of the decompressed image, wherein the image enhancer is configured based on the adjusted predicted image compression quality (see Ding, Paragraph [0005], “In existing technologies, all images are usually compressed using the same compression algorithm with the same parameters before transmission and/or storage. However, the size of the compressed image file is related to factors such as the high-frequency components of the image itself and the number of similar color patches,” and Paragraph [0058], “For a specific image, applying the same compression algorithm with different quality parameters (i.e., in the compression algorithm, all parameters remain unchanged except for the quality parameters) can produce a compressed image corresponding to the quality parameters. The visual quality score of this compressed image is the visual quality score corresponding to the quality parameters,” It is well known in the art to derive image quality measures based on high frequency information as disclosed in Ding, applying different quality parameters based on the high-frequency components of the image itself produces a compressed image corresponding to quality parameters).
The combination of Wang and Ding are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, for the size of the compressed image file is related to factors such as the high-frequency components of the image itself and the number of similar color patches; and applying the same compression algorithm with different quality parameters (i.e., in the compression algorithm, all parameters remain unchanged except for the quality parameters) can produce a compressed image corresponding to the quality parameters as taught in the method of Ding in the method of Wang such that the compression rate is as high as possible, thus improving the compression effect (Ding, Paragraph [0015]).
Claim(s) 10 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Hodgkinson et al, WO 2019093234.
Regarding claim 10, Wang in view of Kim does not expressively teach the device of claim 9,
wherein the one or more processors are configured to: select a portion of the decompressed image based on a high frequency portion of the decompressed image; and use the neural network to process the portion of the decompressed image to predict the image compression quality.
However, Hodgkinson in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to: select a portion of the decompressed image based on a high frequency portion of the decompressed image; and use the neural network to process the portion of the decompressed image to predict the image compression quality (see Hodgkinson, Paragraph [0083], “The post-processing unit 108 performs processing to bring the decompressed image closer to the input image, and outputs the processed decompressed image as the output image. The post-processing unit 108 performs post-processing using a third convolutional neural network model,” and Paragraph [0086], “The post-processing unit 108 instructs the post-processing feature acquisition unit 107 to acquire high-frequency information extracted from the original image in order to improve the image quality.”).
The combination of Wang and Hodgkinson are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to acquire high-frequency image information to improve the image quality as taught in the method of Hodgkinson in the method of Wang to perform image compression with further suppression of image quality degradation (Hodgkinson, Paragraph [0006]).
Regarding claim 19, Wang does not expressively teach the device of claim 1, further comprising
a modem configured to receive the encoded pre-processed image.
However, Hodgkinson in a similar invention in the same field of endeavor teaches
a modem configured to receive the encoded pre-processed image (see Hodgkinson, Paragraph [0177], “the modulation/demodulation unit ex452”).
The combination of Wang and Hodgkinson are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to have a modulation/demodulation unit as taught in the method of Hodgkinson in the method of Wang to perform image compression with further suppression of image quality degradation (Hodgkinson, Paragraph [0006]).
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Kim et al, US 20200162751 in view of Agustsson et al, Extreme Learned Image Compression with GANs, 2018.
Regarding claim 15, Wang does not expressively teach the device of claim 1,
wherein, to configure the image enhancer, the one or more processors are configured to, based on the predicted image compression quality being greater than an image compression quality threshold, select a neural network trained based on a Generative Adversarial Network (GAN) technique as the image enhancement network to process the decompressed image.
However, Agustsson in a similar invention in the same field of endeavor teaches
wherein, to configure the image enhancer, the one or more processors are configured to, based on the predicted image compression quality being greater than an image compression quality threshold, select a neural network trained based on a Generative Adversarial Network (GAN) technique as the image enhancement network to process the decompressed image (see Agustsson, Abstract, “We propose a framework for extreme learned image compression based on Generative Adversarial Networks (GANs), obtaining visually pleasing images at significantly lower bitrates than previous methods,” and pg. 2588-2589, 3. Experiments, User study: “For each pairing of methods on Cityscapes and ADE20K,we compare the decompressed images obtained for a set of 20 randomly picked validation images at different bpp, having as reference the downscaled 1024×512px images. For each pairing on Kodak, we used all 24 images of the dataset. 9 randomly selected users were asked to select the best decompression result for each test image and pairing of methods”).
The combination of Wang and Agustsson are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to perform learned image compression based on Generative Adversarial Networks (GANs); compare the decompressed images obtained and have users select the best decompression result as taught in the method of Agustsson in the method of Wang to produce visually appealing high resolution images (Agustsson, pg. 2587, 1. Introduction).
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al, 20230410269 in view of Boic et al, US 20160035389.
Regarding claim 18, Wang does not expressively teach the device of claim 1,
wherein the one or more processors are configured to configure the image enhancer responsive to detection of a scene change in a sequence of decompressed images.
However, Boic in a similar invention in the same field of endeavor teaches
wherein the one or more processors are configured to configure the image enhancer responsive to detection of a scene change in a sequence of decompressed images (see Boic, Paragraph [0003], “Some of these approaches operate on decoded or decompressed image data, detecting scene changes by inspecting pixel values of frames of video”).
The combination of Wang and Boic are analogous art because they are both in the same field of endeavor of image enhancement. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to operate on decoded or decompressed image data, detecting scene changes by inspecting pixel values of frames of video as taught in the method of Boic in the method of Wang to efficiently identifying summarization segments of an encoded video without the need to decode the encoded video to obtain image data (Boic, Paragraph [0001]).
Allowable Subject Matter
Claim 16 is 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
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOMINIQUE JAMES whose telephone number is (703)756-1655. The examiner can normally be reached 9:00 am - 6:00 pm 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, Emily Terrell can be reached at (571)270-3717. 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.
/DOMINIQUE JAMES/Examiner, Art Unit 2666
/EMILY C TERRELL/Supervisory Patent Examiner, Art Unit 2666
Prosecution Insights