DETAILED ACTION
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on February 11th, 2026 has been entered.
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 .
Response to Arguments
Applicant’s arguments, see “Remarks”, filed February 11th, 2026, with respect to independent claim 14 and dependent claims 15-17 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Furthermore, an updated search yielded prior art sufficient to meet the limitations of amended independent claim 14 (which were previously included in dependent claim 18).
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 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.
Claims 14 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Jin (US20210319243) in view of Yu (“Predicting the Quality of Images Compressed After Distortion in Two Steps”).
In regards to claim 14, Jin teaches an image processing method, comprising: acquiring an input image (Jin Paragraph [0042] “In an embodiment of the disclosure, a user may specify a to-be-processed image (or target image) by using a terminal device”); and detecting a target area in the input image (Jin Paragraph [0043] “In an embodiment of the disclosure, after determining the target image, the server 105 may extract a feature map of the target image. For example, the server may extract a feature map of the target image by using any convolutional layer in a convolutional neural network (CNN) model. After the feature map of the target image is extracted, the feature map may be divided into a plurality of target regions;”).
Jin does not teach reducing the input image to a predetermined size to obtain a reduced image; acquiring quality degradation level information by predicting quality degradation levels associated with different areas in the reduced image; and processing the target area based on the quality degradation level information to obtain a processed output image.
However, Yu teaches reducing the input image to a predetermined size to obtain a reduced image (Yu Figure 2 “Compressed Image”; Figure 3 “Ic”); acquiring quality degradation level information by predicting quality degradation levels associated with different areas in the reduced image (Yu Figure 2; Section III A “A reference IQA module aims to capture perceptual quality differences between a distorted image and a reference image… As mentioned earlier, there is now a rich variety of effective reference image quality models. From among these, we will use MS-SSIM as an exemplar R module for comparing I with Ic.” Examiner note: This reference describes using “Multi-Scale Structural Similarity” for performing one step of image quality assessment. As described in the paper cited by Yu (Zhou Wang “MULTI-SCALE STRUCTURAL SIMILARITY FOR IMAGE QUALITY ASSESSMENT”), a sliding window is used to predict quality levels of different portions of the image, these quality scores are combined into a quality map, and a mean SSIM index of the quality map is used to evaluate the overall image quality (Zhou Wang, Section 2 Final paragraph)); and processing the target area based on the quality degradation level information to obtain a processed output image (Yu Figure 2 Examiner note: After performing MS-SSIM on the image, the overall quality score is used to further process the image and obtain a final predicted quality score Q2step).
Yu is considered to be analogous to the claimed invention because they are solving the same problem of image quality quantization. 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 modified the system of Jin to include the teachings of Yu, to provide the advantage of increased Pearson’s linear correlation coefficient, which is a measure of the predicted quality score and their subjective mean opinion score (MOS) (Yu Figure 12; Section V “We evaluated the performance between predicted quality scores and subjective MOS using SROCC and the Pearson’s (linear) correlation coefficient (LCC).”)
In regards to claim 18, Jin in view of Yu teaches the image processing method of claim 14, wherein the acquiring of the quality degradation level information comprises: quantizing the predicted quality degradation levels to acquire the quality degradation level information (Yu Figure 2; Figure 2 Description “A reference module is then applied to I and Ic resulting a predicted quality score QR.”).
Claims 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Jin in view of Yu, and further in view of Yan (US20200042769) and Zou (US20160283780).
In regards to claim 15, Jin in view of Yu teaches the image processing method of claim 15, but fails to teach obtaining absolute semantic layout information by parsing the target area; obtaining relative semantic layout information by detecting key points of the target area; and obtaining semantic layout information by encoding the obtained absolute semantic layout information and the relative semantic layout information, wherein the target area is processed based on the semantic layout information.
However, Yan teaches obtaining absolute semantic layout information by parsing the target area (Yan Paragraph [0119] “An image region containing a face of an original image in the RGB color space is cut out (annotated as “FaceReg” image).”; Paragraph [0121] “The standard face “mask” contains standard face key-point information. In actual processing, an alignment operation (e.g., coordinate alignment) is performed by persons skilled in the art according to the detected face key-point information and the standard face key-point information in the standard face “mask”, to achieve the deformation of the standard face “mask”. For example, the coordinates of the key-point on the standard face “mask” image and the coordinates of the detected face key-point are used as inputs, to respectively calculate the fitting functions of the X direction and the Y direction, and then the pixel points on the “FaceReg” image are fit and interpolated to the target point to achieve the deformation of the standard face “mask”.”).
Yan is considered to be analogous to the claimed invention because they are in the same field of using image processing techniques on a human face to produce a different image. 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 modified the system of Jin, Fang, and Rao to include the teachings of Yan, to provide the advantage of having an efficient system that can differentiate between regions of the face (Yan Paragraph [0148] “Therefore, distinguishing the first region and the second region in the face region image is beneficial to improving the intelligent facial processing effect.”).
Furthermore, Zou teaches obtaining relative semantic layout information by detecting key points of the target area (Zou Paragraph [0181] “A Euclidean distance between the above two vectors is calculated, that is, a Euclidean distance between the above two groups of feature points is calculated to serve as the magnitude of overall position change of all the feature points of the human face edge in the human face image before and after the determination of the step S104.”).); and obtaining semantic layout information by encoding the obtained absolute semantic layout information and the relative semantic layout information (Zou Paragraph [0145] “The human face image shown in FIG. 2 is input, and calculation is conducted by using the human face edge feature point calculation model in combination with pre-trained parameters to obtain position information of feature points of the human face edge in the human face image, that is, a coordinate value of each feature point.” Examiner note: In this reference the absolute semantic layout information is the position information of the feature points, and the relative semantic information is the distance between the vectors of paragraph [0181].); wherein the target area is processed based on the semantic layout information (Zou Figure 1; Paragraph [0190] “The position information of this group of feature points is used as qualified feature points of human face edge.” Examiner note: This portion of Zou uses the point calculated from the previous steps (which include the semantic layout information, as shown in claim 9) to obtain qualified feature points of the face, which is analogous to the target area).
Zou is considered to be analogous to the claimed invention because they are in the same field of detecting facial features. 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 modified the system of Jin, Fang, and Rao to include the teachings of Zou, to provide the advantage of having improved accuracy (Zou Paragraph [0084] “Moreover, convergence directions of the feature points during the process of linear regression are constrained and corrected by using the fitted profile edge curve, which improves the accuracy of positioning of the feature points of human face edge, and implements positioning of feature points of human face edge for human face images having different backgrounds, thereby making a wider application scope.”)
In regards to claim 16, Jin in view of Yu, Yan, and Zou teaches the image processing method of claim 15, wherein the obtaining of the absolute semantic layout information comprises: obtaining a face parsing map by parsing the target area (Yan Paragraph [0121] “The standard face “mask” contains standard face key-point information. In actual processing, an alignment operation (e.g., coordinate alignment) is performed by persons skilled in the art according to the detected face key-point information and the standard face key-point information in the standard face “mask”, to achieve the deformation of the standard face “mask”. For example, the coordinates of the key-point on the standard face “mask” image and the coordinates of the detected face key-point are used as inputs, to respectively calculate the fitting functions of the X direction and the Y direction, and then the pixel points on the “FaceReg” image are fit and interpolated to the target point to achieve the deformation of the standard face “mask”.”); and obtaining the absolute semantic layout information by performing a blur processing on the face parsing map. (Yan Paragraph[0129] “Gaussian blur and median blur are performed on the “FaceReg” image, and the results thereof are combined as a blurred face image”).
In regards to claim 17, Jin in view of Yu, Yan, and Zou teaches the image processing method of claim 15, wherein the obtaining of the relative semantic layout information comprises: detecting the key points of the target area (Zou Paragraph [0140] “Feature points of the human face edge in the human face image are calculated and obtained by using a preset human face edge feature point calculation model, and feature information of each feature point is acquired.”); selecting a first base point and a second base point from among the detected key points (Zou Figure 6 C to A1); and obtaining the relative semantic layout information by mapping a vector including at least one point in the target area and the first base point, to a reference vector including the first base point and the second base point (Zou Paragraph [0181] “A Euclidean distance between the above two vectors is calculated, that is, a Euclidean distance between the above two groups of feature points is calculated to serve as the magnitude of overall position change of all the feature points of the human face edge in the human face image before and after the determination of the step S104.”).
Allowable Subject Matter
Claims 1, 3-13, and 19-21 are allowable over the prior art.
Independent claims 1 and 19 recite the limitation “obtain an output image after the target area is processed based on the rearranged feature blocks and the feature map by weighting and combining the rearranged feature blocks based on a level of importance of at least one rearranged feature block, wherein the level of importance is determined based on predicted quality degradation levels associated with a reduced image corresponding to the input image”. Examiner found neither prior art cited in its entirety, not based on the prior art, found any motivation to combine any of the said prior art that teaches this limitation in the context of the claim as a whole.
As a non-limiting example, Jin in view of Yu (as applied to claims 14 and 18) teaches predicting quality scores of various regions of an image, and combining the scores to predict the quality level of the entire image. However, this reference falls short from teaching the allowed limitation because it does not base a level of importance on the predicted quality score. The prior art of record does not teach using predicted quality scores of feature blocks to weight the feature blocks and rearranging the feature blocks based on the weight.
As another non-limiting example, a close prior art, Xu, teaches a method of predicting quality scores of an image. Xu does this by breaking the image up into blocks, and predicting the quality score of the blocks based on the quality score of the respective patch using a trained machine learning model. However, Xu falls short from teaching this limitation because it does not base a level of importance on the predicted quality score. Further the blocks of this disclosure are not rearranged based on their importance.
As another non-limiting example, a close prior art Zhang “Backward Registration-Based Aspect Ratio Similarity for Image Retargeting Quality Assessment” teaches a method of retargeting (or resizing) an image, and testing the quality level of the retargeted image compared to the original image. This reference fails to teach a level of importance which is based upon the predicted quality level of the retargeted image.
As another non-limiting example, a close prior art US20210385502 teaches predicting quality of a video. This is done by downsampling an image frame and using the downsampled image for to estimate image quality. This reference does not teach weighting feature blocks according to the image quality. Instead, this reference teaches weighting the quality scores according to “sensitivity information”. This is distinct from the methods of the current disclosure, as the predicted quality is weighted according to the sensitivity information, rather than the sensitivity information being weighted according to the predicted quality.
Finally, as another non-limiting example, a close prior art Kim “Deep Convolutional Neural Models for Picture-Quality Prediction” teaches an overview of picture quality prediction, specifically those performed by neural networks.
For the reasons stated above, the current prior art of record, considered individually or in combination, fails to teach or reasonably suggest the claimed features of independent claims 1 and 19 structurally and functionally interconnected with other limitations in the manner as cited in the independent claims and dependent claims. Examiner notes that the current invention as disclosed in independent claims 1 and 19 is allowed in its entirety. Each and every limitation working together realizes the current claimed invention’s novelty. No single limitation alone accomplishes the allowability of the inventive independent claims, rather each and every limitation of the claims and their disclosed relationships are integral.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CALEB LOGAN ESQUINO whose telephone number is (703)756-1462. The examiner can normally be reached M-Fr 8:00AM-4:00PM 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, Andrew Bee can be reached at (571) 270-5183. 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.
/CALEB L ESQUINO/Examiner, Art Unit 2677
/ANDREW W BEE/Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights