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 .
Election/Restrictions
Applicant’s election of Group I, claims 1-10 and 18-20, is acknowledged. Claims 11-17 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected invention, there being no allowable generic or linking claim. Election was made without traverse in the reply filed on March 6, 2026.
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.
Claims 1-3, 5, 6, 8-10, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Price et al. (U.S. Patent Application Publication No. 2018/0253865), referred herein as Price, in view of Moore et al. (U.S. Patent Application Publication No. 2015/0106755), referred herein as Moore.
Regarding claim 1, Price teaches a computer-implemented method for generating mattes for images, the method comprising: receiving an image that includes a foreground having a first color and a background having a second color, wherein the second color is highly contrasted and different from the first color (paragraph 59, the last 13 lines; paragraph 91, lines 1-7; paragraph 96, lines 15-19; paragraph 100, lines 1-6; an input image is received comprising a foreground with a first color and a background in a highly contrasted, different second color); and
generating a matte based on the second color included in the image (paragraph 91, the last 6 lines; paragraph 96, lines 22-27; paragraph 101, lines 1-2; a matte is generated based on the second color).
Price teaches that the first foreground and second background colors are in high contrast to one another (paragraph 96, lines 1-10; paragraph 100), but does not explicitly teach that they are complements.
However, in a similar field of endeavor, Moore teaches a method comprising receiving an image that includes a foreground having a first color and a background with a second color, and processing the image to generate a foreground image based on the second color (paragraph 68; paragraph 127; paragraphs 134 and 135; paragraph 145), wherein the first and second colors are complements (paragraph 150, the last 8 lines; paragraph 151, lines 1-19).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the color complements of Moore with the foreground and background processing of Price because this provides maximum color separation that results in a high contrast between foreground and background (which is of particular relevance in the high contrast images of Price), thus improving the recognition and processing of the foreground and background (see, for example, Moore, paragraph 82; paragraph 140, the last 6 lines; paragraph 151, lines 20-23).
Regarding claim 2, Price in view of Moore teaches the computer-implemented method of claim 1, further comprising: generating a foreground image based on the image and the matte; and processing the foreground image via a trained machine learning model to generate a colorized foreground image that includes the second color (Price, paragraph 93, lines 1-4; paragraphs 94 and 95; paragraph 96, lines 22-34; paragraph 103, lines 1-12).
Regarding claim 3, Price in view of Moore teaches the computer-implemented method of claim 2, further comprising generating a composite image based on the colorized foreground image and an image of another background (Price, paragraph 71, lines 1-9; paragraphs 94 and 95; paragraph 101, lines 4-8; paragraph 102, lines 1-5).
Regarding claim 5, Price in view of Moore teaches the computer-implemented method of claim 2, further comprising training, based on at least one first channel corresponding to the first color from one or more images and at least one second channel corresponding to the second color from the one or more images, a machine learning model to generate the trained machine learning model (Price, paragraph 62, lines 1-11; paragraph 63, lines 1-11; paragraph 69, lines 1-9; paragraph 71; paragraph 72, lines 1-3).
Regarding claim 6, Price in view of Moore teaches the computer-implemented method of claim 1, further comprising performing one or more operations to reduce color crosstalk in the image based on a predetermined color calibration transformation (Price, paragraph 76; paragraph 96, lines 1-14; paragraph 100; Moore, paragraph 140, lines 1-15; paragraph 145; paragraph 150, the last 8 lines; paragraph 151, lines 1-19; the motivation to combine is similar to that discussed above in the rejection of claim 1).
Regarding claim 8, Price in view of Moore teaches the computer-implemented method of claim 1, further comprising training a machine learning model based on the image and the matte (Price, paragraph 62, lines 1-11; paragraph 63, lines 1-11; paragraph 106).
Regarding claim 9, Price in view of Moore teaches the computer-implemented method of claim 1, wherein the second color is one of green, blue, or red, and the first color is one of magenta, yellow, or cyan (Price, paragraph 17; paragraph 100; Moore, paragraph 85; paragraph 150, the last 8 lines; paragraph 151, lines 1-19; as just one example, in Moore the background [second] color may be green, and the foreground [first] color would then comprise its complement, which is magenta; the motivation to combine is similar to that discussed above in the rejection of claim 1).
Regarding claim 10, Price in view of Moore teaches the computer-implemented method of claim 1, wherein the matte comprises one of an alpha matte or a holdout matte (Price, paragraph 16, lines 1-9; paragraph 60; paragraph 96, lines 1-10).
Regarding claim 18, the limitations of this claim substantially correspond to the limitations of claim 1 (except for the media, instructions, and processor, which is taught by Price, fig 8, memory 812, processor 814, instructions 824; paragraph 119, lines 1-7); thus they are rejected on similar grounds.
Regarding claim 19, the limitations of this claim substantially correspond to the limitations of claim 2; thus they are rejected on similar grounds.
Regarding claim 20, Price in view of Moore teaches the one or more non-transitory computer-readable media of claim 18, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform the step of performing one or more operations to at least one of (i) reduce color crosstalk in the image based on a predetermined color calibration transformation, or (ii) subtract a predetermined bounce light from the image based on the matte (Price, paragraph 76; paragraph 96, lines 1-14; paragraph 100; Moore, paragraph 140, lines 1-15; paragraph 145; paragraph 150, the last 8 lines; paragraph 151, lines 1-19; the motivation to combine is similar to that discussed above in the rejection of claim 1).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Price, in view of Moore, and further in view of Zikos et al. (U.S. Patent Application Publication No. 2022/0414820), referred herein as Zikos.
Regarding claim 4, Price in view of Moore teaches the computer-implemented method of claim 3, but does not teach the method, further comprising: computing an optical flow based on the image and one or more other images; and performing one or more operations to add motion blur to the composite image based on the optical flow.
However, in a similar field of endeavor, Zikos teaches a method comprising receiving an image that includes a foreground having a first color and a background with a second color that is contrasted from the first color, and processing the image to generate a foreground image comprising an alpha channel (paragraph 54; paragraphs 134 and 135; paragraphs 151 and 152), and further comprising: computing an optical flow based on the image and one or more other images, and performing one or more operations to add motion blur to the composite image based on the optical flow (paragraphs 114-116; paragraph 132; paragraphs 162-164).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the optical flow and motion blur of Zikos with the image compositing of Price in view of Moore because this helps provide a higher quality output image, especially at the edges, and can improve the separation of background and foreground (see, for example, Zikos, paragraph 7; paragraph 147, the last 5 lines; paragraph 162 ).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Price, in view of Moore, and further in view of Rhodes et al. (U.S. Patent Application Publication No. 2023/0169658), referred herein as Rhodes.
Regarding claim 7, Price in view of Moore teaches the computer-implemented method of claim 1, but does not teach the method, further comprising subtracting a predetermined bounce light from the image based on the matte.
However, in a similar field of endeavor, Rhodes teaches a method comprising receiving an image comprising a foreground and background with different colors, and generating an alpha matte based on the colors (paragraphs 34 and 36; paragraph 53; paragraph 64), further comprising subtracting a predetermined bounce light from the image based on the matte (paragraphs 25 and 40; paragraph 60, lines 1-13; paragraph 61, lines 1-5 and the last 12 lines; paragraph 69, lines 1-8; paragraph 70, lines 1-11).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the bounce light subtraction of Rhodes with the image processing of Price in view of Moore because this improves the image processing and output by removing artifacts and correcting images to prevent noise from being introduced (see, for example, Rhodes, paragraphs 64 and 73).
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Chen (U.S. Patent Application Publication No. 2003/0198382); Apparatus and method for removing background on visual.
Thomas (U.S. Patent Application Publication No. 2005/0057663); Video processing.
Liu (U.S. Patent Application Publication No. 2005/0212820); Method, system, and device for automatic determination of nominal backing color and a range thereof.
Yamada (U.S. Patent Application Publication No. 2010/0061628); Image processing apparatus, image processing method, and program.
Dunn (U.S. Patent Application Publication No. 2011/0193871); Rendering multi-layered image.
Wang (U.S. Patent No. 8,358,691); Methods and apparatus for chatter reduction in video object segmentation using a variable bandwidth search region.
Marison (U.S. Patent Application Publication No. 2014/0002487); Animated visualization of alpha channel transparency.
Vonolfen (U.S. Patent Application Publication No. 2013/0243248); Method for differentiating between background and foreground of scenery and also method for replacing a background in images of a scenery.
Dehais (U.S. Patent Application Publication No. 2014/0055570); Model and method for producing 3D photorealistic models.
Vlahos (U.S. Patent Application Publication No. 2015/0071531); Conversion of an image to a transparency retaining readability and clarity of detail while automatically maintaining color information of broad areas.
Holten (U.S. Patent Application Publication No. 2014/0139546); Data visualization system.
Vlahos (U.S. Patent Application Publication No. 2016/0048991); Method for preventing selected pixels in a background image from showing through corresponding pixels in a transparency layer.
Eklin (U.S. Patent Application Publication No. 2021/0148822); Method of analyzing samples, analyzing device and computer program.
Fallarero (U.S. Patent Application Publication No. 2021/0333198); Method of analyzing liquid samples, microplate reader and computer program.
Benesh (U.S. Patent Application Publication No. 2019/0094554); Visual perception enhancement of displayed color symbology.
Wang (U.S. Patent Application Publication No. 2019/0236788); Fully automated alpha matting for virtual reality systems.
Price (U.S. Patent Application Publication No. 2020/0311946); Interactive image matting using neural networks.
Aydin (U.S. Patent Application Publication No. 2020/0357142); Learning-based sampling for image matting.
Lin (U.S. Patent Application Publication No. 2021/0027470); Utilizing a neural network having a two-stream encoder architecture to generate composite digital images.
Huang (U.S. Patent Application Publication No. 2022/0214892); Foreground element display method and electronic device.
Yu (U.S. Patent Application Publication No. 2022/0262009); Generating refined alpha mattes utilizing guidance masks and a progressive refinement network.
Price (U.S. Patent Application Publication No. 2023/0135978); Generating alpha mattes for digital images utilizing a transformer-based encoder-decoder.
Rhodes (U.S. Patent Application Publication No. 2024/0296612); Preparation systems for efficiently generating alpha mattes and modified digital videos utilizing polarized light.
Wang et al. (Soft scissors: an interactive tool for realtime high quality matting); ACM; 2007.
Grundhofer et al. (Color invariant chroma keying and color spill neutralization for dynamic scenes and cameras); Springer; 2010.
Wang (Robust Chroma Keying System based on Human Visual Perception and Statistical Color Models); Ottawa-Carleton Institute of Electrical and Computer Engineering; 2016.
Cho et al. (Deep Convolutional Neural Network for Natural Image Matting Using Initial Alpha Mattes); IEEE; 2019.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAVID T WELCH whose telephone number is (571)270-5364. The examiner can normally be reached on Monday-Thursday, 8:30-5:30 EST, and alternate Fridays, 9:00-2:30 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, Xiao Wu can be reached on 571-272-7761. 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.
DAVID T. WELCH
Primary Examiner
Art Unit 2613
/DAVID T WELCH/Primary Examiner, Art Unit 2613
Prosecution Insights