Ex Parte He et alDownload PDFPatent Trial and Appeal BoardAug 8, 201613433948 (P.T.A.B. Aug. 8, 2016) Copy Citation UNITED STA TES p A TENT AND TRADEMARK OFFICE APPLICATION NO. FILING DATE 13/433,948 03/29/2012 22879 7590 08/10/2016 HP Inc, 3390 E. Harmony Road Mail Stop 35 FORT COLLINS, CO 80528-9544 FIRST NAMED INVENTOR Lulu He UNITED STATES DEPARTMENT OF COMMERCE United States Patent and Trademark Office Address: COMMISSIONER FOR PATENTS P.O. Box 1450 Alexandria, Virginia 22313-1450 www .uspto.gov ATTORNEY DOCKET NO. CONFIRMATION NO. 82900065 9870 EXAMINER HARANDI, SIAMAK ART UNIT PAPER NUMBER 2665 NOTIFICATION DATE DELIVERY MODE 08/10/2016 ELECTRONIC Please find below and/or attached an Office communication concerning this application or proceeding. The time period for reply, if any, is set in the attached communication. Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the following e-mail address( es): ipa.mail@hp.com barbl@hp.com yvonne.bailey@hp.com PTOL-90A (Rev. 04/07) UNITED STATES PATENT AND TRADEMARK OFFICE BEFORE THE PATENT TRIAL AND APPEAL BOARD Ex parte LULU HE, FENG TANG, and QIAN LIN Appeal2014-008847 Application 13/433,948 Technology Center 2600 Before CARLA M. KRIVAK, HUNG H. BUI, and MICHAEL M. BARRY, Administrative Patent Judges. KRIVAK, Administrative Patent Judge. DECISION ON APPEAL Appellants appeal under 35 U.S.C. § 134(a) from a final rejection of claims 1-20. 1 We have jurisdiction under 35 U.S.C. § 6(b ). We affirm. 1 The Examiner has noted claim 4 is objected to but would be allowable if rewritten in independent forms including all of the limitations of the base claims and any intervening claims (Final Act. 19). Appeal2014-008847 Application 13/433,948 STATEMENT OF THE CASE Appellants' invention is directed to an image segmentation system defining a first discriminative classifier and a second discriminative classifier (Abstract). Independent claim 1, reproduced below, is exemplary of the subject matter on appeal. 1. An image segmentation method, comprising: identifying a reference segment of an object; defining a first discriminative classifier associated with a first segment of the object in an image based on a first foreground sample region associated with the first segment of the object in the image and a first background sample region associated with the first segment of the object in the image, wherein a location of the first foreground sample region and the first background sample region are selected relative to the reference segment; defining a second discriminative classifier associated with a second segment of the object based on a second foreground sample region associated with the second segment of the object in the image and a second background sample region associated with the second segment of the object in the image, wherein a location of the second foreground sample region and the second background sample region are selected relative to the reference segment; identifying at least a portion of the first segment using the first discriminative classifier; and identifying at least a portion of the second segment using the second discriminative classifier. REFERENCES and REJECTIONS The Examiner rejected claims 1-3, 6-14, and 16-19 under 35 U.S.C. 2 Appeal2014-008847 Application 13/433,948 § 103(a) based upon the teachings of Dollar (Multiple Component Learning for Object Detection, Computer Vision-ECCV (2008)) and Luo (US 6,697,502 B2; Feb. 24, 2004) (Final Act. 5-17). The Examiner rejected claims 5, 15, and 20 under 35 U.S.C. § 103(a) based upon the teachings of Dollar and Gokturk (US 8,315,442 B2; Nov. 20, 2012) (Final Act. 17-19). ANALYSIS Appellants assert Dollar does not "sample foreground and background regions associated with particular segments of an object" (App. Br. 9). Thus, Appellants contend, Dollar does not utilize a reference segment (App. Br. 10). Appellants then assert Luo does not cure the deficiencies of Dollar as Luo detects skin regions by comparing an average color of a region to a predetermined distribution and does not "utilize reference segments, background samples, and/or foreground samples" as claimed (App. Br. 13). We do not agree. We agree with and adopt the Examiner's findings as our own (Final Act. 5-19; Ans. 3-8). Particularly, the Examiner relies on Dollar for disclosing classifying regions based on background and foreground regions (patches) and Luo for determining a reference region and other regions referenced to the reference region (Ans. 5---6). Thus, applying Luo's teachings to Dollar's system to identify regions that can be individually classified and then combined to identify an object, would result in Appellants' claimed invention (id.). We further note paragraph 1016 of Appellants' Specification states "[ o ]ften, reference segments are visually distinctive or have visual properties that can be identified from other 3 Appeal2014-008847 Application 13/433,948 portions of an image. As examples, the face of a person, the corolla of a flower, and the license plate of an automobile can be reference segments." Thus, Appellants' example of reference segments is broad enough to cover the reference regions disclosed in Luo (Ans. 5). Appellants' arguments, for the most part, recite the claims, state what each reference teaches, and then assert the reference does not disclose the claimed invention, without responding to the Examiner's findings (App. Br. 8-20). For example, the Examiner finds: Luo discloses detecting a potential face (reference segment) using skin/color detection. Then Luo detects human parts which are associated with the face (reference segment) through the "link nodes", in which they are relatively associated with the face (reference segment). This teaching of Luo, when used to modify Dollar's system, would allow the combination of Dollar and Luo to function as the claimed invention. (Final Act. 3) Appellants' response merely asserts the two references cannot be combined without providing persuasive reasoning or argument as to why and how the Examiner erred (see, e.g., App. Br. 13-19). Further, Appellants appear to be arguing the references separately: Appellants argue Luo does not disclose background and foreground sample features, however, the Examiner relies on Dollar for these features (App. Br. 18; Final Act. 4--6; Ans. 6). Thus, on this record, we are not persuaded the Examiner's reading of the claims on the cited combination of references is overly broad, unreasonable, or inconsistent with the Specification. We find the weight of the evidence supports the Examiner's ultimate legal conclusion of obviousness and, therefore, sustain the Examiner's rejection of independent 4 Appeal2014-008847 Application 13/433,948 claims 1, 9, and 16, argued together, dependent claims 2, 3, 6-8, 10-14, and 17-19 dependent therefrom, and claims 5, 15, and 20 not separately argued (App. Br. 20). DECISION The Examiner's decision rejecting claims 1-20 is affirmed. No time period for taking any subsequent action in connection with this appeal may be extended under 37 C.F.R. § 1.136(a)(l )(iv). AFFIRMED 5 Copy with citationCopy as parenthetical citation