# US 10,121,068 B2 · Information processing apparatus, information processing method and program > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,068 B2 - Document ID: US10121068B2 - Status: Granted - Kind: B2 - Application number: 15/234,855 - Filed: 2016-08-11 - Published: 2017-02-23 - Granted: 2018-11-06 - Earliest claimed: 2015-08-18 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Shinji Yamamoto; Tomoya Honjo; Hiroshi Tojo - Web page: https://patentgrep.com/patent/US10121068B2 ## CPC - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An information processing apparatus includes a detecting unit, an extracting unit, a managing unit, and a deriving unit. The detecting unit detects an object from an image. The extracting unit extracts a feature amount of the object detected by the detecting unit. The managing unit manages an element in the object detected by the detecting unit in association with the feature amount of the object in the element. The deriving unit derives a reliability indicative of a certainty for identifying an object with respect to the feature amount of the element. ## Claims ### Claim 1 An information processing apparatus comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the information processing apparatus to function as: a detecting unit configured to detect an object from an image, an extracting unit configured to extract a feature amount of the detected object, a deriving unit configured to derive a reliability for an extracted feature amount, wherein the derived reliability is indicative of a certainty for identifying an object with respect to the extracted feature amount, a managing unit configured to manage an element in the detected object in association with the extracted feature amount and the derived reliability, and an identifying unit configured to identify a selected object among a plurality of images, wherein, in a case where the information processing apparatus receives input to identify a selected object based on a search condition that includes a selected feature amount associated with an element, the identifying unit identifies the selected object among the plurality of images based on the search condition, feature amounts associated with elements managed by the managing unit, and derived reliabilities. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, wherein the executed instructions further cause the one or more processors to function as an output unit configured to output the reliability of the selected feature amount of the selected object. ### Claim 3 (depends on 2) The information processing apparatus according to claim 2, wherein the output unit outputs a result of the identification. ### Claim 4 (depends on 2) The information processing apparatus according to claim 2, wherein the feature amounts associated with elements managed by the managing unit and utilized by the identifying unit in the identification is limited to feature amounts having reliabilities equal to or higher than a threshold value among the feature amounts associated with elements managed by the managing unit. ### Claim 5 (depends on 1) The information processing apparatus according to claim 1, wherein the deriving unit derives the reliability based on a number of frames from which the feature amounts are extracted. ### Claim 6 (depends on 1) The information processing apparatus according to claim 1, wherein the deriving unit derives the reliability based on a resolution of a target region from which the feature amount is extracted. ### Claim 7 (depends on 1) The information processing apparatus according to claim 1, wherein the element is one or an arbitrary combination of an orientation of an object, a region of an object, and a category for identifying a feature. ### Claim 8 (depends on 7) The information processing apparatus according to claim 7, wherein the category is at least one of presence/absence of a bag, sunglasses, or a beard, age, sex, height, clothes, or body shape. ### Claim 9 (depends on 1) The information processing apparatus according to claim 1, wherein the extracting unit extracts the feature amount based on color, brightness, or edge of the object. ### Claim 10 (depends on 1) The information processing apparatus according to claim 1, wherein the deriving unit derives, for each element, a reliability indicative of a certainty for identifying an object by using a number of frames from which a feature amount is acquired and a number of pixels of an object for which a feature amount is calculated. ### Claim 11 A method for an information processing apparatus, the method comprising: detecting an object from an image; extracting a feature amount of the detected object; deriving a reliability for an extracted feature amount, wherein the derived reliability is indicative of a certainty for identifying an object with respect to the extracted feature amount; managing an element in the detected object in association with the extracted feature amount and the derived reliability; and identifying a selected object among a plurality of images; wherein, in a case where the information processing apparatus receives input to identify a selected object based on a search condition that includes a selected feature amount associated with an element, identifying includes identifying the selected object among the plurality of images based on the search condition, managed feature amounts associated with elements, and derived reliabilities. ### Claim 12 (depends on 11) The method according to claim 11, further comprising outputting the reliability of the selected feature amount of the selected object. ### Claim 13 (depends on 12) The method according to claim 12, wherein outputting includes outputting a result of the identification. ### Claim 14 (depends on 12) The method according to claim 12, wherein the managed feature amounts associated with elements and utilized in the identification is limited to feature amounts having reliabilities equal to or higher than a threshold value among the managed feature amounts associated with elements. ### Claim 15 (depends on 11) The method according to claim 11, wherein deriving includes deriving the reliability based on a number of frames from which the feature amounts are extracted. ### Claim 16 (depends on 11) The method according to claim 11, wherein deriving includes deriving the reliability based on a resolution of a target region from which the feature amount is extracted. ### Claim 17 (depends on 11) The method according to claim 11, wherein the element is one or an arbitrary combination of an orientation of an object, a region of an object, and a category for identifying a feature, and wherein the category is at least one of presence/absence of a bag, sunglasses, or a beard, age, sex, height, clothes, or body shape. ### Claim 18 (depends on 11) The method according to claim 11, wherein extracting includes extracting the feature amount based on color, brightness, or edge of the object. ### Claim 19 (depends on 11) The method according to claim 11, wherein deriving includes deriving, for each element, a reliability indicative of a certainty for identifying an object by using a number of frames from which a feature amount is acquired and a number of pixels of an object for which a feature amount is calculated. ### Claim 20 A non-transitory computer readable recording medium storing a program to cause an information processing apparatus to perform a method, the method comprising: detecting an object from an image; extracting a feature amount of the detected object; deriving a reliability for an extracted feature amount, wherein the derived reliability is indicative of a certainty for identifying an object with respect to the extracted feature amount; managing an element in the detected object in association with the extracted feature amount and the derived reliability; and identifying a selected object among a plurality of images; wherein, in a case where the information processing apparatus receives input to identify a selected object based on a search condition that includes a selected feature amount associated with an element, identifying includes identifying the selected object among the plurality of images based on the search condition, managed feature amounts associated with elements, and derived reliabilities. ### Claim 21 (depends on 1) The information processing apparatus according to claim 1, wherein, to increase precision of the information processing apparatus in identifying the selected object among the plurality of images, the identifying unit excludes from the identification a feature amount having a reliability derived by the deriving unit that is lower than a predetermined threshold value. ### Claim 22 (depends on 1) The information processing apparatus according to claim 1, wherein the information processing apparatus is an object identification device configured to be in communication with a plurality of video cameras over a network.