发明名称 Image processing device and image processing method for processing an image
摘要 An image processing device includes a facial region extraction unit extracting a facial region, an identification information acquisition unit acquiring identification information for identifying a face in the facial region, and first and second integrated processing units performing integrated processing. The first and second integrated processing units determine a threshold value on the basis of a relationship between an estimated area and a position of the face being tracked, calculate a similarity between a face being tracked and a face pictured in an image to be stored in a predetermined storage period, and determine if the face being tracked and the stored face image are the face of the same person.
申请公布号 US8903123(B2) 申请公布日期 2014.12.02
申请号 US201012954212 申请日期 2010.11.24
申请人 Sony Corporation 发明人 Tsurumi Shingo;Sun Yun;Gotoh Tomohiko
分类号 G06K9/00;G06T7/20 主分类号 G06K9/00
代理机构 Finnegan, Henderson, Farabow, Garrett & Dunner, LLP 代理人 Finnegan, Henderson, Farabow, Garrett & Dunner, LLP
主权项 1. An image processing device comprising: a processing unit; and a non-transitory computer-readable medium coupled to the processing unit storing instructions that, when executed by the processing unit, cause the device to: extract a facial region including a face, after detecting the face pictured in an image;acquire identification information for identifying a face associated with the extracted facial region;perform a first integrated processing by determining if a face being tracked and a face pictured in an image to be stored in a predetermined storage period after vanishing from the image are the face of the same person based on the identification information; andperform a second integrated processing by determining if a face being tracked and a face pictured in an image to be stored in a predetermined storage period after vanishing from the image are the face of the same person based on the identification information in a different manner from that of the first integrated processing, wherein the first integrated processing is performed by determining a threshold value on the basis of a relationship between an estimated area in which the stored face image is predicted to appear and a position of the face being tracked,calculating a similarity between the face being tracked and the stored face image, anddetermining if the face being tracked and the stored face image are the face of the same person based on the calculated similarity, and the threshold value corresponding to the stored face image used in calculating the similarity, andwherein the second integrated processing is performed by calculating a similarity between the face being tracked and the stored face image for a plurality of face directions, anddetermining if the face being tracked and the stored face image are the face of the same person based on the calculated similarity for the plurality of face directions.
地址 Tokyo JP