# US 8,149,280 B2 · Face detection image processing device, camera device, image 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 8,149,280 B2 - Document ID: US8149280B2 - Status: Granted - Kind: B2 - Application number: 12/364,121 - Filed: 2009-02-02 - Published: 2009-08-20 - Granted: 2012-04-03 - Earliest claimed: 2008-02-15 - Assignees: Sony Corporation - Inventors: Koji Yoda - Web page: https://patentgrep.com/patent/US8149280B2 ## CPC - H04N 5/2628: {Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation} - H04N 5/77: between a recording apparatus and a television camera - H04N 9/8205: {involving the multiplexing of an additional signal and the colour video signal} - H04N 23/611: where the recognised objects include parts of the human body - G06V 40/161: {Detection; Localisation; Normalisation} - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Disclosed herein is an image processing device including: a face detector configured to detect a face from an image given on a basis of detection information; and a processing unit configured to set the detection information of the face detector, receive at least an input image before distortion correction of the image before the distortion correction and an image after the distortion correction, divide an entire image region of the input image, and supply each of the divided images to the face detector on a time-division basis, wherein the face detector detects faces from a face of a maximum size to a face of a minimum size in the entire image in a detectable range. ## Claims ### Claim 1 An image processing device comprising: a face detector configured to detect a face from an image given on a basis of detection information; and a processing unit configured to set the detection information of said face detector, receive at least an input image before distortion correction of the image before the distortion correction and an image after the distortion correction, divide an entire image region of the input image, and supply each of the divided images to said face detector on a time-division basis, wherein said face detector detects faces from a face of a maximum size to a face of a minimum size in the entire image in a detectable range. ### Claim 2 (depends on 1) The image processing device according to claim 1, wherein said processing unit divides said entire image region so as to have an image overlap region on a division boundary line. ### Claim 3 (depends on 1) The image processing device according to claim 1, wherein said processing unit sets said detection information including face sizes in said face detector such that detected face sizes are prevented from coinciding with each other between divided and reduced images. ### Claim 4 (depends on 1) The image processing device according to claim 1, wherein said processing unit performs control for a detected face so as to detect only a peripheral image region of the face on a basis of face detection result information obtained by said face detector. ### Claim 5 (depends on 4) The image processing device according to claim 4, wherein said processing unit has a function of setting a region for detecting a face to a range proportional to size of the face. ### Claim 6 (depends on 4) The image processing device according to claim 4, wherein said processing unit has a function of setting a region for said face detector to detect a face to a range in consideration of an amount of movement estimated from a positional relation of the face in a past. ### Claim 7 (depends on 1) The image processing device according to claim 1, wherein said processing unit controls said face detector to detect motion in the entire image region and detect a face within only a region where the motion occurs as an object. ### Claim 8 (depends on 3) The image processing device according to claim 3, wherein said processing unit controls said face detector to detect motion in the entire image region and detect a face within only a region where the motion occurs as an object. ### Claim 9 (depends on 4) The image processing device according to claim 4, wherein said processing unit controls said face detector to detect motion in the entire image region and detect a face within only a region where the motion occurs as an object. ### Claim 10 A camera device comprising: an image pickup element; an optical system for forming an image of a subject on said image pickup element; and an image processing device capable of subjecting an original image picked up with a wide-angle lens by said image pickup element to distortion correction using a distortion correcting parameter, wherein said image processing device includes a face detector configured to detect a face from an image given on a basis of detection information, and a processing unit configured to set the detection information of said face detector, receive at least an input image before distortion correction of the image before the distortion correction and an image after the distortion correction, divide an entire image region of the input image, and supply each of the divided images to said face detector on a time-division basis, and said face detector detects faces from a face of a maximum size to a face of a minimum size in the entire image in a detectable range. ### Claim 11 (depends on 10) The camera device according to claim 10, wherein said processing unit divides said entire image region so as to have an image overlap region on a division boundary line. ### Claim 12 (depends on 10) The camera device according to claim 10, wherein said processing unit sets said detection information including face sizes in said face detector such that detected face sizes are prevented from coinciding with each other between divided and reduced images. ### Claim 13 (depends on 10) The camera device according to claim 10, wherein said processing unit performs control for a detected face so as to detect only a peripheral image region of the face on a basis of face detection result information obtained by said face detector. ### Claim 14 (depends on 13) The camera device according to claim 13, wherein said processing unit has a function of setting a region for detecting a face to a range proportional to size of the face. ### Claim 15 (depends on 13) The camera device according to claim 13, wherein said processing unit has a function of setting a region for said face detector to detect a face to a range in consideration of an amount of movement estimated from a positional relation of the face in a past. ### Claim 16 (depends on 10) The camera device according to claim 10, wherein said processing unit controls said face detector to detect motion in the entire image region and detect a face within only a region where the motion occurs as an object. ### Claim 17 (depends on 12) The camera device according to claim 12, wherein said processing unit controls said face detector to detect motion in the entire image region and detect a face within only a region where the motion occurs as an object. ### Claim 18 (depends on 13) The camera device according to claim 13, wherein said processing unit controls said face detector to detect motion in the entire image region and detect a face within only a region where the motion occurs as an object. ### Claim 19 An image processing method for detecting a face from an image given on a basis of detection information set in a face detector, said image processing method comprising the steps of: setting said detection information; dividing at least an entire image region before distortion correction of images before the distortion correction and after the distortion correction; and supplying each of the divided images to said face detector on a time-division basis, wherein said face detector detects faces from a face of a maximum size to a face of a minimum size in the entire image in a detectable range. ### Claim 20 A non-transitory computer readable medium having stored thereon computer executable image processing instructions for detecting a face from an image given on a basis of detection information set in a face detector, said image processing instructions comprising: setting said detection information; dividing at least an entire image region before distortion correction of images before the distortion correction and after the distortion correction; and supplying each of the divided images to said face detector on a time-division basis, wherein said face detector detects faces from a face of a maximum size to a face of a minimum size in the entire image in a detectable range.