Image recomposition from face detection and facial features
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/46
G06K-009/00
출원번호
US-0284229
(2011-10-28)
등록번호
US-9008436
(2015-04-14)
발명자
/ 주소
Ptucha, Raymond William
출원인 / 주소
Intellectual Ventures Fund 83 LLC
인용정보
피인용 횟수 :
0인용 특허 :
12
초록▼
A computer implemented method for modifying a digital image comprising identifying two or more individual regions in the digital image that each include a human face, and digitally defining at least one combined region that includes the two or more individual regions wherein at least one border of t
A computer implemented method for modifying a digital image comprising identifying two or more individual regions in the digital image that each include a human face, and digitally defining at least one combined region that includes the two or more individual regions wherein at least one border of the at least one combined region is collinear with a border of one of the individual regions.
대표청구항▼
1. A method, comprising: identifying, by a computing device, two or more individual regions in a digital image that each include a face;assigning, by the computing device, a fitness score to each of the two or more individual regions, wherein a fitness score for a particular region is based on a fac
1. A method, comprising: identifying, by a computing device, two or more individual regions in a digital image that each include a face;assigning, by the computing device, a fitness score to each of the two or more individual regions, wherein a fitness score for a particular region is based on a facial expression characteristic of the face corresponding to the particular region and an exposure amount of the face corresponding to the particular region, and wherein the facial expression characteristic comprises a gaze direction; defining, by the computing device, a combined region based on the fitness score, wherein the combined region includes the two or more individual regions, wherein a border of the combined region is collinear with a border of one of the two or more individual regions;determining, by the computing device, an average gaze direction based on the gaze direction of faces associated with the two or more individual regions; anddefining, by the computing device, a gaze region that is based on the average gaze direction. 2. The method of claim 1, wherein each border of the combined region is collinear with a border of the two or more individual regions. 3. The method of claim 1, further comprising modifying the digital image such that the combined region satisfies a rule of thirds composition. 4. The method of claim 3, wherein the rule of thirds composition is based on an adjustable parameter that specifies an amount of expansion of an individual region. 5. The method of claim 1, further comprising modifying an aspect ratio of the digital image, wherein the modifying comprises deleting a portion of the digital image such that the combined region is preserved without removing any of its pixels. 6. The method of claim 1, further comprising modifying an aspect ratio of the digital image such that a portion of only one of the two or more individual regions is deleted, wherein the modifying the aspect ratio is responsive to determining that modifying the aspect ratio of the digital image cannot be completed together with preserving the combined region. 7. The method of claim 1, further comprising detecting and issuing a notification that a portion of the combined region would be deleted if a preselected modification of the digital image is executed. 8. The method of claim 7, wherein the preselected modification comprises modifying an aspect ratio of the digital image. 9. The method of claim 1, further comprising determining a size of each of the two or more individual regions, wherein determining the size of each of the two or more individual regions comprises excluding at least one of the two or more individual regions from the combined region if the size of the at least one of the two or more individual regions is smaller than a largest one of the two or more individual regions by a preselected magnitude. 10. The method of claim 9, wherein the size of each of the two or more individual regions is determined by either an area or a width of each of the two or more individual regions. 11. The method of claim 1, further comprising: ignoring at least one of the two or more individual regions whose fitness score is below a preselected threshold, wherein the combined region includes two or more individual regions whose fitness score is above the preselected threshold. 12. The method of claim 11, wherein the fitness score for a particular region is further based on a size and location of the face corresponding to the particular region, and wherein the facial expression characteristic is further based on at least one of an eye blink, an expression, a pose, an occlusion, sharpness, or contrast. 13. The method of claim 1, further comprising storing data for identifying the combined region, wherein the data is stored in association with the digital image. 14. The method of claim 1, further comprising zooming in or out of the combined region by a preselected amount to form a modified digital image. 15. The method of claim 1, further comprising determining a width of at least one of the two or more individual regions including determining a size of a padding region based on the determined width, wherein the determined padding region corresponds to the at least one of the two or more individual regions. 16. The method of claim 1, further comprising modifying an aspect ratio of the digital image such that equal amounts of the combined region are cropped from opposing sides of the combined region, wherein the modifying the aspect ratio is responsive to determining that modifying the aspect ratio of the digital image cannot be completed together with preserving the combined region without removing any of its pixels. 17. The method of claim 16, further comprising: detecting that a portion of the combined region would be cropped if a preselected modification of the digital image is executed; andissuing a notification based on the detecting that the portion of the combined region would be cropped if the preselected modification of the digital image is executed. 18. The method of claim 1, further comprising modifying an aspect ratio of the digital image such that about forty percent of a total amount cropped from the digital image is cropped from a top border of the digital image, wherein the modifying the aspect ratio is responsive to determining that modifying the aspect ratio of the digital image cannot be completed together with preserving the combined region without removing any of its pixels. 19. A system comprising: a processor configured to: identify two or more individual regions in a digital image that each include a face;assign a fitness score to each of the two or more individual regions, wherein a fitness score for a particular region is based on a facial expression characteristic of the face corresponding to the particular region and an exposure amount of the face corresponding to the particular region, and wherein the facial expression characteristic comprises a gaze direction;define a combined region that includes the two or more individual regions, wherein a border of the combined region is collinear with a border of one of the two or more individual regions;determine an average gaze direction based on the gaze direction of faces associated with the two or more individual regions; anddefine a gaze region that is based on the average gaze direction. 20. A non-transitory computer-readable medium having instructions stored thereon, the instructions comprising: instructions to identify two or more individual regions in a digital image that each include a face;instructions to assign a fitness score to each of the two or more individual regions, wherein a fitness score for a particular region is based on a facial expression characteristic of the face corresponding to the particular region and an exposure amount of the face corresponding to the particular region, and wherein the facial expression characteristic comprises a gaze direction;instructions to define a combined region that includes the two or more individual regions, wherein a border of the combined region is collinear with a border of one of the two or more individual regions;instructions to determine an average gaze direction based on the gaze direction of the faces associated with the two or more individual regions; andinstructions to define a gaze region that is based on the average gaze direction. 21. The method of claim 1, further comprising determining a vector indicating a gaze orientation of the face corresponding to each of the two or more individual regions, wherein the gaze direction is based on the determined vector. 22. The method of claim 1, wherein the gaze region does not include the combined region. 23. The method of claim 1, wherein the gaze region comprises a region of the digital image that extends from the border of the combined region to a point on the digital image that is in the average gaze direction. 24. The method of claim 1, further comprising determining, by the computing device, an output image that includes the combined region and the gaze region.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (12)
Atkins, C. Brian, Arranging graphic objects on pages.
Steinberg, Eran; Prilutsky, Yury; Corcoran, Peter; Bigioi, Petronel, Perfecting of digital image capture parameters within acquisition devices using face detection.
Luo, Jiebo; Gray, Robert T.; Gindele, Edward B., Producing an image of a portion of a photographic image onto a receiver using a digital image of the photographic image.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.