Photographing apparatus, method and medium using image recognition
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
H04N-005/232
G06K-009/00
G06T-005/00
G06T-007/73
H04N-001/21
출원번호
US-0613304
(2017-06-05)
등록번호
US-10110803
(2018-10-23)
우선권정보
JP-2004-013112 (2004-01-21)
발명자
/ 주소
Ito, Wataru
출원인 / 주소
FUJIFILM Corporation
대리인 / 주소
Sughrue Mion, PLLC
인용정보
피인용 횟수 :
0인용 특허 :
12
초록▼
Processing for judging whether a face is included in a frame is performed, in a predetermined interval, on each of frames included in a moving image of a subject, displayed on a monitor, until the judgment becomes positive. If it is judged that a face is included in a frame, the facial position is d
Processing for judging whether a face is included in a frame is performed, in a predetermined interval, on each of frames included in a moving image of a subject, displayed on a monitor, until the judgment becomes positive. If it is judged that a face is included in a frame, the facial position is detected in the frame, and stored. Then, judgment is made as to whether a face is included in the next frame after predetermined time. If the judgment is positive, the facial position is detected. The previously stored facial position is replaced by the newly detected facial position, and the newly detected facial position is stored. These processes are repeated until photographing operation is performed by operating a release unit.
대표청구항▼
1. A non-transitory computer readable medium of a camera device, the computer readable medium storing a program for causing a processor to execute an image processing method, wherein the camera device generates a moving image of a subject by continuously taking photographs of the subject, the camera
1. A non-transitory computer readable medium of a camera device, the computer readable medium storing a program for causing a processor to execute an image processing method, wherein the camera device generates a moving image of a subject by continuously taking photographs of the subject, the camera device including: a display for displaying information including the moving image,a user interface that initiates a photographing operation to generate a photograph of the subject, the photograph comprising image data; andmemory for storing information including the image data,the program comprising instructions for processing successive frames of the moving image until terminated responsive to a release input from a user, the processing comprising:determining whether a human face is included in a frame;detecting a facial position in the frame if the determining step determines that a face is included in the frame; andstoring the detected facial position in the memory,wherein the determining of whether a human face is included in the frame comprises:determining whether a human face is included in a first frame of the successive frames;if a human face is not determined to be in the first frame, repeating the determining on a next frame of the successive frames; andif a human face is determined to be in the first frame, determining whether a human face is included in a next frame of the successive frames, andwherein the determining of whether a human face is included in the next frame of the successive frames comprises:determining a variation between the first frame and the next frame;if the variation exceeds a threshold, determining whether a human face is included in the next frame of the successive frames by processing each pixel of the next frame; andif the variation does not exceed the threshold, determining whether a human face is included in the next frame by processing only pixels in the next frame located in a region corresponding to the region of the first frame in which the human face was detected. 2. The non-transitory computer readable medium of claim 1, wherein the user interface comprises a button, wherein the release input is generated when the user presses the button . 3. The non-transitory computer readable medium of claim 1, wherein the memory comprises a frame memory for storing the image data. 4. The non-transitory computer readable medium of claim 1, wherein the determining of whether a human face is included in the frame comprises: determining whether a human face is included in a first frame of the successive frames and, if not, repeating the determining on a next frame of the successive frames. 5. The non-transitory computer readable medium of claim 4, wherein the determining of whether a human face is included in the first frame of the successive frames comprises: processing each pixel of the first frame. 6. The non-transitory computer readable medium of claim 4, wherein the determining of whether a human face is included in the first frame of the successive frames comprises: processing each pixel of the first frame to generate a characteristic value indicative of the presence of a human face. 7. The non-transitory computer readable medium of claim 4, wherein the first frame of the successive frames is preceded by a previous frame of the successive frames. 8. The non-transitory computer readable medium of claim 1, wherein the determining of whether a human face is included in the frame includes using reference data obtained by a machine learning technique. 9. The non-transitory computer readable medium of claim 1, wherein the program further comprises instructions for determining whether there is a smile in or near the facial position. 10. The non-transitory computer readable medium of claim 1, wherein the program further comprises instructions for determining whether eyes of the human face are closed, and if the eyes are closed, selecting a frame including a face with open eyes from a previous or subsequent frame of the successive frames. 11. Camera apparatus for generating a photograph of a subject, wherein the camera apparatus generates a moving image of the subject by continuously taking photographs of the subject, the moving image comprising multiple successive frames, with each frame including frame image data representing images in the frame, the camera apparatus comprising: a display for displaying information including the moving image;a release button that, when pressed, initiates a photographing operation to generate the photograph of the subject, the photograph comprising image data;memory for storing information including the image data;a central processing unit; anda computer readable medium storing a program for causing the central processing unit to process the successive frames of the moving image, the program comprising instructions for:image processing frame image data of each frame of the moving image until the release button is determined to have been pressed, the image processing comprising:performing human facial analysis on the frame image data of the frame to determine whether the frame image data includes a human face;detecting a facial position in the frame if the frame image data is determined to include a human face; andstoring the detected facial position in the memory,wherein the performing of human facial analysis comprises:determining whether a human face is included in a first frame of the successive frames;if a human face is not determined to be in the first frame, repeating the determining on a next frame of the successive frames; andif a human face is determined to be in the first frame, determining whether a human face is included in a next frame of the successive frames, andwherein the determining of whether a human face is included in the next frame of the successive frames comprises:determining a variation between the first frame and the next frame;if the variation exceeds a threshold, determining whether a human face is included in the next frame of the successive frames by processing each pixel of the next frame; andif the variation does not exceed the threshold, determining whether a human face is included in the next frame by processing only pixels in the next frame located in a region corresponding to the region of the first frame in which the human face was detected. 12. Camera apparatus of claim 11, further comprising a photography unit. 13. Camera apparatus of claim 11, wherein the memory comprises a frame memory for storing the image data. 14. Camera apparatus of claim 11, wherein the performing of human facial analysis comprises: determining whether a human face is included in a first frame of the successive frames and, if not, repeating the determining on a next frame of the successive frames. 15. Camera apparatus of claim 14, wherein the determining of whether a human face is included in the first frame of the successive frames comprises: processing each pixel of the first frame. 16. Camera apparatus of claim 14, wherein the determining of whether a human face is included in the first frame of the successive frames comprises: processing each pixel of the first frame to generate a characteristic value indicative of the presence of a human face. 17. Camera apparatus of claim 14, wherein the first frame of the successive frames is preceded by a previous frame of the successive frames. 18. Camera apparatus of claim 11, wherein the performing of human facial analysis includes using reference data obtained by a machine learning technique. 19. Camera apparatus of claim 11, wherein the program further comprises instructions for determining whether there is a smile in or near the facial position. 20. Camera apparatus of claim 11, wherein the program further comprises instructions for determining whether eyes of the human face are closed, and if the eyes are closed, selecting a frame including a face with open eyes from a previous or subsequent frame of the successive frames. 21. A photographing method for generating a photograph of a subject, wherein the method comprises: generating a moving image of the subject by continuously taking photographs of the subject with a camera apparatus, the moving image comprising multiple successive frames, with each frame including frame image data representing images in the frame;displaying information including the moving image on a display of the camera apparatus;initiating a photographing operation to generate the photograph of the subject, the photograph comprising image data;storing information including the image data; andprocessing the successive frames of the moving image using a processor of the camera apparatus, the processing including:image processing frame image data of each frame of the moving image until the photographing operation is initiated, the image processing comprising:performing human facial analysis on the frame image data of the frame to determine whether the frame image data includes a human face;detecting a facial position in the frame if the frame image data is determined to include a human face; andstoring the detected facial position in a memory, andwherein the performing human facial analysis comprises:determining whether a human face is included in a first frame of the successive frames;if a human face is not determined to be in the first frame, repeating the determining on a next frame of the successive frames; andif a human face is determined to be in the first frame, determining whether a human face is included in a next frame of the successive frames, andwherein the determining of whether a human face is included in the next frame of the successive frames comprises:determining a variation between the first frame and the next frame;if the variation exceeds a threshold, determining whether a human face is included in the next frame of the successive frames by processing each pixel of the next frame; andif the variation does not exceed the threshold, determining whether a human face is included in the next frame by processing only pixels in the next frame located in a region corresponding to the region of the first frame in which the human face was detected. 22. The method of claim 21, wherein the initiating the photography operation comprises generating a release input. 23. The method of claim 22, wherein the release input is generated in response to a user pressing a button. 24. The method of claim 21, wherein the storing comprises storing the image data in a frame memory. 25. The method of claim 21, wherein the performing human facial analysis comprises: determining whether a human face is included in a first frame of the successive frames and, if not, repeating the determining on a next frame of the successive frames. 26. The method of claim 25, wherein the determining of whether a human face is included in the first frame of the successive frames comprises: processing each pixel of the first frame. 27. The method of claim 25, wherein the determining of whether a human face is included in the first frame of the successive frames comprises: processing each pixel of the first frame to generate a characteristic value indicative of the presence of a human face. 28. The method of claim 25, wherein the first frame of the successive frames is preceded by a previous frame of the successive frames. 29. The method of claim 21, wherein the performing human facial analysis includes using reference data obtained by a machine learning technique. 30. The method of claim 21, further comprising determining whether there is a smile in or near the facial position. 31. The method of claim 21, further comprising determining whether eyes of the human face are closed, and if the eyes are closed, selecting a frame including a face with open eyes from a previous or subsequent frame of the successive frames of the frame.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (12)
Badique Eric (Nurnberg DEX), Circuit arrangement for recognizing a human face.
Prasad K. Venkatesh (Cupertino CA) Stork David G. (Stanford CA), Facial feature extraction method and apparatus for a neural network acoustic and visual speech recognition system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.