Detecting orientation of digital images using face detection information
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/32
G06K-009/00
H04N-005/225
출원번호
US-0330480
(2011-12-19)
등록번호
US-8391645
(2013-03-05)
발명자
/ 주소
Steinberg, Eran
Prilutsky, Yury
Corcoran, Peter
Bigioi, Petronel
Blonk, Leo
Gângea, Mihnea
Vertan, Constantin
출원인 / 주소
DigitalOptics Corporation Europe Limited
인용정보
피인용 횟수 :
2인용 특허 :
3
초록▼
A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highl
A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.
대표청구항▼
1. A method of detecting an orientation of a digital image using statistical classifier techniques, comprising: using a processor;acquiring a digital image;detecting an object within the digital image;cropping the digital image including selecting an object region that includes said object within th
1. A method of detecting an orientation of a digital image using statistical classifier techniques, comprising: using a processor;acquiring a digital image;detecting an object within the digital image;cropping the digital image including selecting an object region that includes said object within the digital image and excludes one or more regions of the digital image outside of said object region to obtain a cropped image including the object region;applying a set of object detection classifiers to the cropped image in a first orientation and determining a first level of match between said cropped image at said first orientation and said classifiers;rotating said cropped image to a second orientation to obtain a rotated image, applying the classifiers to said rotated image at said second orientation, and determining a second level of match between said rotated image at said second orientation and said classifiers;comparing said first and second levels of match between said classifiers and said cropped image and between said classifiers and said rotated image, respectively; anddetermining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match. 2. The method of claim 1, further comprising, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof. 3. The method of claim 1, further comprising orienting said classifiers at selected orientations. 4. The method of claim 1, further comprising: generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object; andtracking said object within said collection of low resolution images, and wherein said applying said set of object detection classifiers comprises applying said set of object detection classifiers to at least one image of the collection of low resolution images. 5. A method of detecting an orientation of a digital image using statistical classifier techniques comprising: using a processor;acquiring a digital image;detecting an object within the digital image;cropping the digital image including selecting an object region that includes said object within the digital image and excludes one or more regions of the digital image outside of said object region to obtain a cropped image including said object region;applying a set of object detection classifiers to the cropped image in a first orientation and determining a first level of match between said cropped image at said first orientation and said classifiers;rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said cropped image at said first orientation, and determining a second level of match between said cropped image at said first orientation and said classifiers rotated said first amount;comparing said first and second levels of match between said classifiers and said digital image and between said rotated classifiers and said cropped image, respectively; anddetermining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said digital image. 6. The method of claim 5, further comprising, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof. 7. The method of claim 5, wherein said classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations. 8. The method of claim 5, further comprising: generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object; andtracking said object within said collection of low resolution images, andwherein said applying said set of object detection classifiers comprises applying said set of object detection classifiers to at least one image of the collection of low resolution images. 9. One or more non-transitory computer readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of detecting an orientation of a digital image using statistical classifier techniques, the method comprising: applying a set of object detection classifiers to a digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;cropping the digital image including selecting an object region within the digital image that includes an object and excludes one or more regions of the digital image outside of said object region to obtain a cropped image including said object region;applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;rotating said cropped image to a second orientation, applying the classifiers to the rotated image at said second orientation, and determining a second level of match between the rotated image at said second orientation and said classifiers;comparing said first and second levels of match between said classifiers and said cropped image and between said classifiers and said rotated image, respectively; anddetermining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match. 10. The one or more storage devices of claim 9, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof. 11. The one or more storage devices of claim 9, wherein said classifiers are oriented at known orientations. 12. The one or more storage devices of claim 9, wherein the method further comprises: generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object; andtracking said object within said collection of low resolution images, and wherein said applying said set of object detection classifiers comprises applying said set of object detection classifiers to at least one image of the collection of low resolution images. 13. One or more non-transitory computer readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of detecting an orientation of a digital image using statistical classifier techniques, the method comprising: applying a set of object detection classifiers to a digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;cropping the digital image including selecting an object region within the digital image that includes an object and excludes one or more regions of the digital image outside of said object region to obtain a cropped image including said object region;applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said cropped image at said first orientation, and determining a second level of match between said cropped image at said first orientation and said classifiers rotated said first amount;comparing said first and second levels of match between said classifiers and said cropped image and between said rotated classifiers and said cropped image, respectively; anddetermining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said digital image. 14. The one or more storage devices of claim 13, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof. 15. The one or more storage devices of claim 13, wherein said classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations. 16. The one or more storage devices of claim 13, wherein the method further comprises: generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object; andtracking said object within said collection of low resolution images, and wherein said applying said set of object detection classifiers comprises applying said set of object detection classifiers to at least one image of the collection of low resolution images. 17. A portable digital camera, comprising: one or more optics and a sensor for acquiring a digital image,a processor, andone or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of detecting an orientation of an object within the digital image using statistical classifier techniques, wherein the method comprises: applying a set of object detection classifiers to the digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;cropping the digital image including selecting an object region within the digital image that includes said object and excludes one or more regions of the digital image outside of said object region to obtain a cropped image including said object region;applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;rotating said cropped image to a second orientation, applying the classifiers to the rotated image at said second orientation, and determining a second level of match between the rotated image at said second orientation and said classifiers;comparing said first and second levels of match between said classifiers and said cropped image and between said classifiers and said rotated image, respectively; anddetermining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match. 18. The camera of claim 17, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof. 19. The camera of claim 17, wherein said classifiers are oriented at known orientations. 20. The camera of claim 17, wherein the method further comprises: generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object; andtracking said object within said collection of low resolution images, and wherein said applying said set of object detection classifiers comprises applying said set of object detection classifiers to at least one image of the collection of low resolution images. 21. A portable digital camera, comprising: one or more optics and a sensor for acquiring a digital image,a processor, andone or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of detecting an orientation of an object within the digital image using statistical classifier techniques, wherein the method comprises: applying a set of object detection classifiers to the digital image in a first orientation and determining a first level of match between said digital image at said first orientation and said classifiers;cropping the digital image including selecting an object region within the digital image that includes said object and excludes one or more regions of the digital image outside of said object region to obtain a cropped image including said object region;applying said classifiers to said cropped image and determining said first level of match between said cropped image and said classifiers;rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said cropped image at said first orientation, and determining a second level of match between said cropped image at said first orientation and said classifiers rotated said first amount;comparing said first and second levels of match between said classifiers and said cropped image and between said rotated classifiers and said cropped image, respectively; anddetermining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said digital image. 22. The camera of claim 21, wherein the method further comprises, prior to applying said classifiers to said cropped image, color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, further cropping, or combinations thereof. 23. The camera of claim 21, wherein said classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations. 24. The camera of claim 9, wherein the method further comprises: generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object; andtracking said object within said collection of low resolution images, and wherein said applying said set of object detection classifiers comprises applying said set of object detection classifiers to at least one image of the collection of low resolution images. 25. A method of detecting an orientation of an object within a main digital image using statistical classifier techniques, comprising: using a processor;generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including an object;tracking said object within said collection of low resolution images;acquiring a main digital image;applying a set of object detection classifiers to at least one image of the collection of low resolution images in a first orientation;determining a first level of match between a same or subsequent image of the collection of low resolution images at said first orientation and said classifiers;rotating said same or subsequent image to a second orientation to obtain a rotated image,applying the classifiers to said rotated image at said second orientation;determining a second level of match between said rotated image at said second orientation and said classifiers;comparing said first and second levels of match between said classifiers and said same or subsequent image and between said classifiers and said rotated image, respectively; anddetermining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match. 26. The method of claim 25, further comprising, prior to applying said classifiers to said same or subsequent image, applying color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, or cropping, or combinations thereof. 27. The method of claim 25, further comprising orientating said classifiers at known orientations. 28. A method of detecting an orientation of an object within a main digital image using statistical classifier techniques comprising: using a processor;generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including an object;tracking said object within said collection of low resolution images;acquiring a main digital image;applying a set of object detection classifiers to at least one image of the collection of low resolution images in a first orientation;determining a first level of match between a same or subsequent image of the collection of low resolution images at said first orientation and said classifiers;rotating said set of classifiers a first predetermined amount,applying the classifiers rotated said first amount to said same or subsequent image at said first orientation,determining a second level of match between said same or subsequent image at said first orientation and said classifiers rotated said first amount;comparing said first and second levels of match between said classifiers and said digital image and between said rotated classifiers and said same or subsequent image, respectively; anddetermining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said main digital image. 29. The method of claim 28, further comprising, prior to applying said classifiers to said same or subsequent image, applying color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, or cropping, or combinations thereof. 30. The method of claim 28, wherein said classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations. 31. One or more non-transitory computer readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of detecting an orientation of an object within a main digital image using statistical classifier techniques, the method comprising: using a processor;generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including said object;tracking said object within said collection of low resolution images;acquiring a main digital image;applying a set of object detection classifiers to at least one image of the collection of low resolution images in a first orientation;determining a first level of match between a same or subsequent image of the collection of low resolution images at said first orientation and said classifiers;rotating said same or subsequent image to a second orientation to obtain a rotated image,applying the classifiers to said rotated image at said second orientation, anddetermining a second level of match between said rotated image at said second orientation and said classifiers;comparing said first and second levels of match between said classifiers and said same or subsequent image and between said classifiers and said rotated image, respectively; anddetermining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match. 32. The one or more storage devices of claim 31, wherein the method further comprises, prior to applying said classifiers to said same or subsequent image, applying color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, or cropping, or combinations thereof. 33. The one or more storage devices of claim 31, wherein said classifiers are oriented at known orientations. 34. One or more non-transitory computer readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of detecting an orientation of an object within a main digital image using statistical classifier techniques, the method comprising: using a processor;generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including an object;tracking said object within said collection of low resolution images;acquiring a main digital image;applying a set of object detection classifiers to at least one image of the collection of low resolution images in a first orientation;determining a first level of match between a same or subsequent image of the collection of low resolution images at said first orientation and said classifiers;rotating said set of classifiers a first predetermined amount, applying the classifiers rotated said first amount to said same or subsequent image at said first orientation, anddetermining a second level of match between said same or subsequent image at said first orientation and said classifiers rotated said first amount;comparing said first and second levels of match between said classifiers and said digital image and between said rotated classifiers and said same or subsequent image, respectively; anddetermining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said main digital image. 35. The one or more storage devices of claim 34, wherein the method further comprises, prior to applying said classifiers to said same or subsequent image, applying color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, or cropping, or combinations thereof. 36. The one or more storage devices of claim 34, wherein said classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations. 37. A portable digital camera, comprising: one or more optics and a sensor for acquiring a digital image,a processor, andone or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of detecting an orientation of an object within a main digital image using statistical classifier techniques, wherein the method comprises: using a processor;generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including an object;tracking said object within said collection of low resolution images;acquiring a main digital image;applying a set of object detection classifiers to at least one image of the collection of low resolution images in a first orientation;determining a first level of match between a same or subsequent image of the collection of low resolution images at said first orientation and said classifiers;rotating said same or subsequent image to a second orientation to obtain a rotated image,applying the classifiers to said rotated image at said second orientation, anddetermining a second level of match between said rotated image at said second orientation and said classifiers;comparing said first and second levels of match between said classifiers and said same or subsequent image and between said classifiers and said rotated image, respectively; anddetermining which of the first orientation and the second orientations has a greater probability of being a correct orientation based on which of the first and second levels of match, respectively, comprises a higher level of match. 38. The camera of claim 37, wherein the method further comprises, prior to applying said classifiers to said same or subsequent image, applying color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, or cropping, or combinations thereof. 39. The camera of claim 37, wherein said classifiers are oriented at known orientations. 40. A portable digital camera, comprising: one or more optics and a sensor for acquiring a digital image,a processor, andone or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of detecting an orientation of an object within a main digital image using statistical classifier techniques, wherein the method comprises: using a processor;generating in-camera, capturing or otherwise obtaining in-camera a collection of low resolution images including an object;tracking said object within said collection of low resolution images;acquiring a main digital image;applying a set of object detection classifiers to at least one image of the collection of low resolution images in a first orientation;determining a first level of match between a same or subsequent image of the collection of low resolution images at said first orientation and said classifiers;rotating said set of classifiers a first predetermined amount,applying the classifiers rotated said first amount to said same or subsequent image at said first orientation, anddetermining a second level of match between said same or subsequent image at said first orientation and said classifiers rotated said first amount;comparing said first and second levels of match between said classifiers and said digital image and between said rotated classifiers and said same or subsequent image, respectively; anddetermining which of the first and second levels of match, respectively, comprises a higher level of match in order to determine whether said first orientation is a correct orientation of said main digital image. 41. The camera of claim 40, wherein the method further comprises, prior to applying said classifiers to said same or subsequent image, applying color conversion, edge enhancement, blurring, sharpening, tone reproduction correction, exposure correction, gray scale transformation, region segmentation, or cropping, or combinations thereof. 42. The camera of claim 40, wherein said classifiers are initially oriented at known orientations and, when rotated by said first and second amounts, are rotated to different known orientations.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (3)
Ray, Lawrence A.; Nicponski, Henry, Face detecting camera and method.
Mashimo Yukio (Tokyo JA) Sakurada Nobuaki (Kanagawa JA) Ito Tadashi (Kanagawa JA) Ito Fumio (Kanagawa JA) Shinoda Nobuhiko (Tokyo JA), System for exposure measurement and/or focus detection by means of image senser.
Tertitski, Leonid M.; Chu, Schubert S.; Assaf, Shay; Vellore, Kim R.; Cong, Zhepeng, System and method to detect substrate and/or substrate support misalignment using imaging.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.