A computer-implemented method for organizing images including receiving an image that includes a representation of a human face; generating a correlation value indicating a likelihood that the human face corresponds to a stored facial profile associated with one or more profile images including a hu
A computer-implemented method for organizing images including receiving an image that includes a representation of a human face; generating a correlation value indicating a likelihood that the human face corresponds to a stored facial profile associated with one or more profile images including a human face; evaluating the received image and the generated correlation value to determine, depending on a result of the evaluating, whether the image corresponds to the stored facial profile; associating the received image with the stored facial profile; and storing an indication of the associating.
대표청구항▼
1. A computer-implemented method for organizing images, the computer-implemented method comprising: receiving an image that includes a representation of a human face;generating a correlation value indicating a likelihood that the human face represented in the received image corresponds to a first st
1. A computer-implemented method for organizing images, the computer-implemented method comprising: receiving an image that includes a representation of a human face;generating a correlation value indicating a likelihood that the human face represented in the received image corresponds to a first stored facial profile, where the first stored facial profile is associated with two or more profile images each including a representation of a first human face corresponding to a same individual;evaluating the received image and the generated correlation value to determine, depending on a result of the evaluating, whether the received image corresponds to the first stored facial profile;in response to determining that the received image corresponds to the first stored facial profile, associating the received image with the first stored facial profile;deriving a potential correspondence between an additional human face represented in the received image and the first stored facial profile; andignoring the derived potential correspondence based on the generated correlation value and the first human face corresponding to the first stored facial profile. 2. The computer-implemented method of claim 1, wherein the correlation value indicates that the received image corresponds to another stored facial profile, and wherein evaluating further comprises evaluating first metadata of the received image and second metadata of the two or more profile images associated with the first stored facial profile. 3. The computer-implemented method of claim 1, wherein the two or more profile images associated with the first stored facial profile are obtained from an address book application; andwherein the first stored facial profile is generated based on the two or more profile images and the profile information. 4. The computer-implemented method of claim 1, further comprising: prompting, based on the evaluating, a user for confirmation that the human face represented in the received image corresponds to the first stored facial profile; andaccepting, in response to the prompting, confirmation that the human face represented in the received image corresponds to the first stored facial profile. 5. The computer-implemented method of claim 4, wherein accepting further comprises accepting via a user interface having an affirmative response option and a negative response option. 6. The computer-implemented method of claim 1, further comprising: accessing detection information indicating less than a 90% likelihood that the image represents a human face;establishing that the image depicts skin-tone colors and sharp image details; andconfirming, based on the establishing, that the image represents a human face. 7. The computer-implemented method of claim 6, further comprising: selecting the received image as a key image based on one or more of the detection information, the received image, or the correlation value; anddisplaying the key image as an icon for the first stored facial profile. 8. The computer-implemented method of claim 7, wherein the received image comprises one or more selected from a group consisting of a sharpness indication, a capture date, and an image resolution of the received image. 9. The computer-implemented method of claim 7, wherein the detection information comprises one or more selected from a group consisting of a distance from the human face represented in the received image to another human face depicted in the received image, and an angle of the human face relative to the received image. 10. The computer-implemented method of claim 1, the computer-implemented method further comprising: presenting an indication of the first stored facial profile and an indication of a second stored facial profile in a user interface, wherein the second stored facial profile includes one or more images representing a second human face;receiving an indication in the user interface associating the first stored facial profile with the second stored facial profile; andgenerating a combined album including one or more images from the first stored facial profile and one or more images from the second stored facial profile. 11. The computer-implemented method of claim 1, further comprising: receiving unsorted images representing human faces, unsorted image information, and unsorted correlation values indicating likelihoods that the human faces correspond to the stored facial profile;establishing an initial correlation value threshold;grouping the unsorted images based on the initial correlation value threshold and the unsorted correlation values;deriving a revised correlation threshold based on amounts of unsorted images grouped together and a total number of groups of unsorted images;regrouping the unsorted images based on the revised correlation threshold and the unsorted correlation values; andassociating one or more groups of unsorted images with the first stored facial profile based on the regrouping. 12. A system comprising: a user interface device;a storage device operable to store executable software instructions and image data; andone or more computers operable to interact with the user interface device and the storage device, and to perform operations comprising: receiving an image that includes a representation of a first human face and a second human face;generating a correlation value indicating a likelihood that the first human face represented in the received image corresponds to a first stored facial profile, where the first stored facial profile is associated with two or more profile images each including a representation of the first human face corresponding to the same individual;deriving a potential correspondence between the second human face and the first stored facial profile;ignoring the derived potential correspondence based on the generated correlation value and the first human face corresponding to the first stored facial profile;evaluating the received image and the generated correlation value to determine, depending on a result of the evaluating, whether the received image corresponds to the first stored facial profile; andin response to determining that the received image corresponds to the first stored facial profile, displaying, using the user interface device, the received image in association with the first stored facial profile. 13. The system of claim 12, further comprising: an external input operable to receive data, and to perform input operations comprising:obtaining the two or more profile images and profile information associated with the two or more profile images through the external input. 14. The system of claim 13, the operations further comprising: generating the first stored facial profile based on the obtained two or more profile images and the profile information. 15. The system of claim 13, wherein the external input comprises an address book application adapter for obtaining the two or more profile images and the profile information from an address book application. 16. The system of claim 12, the operations further comprising: prompting, based on the determining, a user via the user interface device for confirmation that the first human face represented in the received image corresponds to the first stored facial profile; andaccepting, in response to the prompting, confirmation via the user interface device that the first human face represented in the received image corresponds to the first stored facial profile. 17. The system of claim 12, the operations further comprising: selecting the received image as a key image based on one or more of the received image or the correlation value; anddisplaying the key image as an icon in association with the first stored facial profile. 18. The system of claim 17, wherein the received image comprises one or more of a sharpness indication, a capture date, or an image resolution of the received image. 19. The system of claim 12, further comprising: receiving unsorted images representing human faces with associated correlation values indicating likelihoods that the human faces correspond to the first stored facial profile;establishing an initial correlation value threshold;grouping the unsorted images based on the initial correlation value threshold and the associated correlation values;deriving a revised correlation threshold based on numbers of unsorted images grouped together and a total number of groups of unsorted images;regrouping the unsorted images based on the revised correlation threshold and the unsorted correlation values; andassociating one or more groups of unsorted images with the first stored facial profile based on the regrouping. 20. The system of claim 12, the system further comprising: presenting the first stored facial profile and a second stored facial profile through the user interface device, wherein the second stored facial profile includes one or more images representing a second human face;receiving an indication through the user interface device to associate the first stored facial profile with the second stored facial profile; andgenerating a combined album including one or more profile images from the first stored facial profile and the second stored facial profile. 21. A computer program product comprising a non-transitory computer useable medium having computer readable instructions therein for organizing images by correlating faces, the computer program product comprising computer readable instruction devices configured to cause a computer system to: receive an image including a representation of a human face;generate a correlation value indicating a likelihood that the human face represented in the received image corresponds to a first stored facial profile, where the first stored facial profile is associated with two or more profile images each including a representation of a first human face corresponding to a same individual;determine, using the received image and the facial profile, that the received image corresponds to the first facial profile;derive a potential correspondence between a second human face, represented in the received image, and the first facial profile; andignore the derived potential correspondence based on the generated correlation value and the first human face corresponding to the first facial profile. 22. The computer program product of claim 21, additionally comprising computer readable instructions configured to cause the computer system to: prompt a user for confirmation that the human face represented in the received image corresponds to the first stored facial profile; andaccept, in response to prompting, confirmation that the human face represented in the received image corresponds to the first stored facial profile. 23. The computer program product of claim 21, the computer program additionally comprising computer readable instructions configured to cause the computer system to: present an indication of the first stored facial profile and an indication of a second stored facial profile in a user interface, wherein the second stored facial profile includes one or more images representing a second human face;receive an indication in the user interface associating the first stored facial profile with the second stored facial profile; andgenerate a combined album including one or more images from the first stored facial profile and one or more images from the second stored facial profile. 24. The computer program product of claim 21, additionally comprising computer readable instructions configured to cause the computer system to: receive unsorted images representing human faces, unsorted image information, and unsorted correlation values indicating likelihoods that the human faces correspond to the first facial profile;establish an initial correlation value threshold;group the unsorted images based on the initial correlation value threshold and the unsorted correlation values;derive a revised correlation threshold based on amounts of unsorted images grouped together and a total number of groups of unsorted images;regroup the unsorted images based on the revised correlation threshold and the unsorted correlation values; andassociate one or more groups of unsorted images with the first facial profile based on the regrouping. 25. The computer program product of claim 21, wherein to determine comprises to determine that the correlation value indicates the received image corresponds to other than the first facial profile, and that the image information, including first metadata, corresponds to second metadata associated with the one or more profile images. 26. The computer program product of claim 21, additionally comprising computer readable instructions configured to cause the computer system to: obtain the two or more profile images and profile information associated with the two or more profile images from an external source; andgenerate the first facial profile based on the two or more profile images and the profile information. 27. The computer program product of claim 26, wherein the external source comprises a user interface. 28. The computer program product of claim 26, wherein the external source comprises an address book application. 29. The computer program product of claim 21, further comprising: accessing detection information indicating less than a 90% likelihood that the received image represents a human face;establishing that the received image depicts skin-tone colors and sharp image details; andconfirming, based on the establishing, that the received image represents a human face. 30. The computer program product of claim 29, additionally comprising computer readable instructions configured to cause the computer system to: select the received image as a key image based on one or more of the image information, the detection information, or the correlation value; anddisplay the key image as an icon in association with the facial profile. 31. The computer program product of claim 29, wherein the image information comprises a capture date. 32. The computer program product of claim 29, wherein the detection information comprises an angle of the first human face relative to the received image.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (8)
Ko, Byoung-Chul; Kim, Kwang-Choon; Baek, Seung-Hyun, Apparatus and method for detecting a face.
Ganong, Ray; Waugh, Donald Craig; Studholme, Chris; Plataniotis, Kostas; Ro, Yong Man, Method, system, and computer program for identification and sharing of digital images with face signatures.
Ganong, Ray; Waugh, Donald; Man Ro, Yong; Plataniotis, Konstantinos; Studholme, Chris, Method, system, and computer program for identification and sharing of digital images with face signatures.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.