Methods and systems are presented for organizing images. In one aspect, a method can include generating a correlation value indicating a likelihood that a face included in a test image corresponds to a face associated with a base image, determining that a correlation threshold exceeds the correlatio
Methods and systems are presented for organizing images. In one aspect, a method can include generating a correlation value indicating a likelihood that a face included in a test image corresponds to a face associated with a base image, determining that a correlation threshold exceeds the correlation value and that the correlation value exceeds a non-correlation threshold, generating a similarity score based on one or more exposure values and one or more color distribution values corresponding to the test image and the base image, combining the similarity score with the correlation value to generate a weighted correlation value, and determining that the test image and the base image are correlated when the weighted correlation value exceeds the correlation threshold.
대표청구항▼
1. A non-transitory computer-readable storage medium storing instructions for managing images, which, when executed by one or more processors, cause the one or more processors to: detect a first face in a first image;receive user input indicative of a confirmation that the first face corresponds to
1. A non-transitory computer-readable storage medium storing instructions for managing images, which, when executed by one or more processors, cause the one or more processors to: detect a first face in a first image;receive user input indicative of a confirmation that the first face corresponds to a user profile;generate a confidence score based on a source of the user input;detect a second face in a second image;generate a correlation value indicating a likelihood that the first face in the first image corresponds to the second face in the second image; anddetermine, based on the confidence score and the correlation value, that the second face corresponds to the user profile. 2. The non-transitory computer-readable storage medium of claim 1, wherein a confidence score based on user input from a user associated with the user profile is more reliable than a confidence score based on user input from a user associated with another user profile. 3. The non-transitory computer-readable storage medium of claim 1, further comprising instructions for causing the one or more processors to: detect a third face in at least one of the first or second images;automatically determine, in response to detecting the third face, that the third face and at least one of the first or second faces represents a forbidden association; anddetermine, based on the forbidden association, that the third face does not correspond to the user profile. 4. The non-transitory computer-readable storage medium of claim 1, wherein the instructions for causing the one or more processors to receive user input indicative of a confirmation that the first face corresponds to a user profile comprise instructions for causing the one or more processors to suggest an identity of the first face based on information from an external source. 5. The non-transitory computer-readable storage medium of claim 4, wherein the received user input comprises a confirmation that the suggested identity of the first face corresponds to the user profile. 6. The non-transitory computer-readable storage medium of claim 1, further comprising instructions for causing the one or more processors to: generate a similarity score based on one or more factors characterizing a similarity between the first face and the second face;combine the similarity score with the correlation value to generate a weighted correlation value; anddetermine that the first face and the second face are correlated when the weighted correlation value exceeds a threshold. 7. A method for managing images, comprising: detecting a first face in a first image;receiving, by one or more processors, user input indicative of a confirmation that the first face corresponds to a user profile;generating, by the one or more processors, a confidence score based on a source of the user input;detect a second face in a second image;generate a correlation value indicating a likelihood that the first face in the first image corresponds to the second face in the second image; anddetermine, based on the confidence score and the correlation value, that the second face corresponds to the user profile. 8. The method of claim 7, wherein a confidence score based on user input from a user associated with the user profile is more reliable than a confidence score based on user input from a user associated with another user profile. 9. The method of claim 7, further comprising: detecting a third face in at least one of the first or second images;automatically determining, in response to detecting the third face, that the third face and at least one of the first or second faces represents a forbidden association; anddetermining, based on the forbidden association, that the third face does not correspond to the user profile. 10. The method of claim 7, wherein receiving user input indicative of a confirmation that the first face corresponds to a user profile comprises suggesting an identity of the first face based on information from an external source. 11. The method of claim 10, wherein the received user input comprises a confirmation that the suggested identity of the first face corresponds to the user profile. 12. The method of claim 7, further comprising: generating a similarity score based on one or more factors characterizing a similarity between the first face and the second face;combining the similarity score with the correlation value to generate a weighted correlation value; anddetermining that the first face and the second face are correlated when the weighted correlation value exceeds a threshold. 13. A computerized system for managing images, comprising: memory storing instructions; andone or more processors coupled to the memory and the user input module, the one or more processors being configured to execute the instructions to: detect a first face in a first image;receive user input, the user input being indicative of a confirmation that the first face corresponds to a user profile;generate a confidence score based on a source of the user input;detect a second face in a second image;generate a correlation value indicating a likelihood that the first face in the first image corresponds to the second face in the second image; anddetermine, based on the confidence score and the correlation value, that the second face corresponds to the user profile. 14. The system of claim 13, wherein a confidence score based on user input from a user associated with the user profile is more reliable than a confidence score based on user input from a user associated with another user profile. 15. The system of claim 13, wherein the one or more processors are further configured to execute the instructions to: detect a third face in at least one of the first or second images;automatically determine, in response to detecting the third face, that the third face and at least one of the first or second faces represents a forbidden association; anddetermine, based on the forbidden association, that the third face does not correspond to the user profile. 16. The system of claim 13, wherein the one or more processors being configured to execute the instructions to receive user input indicative of a confirmation that the first face corresponds to a user profile comprises the one or more processors being configured to execute the instructions to suggest an identity of the first face based on information from an external source. 17. The system of claim 16, wherein the received user input comprises a confirmation that the suggested identity of the first face corresponds to the user profile. 18. The system of claim 13, wherein the one or more processors are further configured to execute the instructions to: generate a similarity score based on one or more factors characterizing a similarity between the first face and the second face;combine the similarity score with the correlation value to generate a weighted correlation value; anddetermine that the first face and the second face are correlated when the weighted correlation value exceeds a threshold.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (12)
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.