Obtaining artist imagery from video content using facial recognition
An example method may include receiving, at a computing device, a digital image associated with a particular media content program, the digital image containing one or more faces of particular people associated with the particular media content program. A computer-implemented automated face recognition program may be applied to the digital image to recognize, based on at least one feature vector from a prior-determined set of feature vectors, one or more of the particular people in the digital image, together with respective geometric coordinates for each of the one or more detected faces. At least a subset of the prior-determined set of feature vectors may be associated with a respective one of the particular people. The digital image together may be stored in non-transitory computer-readable memory, together with information assigning respective identities of the recognized particular people, and associating with each respective assigned identity geometric coordinates in the digital image.
1. A tangible, non-transitory computer readable medium comprising instructions that, when executed, cause at least one processor to perform a set of operations comprising:
receiving a digital image associated with a particular media content program, the digital image containing one or more faces of particular people associated with the particular media content program;
applying a face recognition program together with a set of computational models to the digital image to recognize one or more of the particular people in the digital image from among one or more faces detected, together with respective geometric coordinates for each of the one or more detected faces in the digital image, wherein each of at least a subset of the set of the computational models is further associated with a respective one of the particular people; and
storing, in non-transitory computer-readable memory, the digital image together with information (i) assigning respective identities of the recognized one or more of the particular people in the digital image, and (ii) associating with each respective assigned identity geometric coordinates in the digital image of a face to which the identity is assigned.
2. The tangible, non-transitory computer readable medium of claim 1 , wherein applying the face recognition program together with the set of computational models to the digital image to recognize the one or more of the particular people in the digital image from among the one or more faces detected, together with respective geometric coordinates for each of the one or more detected faces in the digital image, comprises:
determining a feature vector corresponding to at least one of the one or more faces detected, together with respective geometric coordinates, in the digital image;
applying the face recognition program together with the set of computational models to the feature vector; and
determining that applying the face recognition program together with a particular model of the set of computational models to the feature vector yields a probability that both exceeds a threshold and is greater than probabilities yielded from applying the face recognition program together with any of the other computational models of the set.
3. The tangible, non-transitory computer readable medium of claim 2 , wherein determining the feature vector corresponding to at least one of the one or more faces detected, together with respective geometric coordinates, in the digital image comprises:
applying a face detection program to the digital image to detect a spatial region of the digital image that includes the at least one of the one or more faces detected, together with respective geometric coordinates of the spatial region; and
applying a computer-implemented feature extraction program to the spatial region of the digital image to generate the feature vector.
4. The tangible, non-transitory computer readable medium of claim 1 , wherein at least one of the one or more of the particular people in the digital image is a cast member of the particular media content program.
5. The tangible, non-transitory computer readable medium of claim 1 , wherein the particular media content program is one of: a television program, a movie, a sporting event, or a web-based user-hosted and/or user-generated content program.
6. The tangible, non-transitory computer readable medium of claim 1 , wherein the set of operations further comprises:
receiving a further digital image associated with a further particular media content program, the further digital image containing one or more faces of further particular people associated with the further particular media content program;
applying the computer-implemented face recognition program together with a further set of computational models to the further digital image to recognize one or more of the further particular people in the further digital image from among one or more further faces detected, together with respective geometric coordinates for each of the one or more further detected faces in the further digital image, wherein each of at least a further subset of the further set of the computational models is additionally associated with a respective one of the further particular people; and
storing, in non-transitory computer-readable memory, the further digital image together with information (i) assigning respective identities of the recognized one or more of the further particular people in the further digital image, and (ii) associating with each respective assigned identity geometric coordinates in the further digital image of a further face to which the identity is assigned.
7. The tangible, non-transitory computer readable medium of claim 6 , wherein the further digital image is different from the digital image,
wherein the further particular media content program is one of: different from the particular media content program, or the same as the particular media content program, and wherein at least one of the recognized further particular people is one of:
different from any of the recognized particular people, or the same as one of the recognized particular people.
8. The tangible, non-transitory computer readable medium of claim 1 , wherein each of the computational models of the set has been trained for recognizing a different one a plurality of people associated with the particular media content program, wherein the plurality includes at least the particular people.
9. A computer-implemented method comprising:
receiving, at a computing device, a digital image associated with a particular media content program, the digital image containing one or more faces of particular people associated with the particular media content program;
applying a computer-implemented face recognition program together with a set of computational models to the digital image to recognize one or more of the particular people in the digital image from among one or more faces detected, together with respective geometric coordinates for each of the one or more detected faces in the digital image, wherein each of at least a subset of the set of the computational models is further associated with a respective one of the particular people; and
storing, in non-transitory computer-readable memory, the digital image together with information (i) assigning respective identities of the recognized one or more of the particular people in the digital image, and (ii) associating with each respective assigned identity geometric coordinates in the digital image of a face to which the identity is assigned.
10. The computer-implemented method of claim 9 , wherein applying the face recognition program together with the set of computational models to the digital image to recognize the one or more of the particular people in the digital image from among the one or more faces detected, together with respective geometric coordinates for each of the one or more detected faces in the digital image, comprises:
determining a feature vector corresponding to at least one of the one or more faces detected, together with respective geometric coordinates, in the digital image;
applying the face recognition program together with the set of computational models to the feature vector; and
determining that applying the face recognition program together with a particular model of the set of computational models to the feature vector yields a probability that both exceeds a threshold and is greater than probabilities yielded from applying the face recognition program together with any of the other computational models of the set.
11. The computer-implemented method of claim 10 , wherein determining the feature vector corresponding to at least one of the one or more faces detected, together with respective geometric coordinates, in the digital image comprises:
applying a face detection program to the digital image to detect a spatial region of the digital image that includes the at least one of the one or more faces detected, together with respective geometric coordinates of the spatial region; and
applying a computer-implemented feature extraction program to the spatial region of the digital image to generate the feature vector.
12. The computer-implemented method of claim 9 , wherein at least one of the one or more of the particular people in the digital image is a cast member of the particular media content program.
13. The computer-implemented method of claim 9 , wherein the particular media content program is one of: a television program, a movie, a sporting event, or a web-based user-hosted and/or user-generated content program.
14. The computer-implemented method of claim 9 , further comprising:
receiving a further digital image associated with a further particular media content program, the further digital image containing one or more faces of further particular people associated with the further particular media content program;
applying the computer-implemented face recognition program together with a further set of computational models to the further digital image to recognize one or more of the further particular people in the further digital image from among one or more further faces detected, together with respective geometric coordinates for each of the one or more further detected faces in the further digital image, wherein each of at least a further subset of the further set of the computational models is additionally associated with a respective one of the further particular people; and
storing, in non-transitory computer-readable memory, the further digital image together with information (i) assigning respective identities of the recognized one or more of the further particular people in the further digital image, and (ii) associating with each respective assigned identity geometric coordinates in the further digital image of a further face to which the identity is assigned.
15. The computer-implemented method of claim 14 , wherein the further digital image is different from the digital image,
wherein the further particular media content program is one of: different from the particular media content program, or the same as the particular media content program,
and wherein at least one of the recognized further particular people is one of:
different from any of the recognized particular people, or the same as one of the recognized particular people.
16. The computer-implemented method of claim 9 , wherein each of the computational models of the set has been trained for recognizing a different one a plurality of people associated with the particular media content program, wherein the plurality includes at least the particular people.
17. A computing device comprising:
at least one processors; and
tangible, non-transitory computer readable medium comprising instructions that, when executed, cause the at least one processor to perform a set of operations comprising:
receiving a digital image associated with a particular media content program, the digital image containing one or more faces of particular people associated with the particular media content program;
applying a face recognition program together with a set of computational models to the digital image to recognize one or more of the particular people in the digital image from among one or more faces detected, together with respective geometric coordinates for each of the one or more detected faces in the digital image, wherein each of at least a subset of the set of the computational models is further associated with a respective one of the particular people; and
storing, in non-transitory computer-readable memory, the digital image together with information (i) assigning respective identities of the recognized one or more of the particular people in the digital image, and (ii) associating with each respective assigned identity geometric coordinates in the digital image of a face to which the identity is assigned.
18. The computing device of claim 17 , wherein applying the face recognition program together with the set of computational models to the digital image to recognize the one or more of the particular people in the digital image from among the one or more faces detected, together with respective geometric coordinates for each of the one or more detected faces in the digital image, comprises:
determining a feature vector corresponding to at least one of the one or more faces detected, together with respective geometric coordinates, in the digital image;
applying the face recognition program together with the set of computational models to the feature vector; and
determining that applying the face recognition program together with a particular model of the set of computational models to the feature vector yields a probability that both exceeds a threshold and is greater than probabilities yielded from applying the face recognition program together with any of the other computational models of the set.
19. The computing device of claim 17 , wherein at least one of the one or more of the particular people in the digital image is a cast member of the particular media content program.
20. The computing device of claim 17 , wherein the particular media content program is one of: a television program, a movie, a sporting event, or a web-based user- hosted and/or user-generated content program.