Method, system and computer program for identification and sharing of digital images with face signatures
First Claim
1. A method for recognizing one or more faces in a digital image, the method comprising:
- receiving a digital image at at least one computer device;
executing, at the at least one computer device, a face detection routine on the digital image involving;
generating one or more face coordinates corresponding to one or more candidate regions for one or more faces;
generating eye coordinates based on the face coordinates;
executing, at the at least one computer device, a face recognition routine involving, for each of the one or more candidate regions for the one or more faces, generating a face signature using one or more projection images defined by the face coordinates and the eye coordinates; and
comparing the face signature with one or more known face signatures to determine a distance value for each comparison, computing an aggregation of the distance values, determining a best match between the face signature and the known face signatures using the aggregated distance values and comparing the best match to a similarity threshold, the best match determining an identity corresponding to at least one of the one or more faces; and
making available results of the face recognition routine wherein the face signature is generated by;
translating, rotating, and scaling the candidate region to a normalized image having a predetermined size wherein the eye coordinates are linked to predetermined locations;
masking the normalized image to define a masked image wherein the face is isolated;
applying a histogram equalization to a greyscale depiction of the masked image; and
generating the face signature using principal component analysis of the one or more projection images.
3 Assignments
0 Petitions
Accused Products
Abstract
Methods and systems are provided for sharing a digital image depicting one or more faces. The method may include linking a plurality of computer terminals to a computer network, each computer terminal associated with an individual; receiving a digital image at at least one of the computer terminals; executing a face recognition routine on the digital image, the face recognition routine detecting at least one face in the digital image, each detected face corresponding to a person, the face recognition routine recognizing at least one of the persons as being one of the individuals; and for each individual recognized in the digital image by the face recognition routine, initiating dissemination of the digital image to the computer terminal associated with respective individual whose face is recognized in the digital image.
-
Citations
23 Claims
-
1. A method for recognizing one or more faces in a digital image, the method comprising:
-
receiving a digital image at at least one computer device; executing, at the at least one computer device, a face detection routine on the digital image involving; generating one or more face coordinates corresponding to one or more candidate regions for one or more faces; generating eye coordinates based on the face coordinates; executing, at the at least one computer device, a face recognition routine involving, for each of the one or more candidate regions for the one or more faces, generating a face signature using one or more projection images defined by the face coordinates and the eye coordinates; and
comparing the face signature with one or more known face signatures to determine a distance value for each comparison, computing an aggregation of the distance values, determining a best match between the face signature and the known face signatures using the aggregated distance values and comparing the best match to a similarity threshold, the best match determining an identity corresponding to at least one of the one or more faces; andmaking available results of the face recognition routine wherein the face signature is generated by;
translating, rotating, and scaling the candidate region to a normalized image having a predetermined size wherein the eye coordinates are linked to predetermined locations;
masking the normalized image to define a masked image wherein the face is isolated;
applying a histogram equalization to a greyscale depiction of the masked image; and
generating the face signature using principal component analysis of the one or more projection images.- View Dependent Claims (2, 3, 4, 5, 13, 14, 15, 23)
-
-
6. A method for sharing a digital image depicting one or more faces, the method comprising:
- receiving a digital image at at least computer device;
enabling the at least one computer device to initiate a face detection routine and a face recognition routine on the digital image, the face detection routine involving generating one or more face coordinates corresponding to one or more candidate regions for one or more faces;
generating eye coordinates based on the face coordinates, the face recognition routine producing a list of one or more persons whose faces are depicted in the digital image, by for each of the one or more candidate regions, generating a face signature using one or more projection images defined by the face coordinates and the eye coordinates, comparing the face signature with one or more known face signatures to determine a distance value for each comparison, determining a best match between the face signature and the known face signatures and comparing the best match to a similarity threshold, the best match determining an identity of a person in the list of one or more persons corresponding to at least one of the one or more faces; and
enabling the at least one computer device to initiate a sharing routine for disseminating the digital image to computer terminals associated with the one or more persons, wherein the face signature is generated by;
translating, rotating, and scaling the candidate region to a normalized image having a predetermined size wherein the eye coordinates are linked to predetermined locations;
masking the normalized image to define a masked image wherein the face is isolated;
applying a histogram equalization to a greyscale depiction of the masked image; and
generating the face signature using principal component analysis of the one or more projection images. - View Dependent Claims (7, 8, 9, 10, 11, 16, 20, 21, 22)
- receiving a digital image at at least computer device;
-
12. A computer device for recognizing one or more faces in a digital image, the device comprising:
- a storage device receiving and storing a digital image;
at least one processor configured to execute a face detection routine and a face recognition routine, the face detection routine involving generating one or more face coordinates corresponding to one or more candidate regions for one or more faces;
generating eye coordinates based on the face coordinates, the face recognition routine involving, for each of the one or more candidate regions, generating a face signature using one or more projection images defined by the face coordinates and the eye coordinates, comparing the face signature with one or more known face signatures to determine a distance value for each comparison, determining a best match between the face signature and the known face signatures and comparing the best match to a similarity threshold, the best match determining an identity corresponding to at least one of the one or more faces, and making available results of the face recognition routine, wherein the face signature is generated by;
translating, rotating, and scaling the candidate region to a normalized image having a predetermined size wherein the eye coordinates are linked to predetermined locations;
masking the normalized image to define a masked image wherein the face is isolated;
applying a histogram equalization to a greyscale depiction of the masked image; and
generating the face signature using principal component analysis of the one or more projection images. - View Dependent Claims (17, 18, 19)
- a storage device receiving and storing a digital image;
Specification