Facilitating face detection with user input
One or more techniques and/or systems are disclosed for improving face detection in an image. A user may select a first eye location while viewing the image (e.g., per red-eye reduction) and a first indication of user input, comprising the location selected by the user, can be received. The first eye location in the image can then be used to determine a face location in the image (and a second user indicated eye location can be used as well). The location of the face can be identified in the image, and the image with the identified face location can be provided to a face detection and/or recognition operation, for example.
1. A computer-based method for improving face detection in an image, comprising:
receiving a first indication of user input identifying a first eye in the image, the first indication comprising a user selection of a first eye size of the first eye and a first eye location of the first eye;
determining whether the first eye is part of a previously detected facial region; and
responsive to determining that the first eye is not part of the previously detected facial region:
determining whether a second indication of user input identifying a second eye in the image is received, the second indication comprising a user selection of a second eye size of the second eye and a second eye location of the second eye;
responsive to determining that the second indication is not received, determining whether the second eye is programmatically detectable;
responsive to detecting the second eye at least one of programmatically or based upon the second indication:
determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye, the face location corresponding to a face region area within the image, and a size of the face region area based at least in part upon a distance between the first eye location and the second eye location;
responsive to not detecting the second eye programmatically or based upon the second indication:
determining the face location in the image based at least in part upon the first indication, the size of the face region area based at least in part upon the first eye size; and
indicating the face location in the image for a face detection operation on the image.
2. The method of claim 1 , the image comprising a digital image.
3. The method of claim 1 , the user input corresponding to a red-eye reduction interaction with the image.
4. The method of claim 1 , the determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye comprising:
comparing the distance between the first eye location and the second eye location with known facial geometry data.
5. The method of claim 1 , the determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye comprising:
verifying that the distance between the first eye location and the second eye location is less than a distance threshold.
6. The method of claim 5 , comprising determining the distance threshold based at least in part upon at least one of the first eye size or the second eye size.
7. The method of claim 1 , the face location centered at the first eye location.
8. The method of claim 1 , the indicating the face location for a face detection operation comprising indicating the face region area.
9. The method of claim 1 , comprising comparing the first eye size to the second eye size to determine whether the first eye and the second eye correspond to a same face.
10. A system for improving face detection in an image, comprising:
one or more processing units; and
memory comprising instructions that when executed by at least one of the one or more processing units perform a method, comprising:
receiving a first indication of user input identifying a first eye in the image, the first indication comprising a user selection of a first eye size of the first eye and a first eye location of the first eye;
determining whether the first eye is part of a previously detected facial region; and
responsive to determining that the first eye is not part of the previously detected facial region:
determining whether a second indication of user input identifying a second eye in the image is received, the second indication comprising a user selection of a second eye size of the second eye and a second eye location of the second eye;
responsive to determining that the second indication is not received, determining whether the second eye is programmatically detectable;
responsive to detecting the second eye at least one of programmatically or based upon the second indication:
determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye;
responsive to not detecting the second eye programmatically or based upon the second indication:
determining the face location in the image based at least in part upon the first indication; and
indicating the face location in the image for a face detection operation on the image.
11. The system of claim 10 , the image comprising a digital image.
12. The system of claim 10 , the determining a face location in the image based at least in part upon the first indication and at least one of the second indication of a programmatic detection of the second eye comprising:
determining the face location based at least in part upon a distance between the first eye location and the second eye location.
13. The system of claim 12 , the determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye comprising:
determining the face location if the distance between the first eye location and the second eye location is less than a distance threshold.
14. The system of claim 13 , the method comprising determining the distance threshold based at least in part upon the first eye size and the second eye size.
15. The system of claim 10 , the method comprising programmatically detecting the second eye in the image based at least in part upon the first indication.
16. A computer readable storage device comprising instructions that when executed perform a method for improving face detection in an image, comprising:
receiving a first indication of user input identifying a first eye in the image;
determining whether the first eye is part of a previously detected facial region; and
responsive to determining that the first eye is not part of the previously detected facial region:
determining whether a second indication of user input identifying a second eye in the image is received;
responsive to determining that the second indication is not received, determining whether the second eye is programmatically detectable;
responsive to detecting the second eye at least one of programmatically or based upon the second indication:
determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye;
responsive to not detecting the second eye programmatically or based upon the second indication:
determining the face location in the image based at least in part upon the first indication; and
indicating the face location in the image for a face detection operation on the image.
17. The computer readable storage device of claim 16 , the face location corresponding to a face region area within the image and the determining a face location in the image based at least in part upon the first indication and at least one of the second indication or a programmatic detection of the second eye comprising:
determining a size of the face region area based at least in part upon a distance between a first eye location of the first eye and a second eye location of the second eye, the first eye location from the first indication and the second eye location from the second indication.
18. The computer readable storage device of claim 16 , the face location corresponding to a face region area within the image and the determining the face location in the image based at least in part upon the first indication comprising:
determining a size of the face region area based at least in part upon a first eye size of the first eye as indicated by the first indication.
19. The computer readable storage device of claim 16 , the first indication of user input comprising a user selection of a first eye size of the first eye and a first eye location of the first eye.
20. The computer readable storage device of claim 16 , the second indication of user input comprising a user selection of a second eye size of the second eye and a second eye location of the second eye.