Detecting actions to discourage recognition

1. A method comprising:

detecting a person in an image or a video by determining a person image region that corresponds to boundaries of the person or a face image region that corresponds to a position of a face of the person;

analyzing pixel values that correspond to the boundaries of the person or the position of the face of the person to generate a recognition avoidance signal;

determining whether the recognition avoidance signal indicates that an action was taken to discourage recognition of the person, wherein the action includes the person using a body part of the person to obscure at least part of the face of the person; and

responsive to the recognition avoidance signal indicating that the action was taken to discourage recognition of the person, declining to perform recognition of the person.

2. The method of claim 1 , wherein declining to perform recognition of the person includes performing at least one of storing the recognition avoidance signal in association with the image or the video to indicate that person recognition is not to be performed, deleting the image or the video, archiving the image or the video, or downranking the image or the video in search results.

3. The method of claim 1 , further comprising:

responsive to the recognition avoidance signal not indicating that the action was taken to discourage recognition of the person, performing recognition of the person by determining an identity of the person and indexing the image or the video in association with the identity.

4. The method of claim 3 , further comprising:

responsive to the recognition avoidance signal indicating that the action was taken to discourage recognition of the person, determining whether the recognition avoidance signal corresponds to an avoidance value that does not meet a threshold value; and

wherein performing recognition of the person is also responsive to the avoidance value not meeting the threshold value.

5. The method of claim 1 , wherein:

the person is a first person;

determining that the action was taken to discourage recognition of the person further includes a determination that the recognition avoidance signal corresponds to an avoidance value that meets a threshold value; and

the method further comprises responsive to the avoidance value meeting the threshold value, detecting a second person in the image or the video and generating the recognition avoidance signal for the second person.

6. The method of claim 1 , wherein performing recognition of the person is based on extracting a recognition template.

7. The method of claim 1 , wherein the image is a first image associated with an event, the video is a first video associated with the event, and further comprising:

identifying one or more additional images or one or more additional videos that are associated with the event; and

determining to not recognize the person within the one or more additional images or the one or more additional videos.

8. The method of claim 1 , wherein determining that the recognition avoidance signal indicates that the action was taken to discourage recognition of the person includes determining a type of action and further comprising:

performing recognition of the person by identifying the person and sharing an identification of the person with a group of users in a social network based on the type of action and not sharing the identification of the person with any users that are not part of the group of users in the social network.

9. A non-transitory computer-readable medium with instructions stored thereon that, when executed by one or more computers, cause the one or more computers to perform operations, the operations comprising:

detecting a person in an image or a video by determining a person image region that corresponds to boundaries of the person or a face image region that corresponds to a position of a face of the person;

analyzing pixel values that correspond to the boundaries of the person or the position of the face of the person to generate a recognition avoidance signal;

determining whether the recognition avoidance signal indicates that an action was taken to discourage recognition of the person, using a body part of the person;

responsive to the recognition avoidance signal indicating that the action was taken to discourage recognition of the person, determining whether the recognition avoidance signal corresponds to an avoidance value that meets a threshold value; and

responsive to the recognition avoidance signal not indicating that the action was taken to discourage recognition of the person and the avoidance value not meeting the threshold value, performing recognition of the person.

10. The computer-readable medium of claim 9 , wherein performing recognition of the person comprises determining an identity of the person and indexing the image or the video in association with the identity.

11. The computer-readable medium of claim 9 , wherein the operations further comprise:

responsive to the recognition avoidance signal indicating that the action has been taken to discourage recognition of the person, performing at least one of storing the recognition avoidance signal in association with the image or the video to indicate that person recognition is not to be performed, deleting the image or the video, archiving the image or the video, or downranking the image or the video in search results.

12. The computer-readable medium of claim 9 , wherein the image or the video is part of a series of images of an event and the recognition avoidance signal is based on an average of a particular avoidance value corresponding to each image in the series of images.

13. The computer-readable medium of claim 9 , wherein the action includes the person using an object to obscure at least part of the face of the person or at least part of the face of the person being obscured digitally.

14. The computer-readable medium of claim 9 , wherein the operations further comprise:

determining permissions associated with the person; and

wherein performing recognition of the person is based on the permissions associated with the person.

15. A system comprising:

one or more processors; and

a memory that stores instructions that, when executed by the one or more processors cause the one or more processors to perform operations comprising:

detecting a person in an image or a video by determining a person image region that corresponds to boundaries of the person or a face image region that corresponds to a position of a face of the person;

analyzing pixel values that correspond to the boundaries of the person or the position of the face of the person to generate a recognition avoidance signal;

determining whether the recognition avoidance signal indicates that an action was taken to discourage recognition of the person, wherein the action includes the person using a body part of the person to obscure at least part of the face of the person; and

responsive to the recognition avoidance signal indicating that the action was taken to discourage recognition of the person, declining to perform recognition of the person.

16. The system of claim 15 , wherein declining to perform recognition of the person includes performing at least one of storing the recognition avoidance signal in association with the image or the video to indicate that person recognition is not to be performed, deleting the image or the video, archiving the image or the video, or downranking the image or the video in search results.

17. The system of claim 15 , wherein the memory stores additional instructions that cause the one or more processors to perform further operations comprising:

responsive to the recognition avoidance signal not indicating that the action was taken to discourage recognition of the person, performing recognition of the person by determining an identity of the person and indexing the image or the video in association with the identity.

18. The system of claim 17 , wherein the operations further include:

responsive to the recognition avoidance signal indicating that the action was taken to discourage recognition of the person, determining whether the recognition avoidance signal corresponds to an avoidance value that does not meet a threshold value; and

wherein performing recognition of the person is also responsive to the avoidance value not meeting the threshold value.

19. The system of claim 15 , wherein:

the person is a first person;

determining that the action was taken to discourage recognition of the person further includes a determination that the recognition avoidance signal corresponds to an avoidance value that meets a threshold value; and

the memory stores additional instructions comprising, responsive to the avoidance value meeting the threshold value, detecting a second person in the image and generating the recognition avoidance signal for the second person.