Automatic photo capture based on social components and identity recognition

摘要

In one embodiment, a mobile device automatically captures image frames by acquiring a real-time video sequence, selecting one or more frames from the real-time video sequence based on social network information and identity recognition, and storing the selected one or more frames in a local storage of the mobile device.

主权项

1. A method comprising:
by a computing device, accessing a sequence of video frames; by the computing device, analyzing one or more of the video frames in the sequence to identify one or more social-network objects, wherein each of the social-network objects is represented by a node in a social graph that comprises a plurality of nodes and edges connecting the nodes; by the computing device, determining a score for each of the identified social-network objects; by the computing device, computing a score for each of the analyzed video frames based at least in part on a total aggregate value of the social-network objects identified in the video frame; by the computing device, selecting one or more of the analyzed video frames based on the scores of the video frames; and by the computing device, presenting the selected one or more of the video frames to a first user, wherein each of the selected one or more of the video frames is presented as an image.