Granted Patent B2

US 8,600,174 · App. 12/948,709 · Granted Dec 3, 2013

Abstract

Claims (17)

1. A method for tagging an image of an individual in a plurality of photos, the method comprising:

identifying a plurality of faces in a plurality of photos;

converting each of the plurality of photos into a plurality of feature vectors, each of the plurality of feature vectors having n-dimensions, wherein each of the plurality feature vectors is based on a plurality of factors comprising facial expression, hair style, hair color, facial pose, eye color, texture of the face, color of the face and facial hair;

clustering each of the plurality of feature vectors;

separating each of the plurality of faces by a cluster;

creating a plurality of albums for each facial cluster;

arranging each of the plurality of photos into an album of the plurality of albums where each face from a photo originated; and

choosing a face that is closest to a center of each facial cluster as an album cover for the facial cluster.

2. The method according to claim 1 further comprising tagging by listing a URL or URI for each of the photos of the plurality of photos in a database.

3. The method according to claim 1 further comprising tagging by inserting a tag code on each of the photos of the plurality of photos.

4. The method according to claim 1 wherein the image of the individual is a facial image of the individual.

5. The method according to claim 1 further comprising:

determining X and Y coordinates of each of the plurality of faces in each photo of the plurality of photos;

determining the size of the face of each photo of the plurality of photos;

determining the tilt of the face of each photo of the plurality of photos;

storing in a database the X and Y coordinates of the face in each photo of the plurality of photos; and

storing in the database an identifier for each photo of the plurality of photos.

Assignments (8)