Face annotation framework with partial clustering and interactive labeling

A system, comprising:

• a storage device for storing a collection of digital images;
• a face annotation engine to label the digital images using a minimal number of user interactions;
• a partial clustering engine in the face annotation engine to automatically cluster some of the digital images into evident clusters instead of forcing every image in the collection into a cluster, each evident cluster containing images that include a face of a single person, and the evident clusters having a uniform background distribution for noisy data;
• and
• an efficient labeling engine in the face annotation engine to iteratively propose clusters of unlabeled images such that user interactions to label the proposed clusters maximize labeling of the digital images and achieve the minimal number of user interactions.

A method performed by a computing device, the method comprising:

• automatically grouping some images of a collection of images into clusters, the grouping comprising:
• using spectral embedding to find representation of face of an image in a plurality of feature spaces, the plurality of feature spaces including a facial feature space representing a face of the image, a clothing feature space representing clothing features in association with the face of the image, and a time feature space representing a time when the image was taken;
• and
• partially clustering the collection of images into clusters with a deliberate bias toward finding evident clusters, each evident cluster including images that reliably contain a face of a person associated with that cluster, the evident clusters having a uniform background distribution for noisy data;
• labeling the clusters;
• and
• iteratively proposing subsequent clusters that when user-labeled, minimize the number of user interactions for labeling the remaining unlabeled images based on global system entropy and subset-saliency entropy.