Learning to Find Pictures of People

Neural Information Processing Systems 

Finding articulated objects, like people, in pictures present.s a par(cid:173) ticularly difficult object. We show how t.o find people by finding putative body segments, and then construct.(cid:173) Since a reasonable model of a person requires at. Instead, the search can be pruned by using projected versions of a classifier that accepts groups corresponding to people. We describe an efficient projection algorithm for one popular classi(cid:173) fier, and demonstrate that our approach can be used to determine whether images of real scenes contain people.