Learning to Find Pictures of People

Finding articulated objects, like people, in pictures presents a particularly difficult object recognition problem. We show how to find people by finding putative body segments, and then constructing assemblies of those segments that are consistent with the constraints on the appearance of a person that result from kinematic properties. Since a reasonable model of a person requires at least nine segments, it is not possible to present every group to a classifier. 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 classifier, and demonstrate that our approach can be used to determine whether images of real scenes contain people.