Learning to find pictures of people

Finding articulated objects, like people, in pictures presents a particularlydifficult object recognition problem. We show how tofind people by finding putative body segments, and then constructingassemblies of those segments that are consistent with the constraintson the appearance of a person that result from kinematicproperties. Since a reasonable model of a person requires at leastnine segments, it is not possible to present every group to a classifier.Instead, the search can be...