Department of Statistics, UCLA

We describe a hierarchical compositional system for detecting de- formable objects in images. Objects are represented by graphical models. The algorithm uses a hierarchical tree where the root of the tree corre- sponds to the full object and lower-level elements of the tree correspond to simpler features. The algorithm proceeds by passing simple messages up and down the tree. The method works rapidly, in under a second, on 320 × 240 images. We demonstrate the approach on detecting cat- s, horses, and hands. The method works in the presence of background clutter and occlusions. Our approach is contrasted with more traditional methods such as dynamic programming and belief propagation.