A Probabilistic Framework for Shape Recognition
This paper describes a probabilistic framework for recognizing 2D shapes with articulated components. The
shapes are represented using both geometrical and a symbolic primitives, that are encapsulated in a two layer hierarchical
architecture. Each primitive is modelled so as to allow a degree of articulated freedom using a polar point distribution model
that captures how the primitive movement varies over a training set. Each segment is assigned a symbolic label to distinguish
its identity, and the overall shape is represented by a configuration of labels. We demonstrate how both the point-distribution
model and the symbolic labels can be combined to perform recognition using a probabilistic hierarchical algorithm. This
involves recovering the parameters of the point distribution model that minimize an alignment error, and recovering symbol
configurations that minimize a structural error. We apply the recognition method to human pose recognition.
Keywords - Polar Point Distrubtion Models, Discrete Relaxation, Shape Recognition, Expectation Maximization Algorithm,
Hierarchical Mixtures Of Shapes, Human Posture.