Large hierarchical object recognition using libraries of parameterized model sub-parts

A description is given of the development of a model-based vision system that utilizes hierarchies of both object structure and object scale. The focus of the research is to use these hierarchies to achieve robust recognition based on effective organization and indexing schemes for model libraries. The goal of the system is to recognize parameterized instances of nonrigid model objects contained in a large knowledge base, despite the presence of noise and occlusion. The approach presented is to develop an object shape representation that incorporates a component subpart hierarchy, to allow for efficient and correct indexing into an automatically generated model library as well as for relative parametrization among subparts, and a scale hierarchy, to allow for a general to specific recognition procedure. The implemented system uses a representation based on significant contour curvature changes and recognition engine based on geometric constraints of feature properties. Examples of the system´s performance are given, followed by an analysis of the results