On deformable models for visual pattern recognition
Chin, Roland T.
|Summary||This paper reviews model-based methods for non-rigid shape analysis and recognition. These methods model, match and classify non-rigid shapes, which are generally problematic for conventional algorithms using rigid models. Issues including deformable model representation, optimization criteria formulation, model matching, and classification are examined in detail. The emphasis of this paper is on 2D deformable models, but some existing 2(1/2)D and 3D deformable models are also briefly reviewed. Potential applications of deformable models and future research directions are discussed.|
Files in this item: