Hierarchical Matching of Deformable Shapes

We describe a new hierarchical representation for twodimensional objects that captures shape information at multiple levels of resolution. This representation is based on a hierarchical description of an object's boundary and can be used in an elastic matching framework, both for comparing pairs of objects and for detecting objects in cluttered images. In contrast to classical elastic models, our representation explicitly captures global shape information. This leads to richer geometric models and more accurate recognition results. Our experiments demonstrate classification results that are significantly better than the current stateof-the-art in several shape datasets. We also show initial experiments in matching shapes to cluttered images.

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Pedro F. Felzenszwalb, Joshua D. Schwartz
• Keywords: Classical Elastic Models, Cluttered Images, Computer Vision, CVPR 2007, Elastic Matching Framework, Global Shape Information, Richer Geometric Models