SMRFI: Shape matching via registration of vector-valued feature images

We perform shape matching by transforming the problem of establishing shape correspondences into an image registration problem. At each vertex on the shape, we calculate a shape feature and encode this feature as image intensity at appropriate positions in the image domain. Calculating multiple features at each vertex and encoding them into the image domain results in a vector-valued feature image. Establishing point correspondence between two shapes is thereafter treated as a registration problem of two vectorvalued feature images. With this shape representation, various existing image registration strategies can now be easily applied. These include the use of a scale-space approach to diffuse the shape features, a coarse-to-fine registration scheme, and various deformable registration algorithms. As our validation shows, by representing shapes as vectorvalued images, the overall method is robust against noise and occlusions. To this end, we have successfully established 2D point cor...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Lisa Tang, Ghassan Hamarneh
• Keywords: Computer Vision, CVPR 2008, Image Registration Problem, Image Registration Strategies, Shape Correspondences, Shape Feature, Shape Matching