Generalized Matching for Recognition and Retrieval in an Image Database

We describe a novel approach for image matching based on deformable intensity surfaces. In this approach , the intensity surface of the image is modeled as a deformable 3D mesh in the (x; y; I(x; y)) space. Each surface point has 3 degrees of freedom, thus capturing ne surface changes. A set of representative deformations within a class of objects (e.g. faces) are statistically learned through a Principal Components Analysis, thus providing a priori knowledge about object-speciic deformations. We demonstrate the power of the approach by recognition and interactive search in a large-scale face database.