Object Recognition Robust Under Translations, Deformations, and Changes in Background

Recognition systems based on model matching using low level features often fail due to a variation in background. As a solution I present a system for the recognition of human faces independent of hairstyle. Correspondence maps between an image and a model are established by coarse-fine matching in a Gabor pyramid. These are used for hierarchical recognition. Keywords--- Object recognition, face recognition, coarseto -fine strategy, parallel processing, Gabor function, wavelet transform, image pyramid, correspondence problem, background independence. I. Introduction The recognition of familiar objects in an unrestricted environment is an easy task for humans and an exorbitantly difficult one for computer vision. Images of "the same thing" can vary considerably by movements in space, changes in lighting, internal distortions and a different background. Thus, the abstract concept of an object can be defined as a huge equivalence class of the possible images showing that object, leaving..