Vectorizing Face Images by Interleaving Shape and Texture Computations

摘要

The correspondence problem in computer vision is basically a matching taskbetween two or more sets of features. Computing feature correspondence is of great importance in computer vision, especially in the subfields of object recognition, stereo, and motion. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. The representation consists of two image measurements made at the feature points: shape and texture. Feature geometry, or shape, is represented using the (x, y) locations of features relative to the some standard reference shape. Image grey levels, or texture, are represented by mapping image grey levels onto the standard reference shape. Computing this representation is essentially a correspondence task, and in this paper we explore an automatic technique for 'vectorizing' face images. Our face vectorizer alternates back and forth between computation steps for shape and texture, and a key idea is to structure the two computations so that each one uses the output of the other. Namely, the texture computation uses shape for geometrical normalization, and the shape computation uses the texture analysis to synthesize a 'reference' image for finding correspondences. A hierarchical coarse-to-fine implementation is discussed, and applications are presented tQ the problems of facial feature detection and registration of two arbitrary faces.