The correspondence problem in computer vision is basically a matching task between two or more sets of features. 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. This representation has two components: (1) shape, or (x, y) feature locations, and (2) texture, defined as the image grey levels mapped onto the standard reference image. This paper explores 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. A hierarchical coarse-to-fine implementation is discussed, and applications are presented to the problems of facial feature detection and registration of two arbitrary faces.
Cited By
- Liu C (2004). Gabor-Based Kernel PCA with Fractional Power Polynomial Models for Face Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 26:5, (572-581), Online publication date: 1-May-2004.
- Zhao W, Chellappa R, Phillips P and Rosenfeld A (2003). Face recognition, ACM Computing Surveys (CSUR), 35:4, (399-458), Online publication date: 1-Dec-2003.
- Fan L and Sung K Model-based varying pose face detection and facial feature registration in video images Proceedings of the eighth ACM international conference on Multimedia, (295-302)
- Jones M and Poggio T (1998). Multidimensional Morphable Models, International Journal of Computer Vision, 29:2, (107-131), Online publication date: 29-Aug-1998.
- Vetter T and Poggio T (1997). Linear Object Classes and Image Synthesis From a Single Example Image, IEEE Transactions on Pattern Analysis and Machine Intelligence, 19:7, (733-742), Online publication date: 1-Jul-1997.
Recommendations
Elastic shape-texture matching for human face recognition
In this paper, a novel, elastic, shape-texture matching method, namely ESTM, for human face recognition is proposed. In our approach, both the shape and the texture information are used to compare two faces without establishing any precise pixel-wise ...
Biview face recognition in the shape-texture domain
Face recognition is one of the biometric identification methods with the highest potential. The existing face recognition algorithms relying on the texture information of face images are affected greatly by the variation of expression, scale and ...
Feature Correspondence by Interleaving Shape and Texture Computations
CVPR '96: Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been ...