Local Scale Selection for Gaussian Based Description Techniques

This paper addresses the problem of the local scale parameter selection for recognition techniques based on Gaussian derivatives. Patterns are described in a feature space of which each dimension is a scale and orientation normalized receptive field (a unit composed of normalized Gaussian-based filters). Scale invariance is obtained by automatic selection of an appropriate local scale [Lin98b] and followed by normalisation of the receptive field to the appropriate scale. Orientation invariance is obtained by the determination of the dominant local orientation and by steering the receptive fields to this orientation. Data is represented structurally in a feature space that is designed for the recognition of static object configurations. In this space an image is modeled by the vectorial representation of the receptive field responses at each pixel, forming a surface in the feature space. Recognition is achieved by measuring the distance between the vector of normalized receptive fields responses of an observed neighborhood and the surface point of the image model. The power of a scale equivariant feature space is validated by experimental results for point correspondences in images of different scales and the recognition of objects under different view points.

[1]  Irene A. Stegun,et al.  Handbook of Mathematical Functions. , 1966 .

[2]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[3]  Michael S. Landy,et al.  Computational models of visual processing , 1991 .

[4]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[6]  Andrea J. van Doorn,et al.  Generic Neighborhood Operators , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  O. Faugeras Three-dimensional computer vision: a geometric viewpoint , 1993 .

[8]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..

[9]  Lucas J. van Vliet,et al.  Recursive implementation of the Gaussian filter , 1995, Signal Process..

[10]  Michael J. Black,et al.  EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation , 1996, ECCV.

[11]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[12]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  James L. Crowley,et al.  Visual Recognition Using Local Appearance , 1998, ECCV.

[14]  James L. Crowley,et al.  Probabilistic recognition of activity using local appearance , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).