Distances between frequency features for 3D visual pattern partitioning

In this paper we propose a technique for the decomposition of a 3D image into a set of low level patterns associated to phase congruency, which we call visual patterns. Those patterns have frequency components in a wide range of bands that are aligned in phase. The method involves clustering of the band-pass filtered versions of the image according to a measure of congruence in phase or, what is equivalent, alignment in the filter's responses energy maxima. This is achieved by defining a distance between the responses of pairs of filters and applying a hierarchical clustering analysis to the resulting distance matrix. To measure the degree of maxima alignment we propose a set of alternative distances and study their suitability. From this study we conclude that a measure of linear dependence between the local energy of filters' responses is more appropriate than a more general measure of dependence.

[1]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Quick Rf.  A vector-magnitude model of contrast detection. , 1974 .

[3]  Nicholas Ayache,et al.  Unifying maximum likelihood approaches in medical image registration , 2000 .

[4]  Xosé R. Fernández-Vidal,et al.  Multiresolution Approach to "Visual Pattern" Partitioning of 3D Images , 2004, ICIAR.

[5]  J. Chamorro-MartJ,et al.  A FREQUENCY-DOMAIN APPROACH FOR THE EXTRACTION OF MOTION PATTERNS , 2003 .

[6]  Nikhil R. Pal,et al.  Cluster validation using graph theoretic concepts , 1997, Pattern Recognit..

[7]  Svetha Venkatesh,et al.  On the classification of image features , 1990, Pattern Recognit. Lett..

[8]  Xosé R. Fernández-Vidal,et al.  The RGFF Representational Model: A System for the Automatically Learned Partitioning of 'Visual Patterns' in Digital Images , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Robyn A. Owens,et al.  Feature detection from local energy , 1987, Pattern Recognit. Lett..

[10]  M. Basseville.  Information : entropies, divergences et moyennes , 1996 .

[11]  Jitendra Malik,et al.  Detecting and localizing edges composed of steps, peaks and roofs , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[12]  N. Graham.  Visual Pattern Analyzers , 1989 .

[13]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[14]  David Sarrut,et al.  Similarity measures for image registrationDavid , 1999 .

[15]  Paul A. Viola,et al.  Alignment by Maximization of Mutual Information , 1997, International Journal of Computer Vision.

[16]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[17]  Svetha Venkatesh,et al.  Edge detection is a projection , 1989, Pattern Recognit. Lett..

[18]  Peter Kovesi,et al.  Invariant measures of image features from phase information , 1996 .

[19]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[20]  Lucas J. van Vliet,et al.  3D-Orientation Space; Filters and Sampling , 2003, SCIA.

[21]  Nicholas Ayache,et al.  The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration , 1998, MICCAI.

[22]  D. Burr,et al.  Feature detection in human vision: a phase-dependent energy model , 1988, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[23]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.