Voronoi Pyramids Controlled by Hopfield Neural Networks

We present a novel method for irregular pyramid construction. The contributions of this paper are twofold: (1) Instead of starting with the original regular pixel grid, we first apply an adaptive Voronoi tessellation to the image. This provides the advantage that the number of cells at the bottom level of the pyramid is already reduced as compared to the number of pixels of the original image. (2) For the construction of the irregular pyramid, we present a Hopfield neural network which controls the decimation process. The decimation by Hopfield networks includes naturally the concept of the adaptive pyramid. The validity of our approach is demonstrated by several examples in image segmentation.

[1]  R. Marcelpoil,et al.  Methods for the study of cellular sociology: Voronoi diagrams and parametrization of the spatial relationships , 1992 .

[2]  V. Ralph Algazi,et al.  Continuous skeleton computation by Voronoi diagram , 1991, CVGIP Image Underst..

[3]  J. Chassery,et al.  2 - Diagramme de Voronoï appliqué à la segmentation d'images et à la détection d'évènements en imageris multi-sources (1) , 1991 .

[4]  Horst Bischof,et al.  Pyramidal Neural Networks , 1995 .

[5]  Walter G. Kropatsch,et al.  Preserving Topology in the Irregular Curve Pyramid , 1993, DAGM-Symposium.

[6]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[7]  Steven W. Zucker,et al.  Region growing: Childhood and adolescence* , 1976 .

[8]  Hanan Samet,et al.  The Design and Analysis of Spatial Data Structures , 1989 .

[9]  Robert M. Haralick,et al.  Glossary of computer vision terms , 1990, Pattern Recognit..

[10]  Jean-Michel Jolion,et al.  The adaptive pyramid: A framework for 2D image analysis , 1991, CVGIP Image Underst..

[11]  P. Stevens Patterns in Nature , 1974 .

[12]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Hanan Samet,et al.  Connected Component Labeling Using Quadtrees , 1981, JACM.

[14]  Azriel Rosenfeld,et al.  A critical view of pyramid segmentation algorithms , 1990, Pattern Recognit. Lett..

[15]  Walter G. Kropatsch,et al.  Neural Networks versus Image Pyramids , 1993 .

[16]  Ramesh C. Jain,et al.  A Pyramid-Based Approach to Segmentation Applied to Region Matching , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Walter G. Kropatsch,et al.  Hopfield networks for irregular decimation , 1994 .

[18]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[19]  J. C. Tilton Image segmentation by iterative parallel region growing with applications to data compression and image analysis , 1988, Proceedings., 2nd Symposium on the Frontiers of Massively Parallel Computation.

[20]  Walter G. Kropatsch,et al.  The Dual Irregular Pyramid , 1993, CAIP.

[21]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[22]  Robin Sibson,et al.  Computing Dirichlet Tessellations in the Plane , 1978, Comput. J..

[23]  Donald Geman,et al.  Boundary Detection by Constrained Optimization , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  J. Chassery,et al.  Segmentation and measurement based on 3D Voronoi diagram: application to confocal microscopy. , 1993, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[25]  Pascal Bertolino,et al.  Edge detection for biomedical images: A self-adaptive and randomized operator , 1992, 1992 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Azriel Rosenfeld,et al.  Arc Colorings, Partial Path Groups, and Parallel Graph Contractions , 1989, J. Parallel Distributed Comput..

[27]  Steven L. Tanimoto,et al.  Paradigms for pyramid machine algorithms , 1986 .

[28]  Sanjeev Saxena,et al.  Efficient VLSI Parallel Algorithm for Delaunay Triangulation on Orthogonal Tree Network in Two and Three Dimensions , 1990, IEEE Trans. Computers.

[29]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[30]  H. Honda Description of cellular patterns by Dirichlet domains: the two-dimensional case. , 1978, Journal of theoretical biology.

[31]  Santosh S. Venkatesh,et al.  The capacity of the Hopfield associative memory , 1987, IEEE Trans. Inf. Theory.

[32]  Sudhakar M. Reddy,et al.  Guaranteed convergence in a class of Hopfield networks , 1992, IEEE Trans. Neural Networks.

[33]  Peter Meer,et al.  Stochastic image pyramids , 1989, Comput. Vis. Graph. Image Process..