A mean field annealing approach to robust corner detection

This paper is an extension of our previous paper to improve the capability of detecting corners. We proposed a method of boundary smoothing for curvature estimation using a constrained regularization technique in the previous paper. We propose another approach to boundary smoothing for curvature estimation in this paper to improve the capability of detecting corners. The method is based on a minimization strategy known as mean field annealing which is a deterministic approximation to simulated annealing. It removes the noise while preserving corners very well. Thus, we can detect corners easier and better in this approach than in the constrained regularization approach. Finally, some matching results based on the corners detected by corner sharpness in the mean field annealing approach are presented as a demonstration of the power of the proposed algorithm.

[1]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[2]  C. Reinsch.  Smoothing by spline functions , 1967 .

[3]  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.

[4]  R.M. McElhaney,et al.  Algorithms for graphics and image processing , 1983, Proceedings of the IEEE.

[5]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[6]  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.

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

[8]  José L. Marroquín,et al.  Probabilistic solution of inverse problems , 1985 .

[9]  Wesley E. Snyder,et al.  Range Image Restoration Using Mean Field Annealing , 1988, NIPS.

[10]  Miller,et al.  Graph partitioning using annealed neural networks , 1989 .

[11]  N. M. Nasrabadi,et al.  Object recognition based on graph matching implemented by a Hopfield-style neural network , 1989, International 1989 Joint Conference on Neural Networks.

[12]  Wei-Chung Lin,et al.  A hierarchical multiple-view approach to three-dimensional object recognition , 1991, IEEE Trans. Neural Networks.

[13]  Wesley E. Snyder,et al.  A Constrained Regularization Approach to Robust Corner Detection , 1994, IEEE Trans. Syst. Man Cybern. Syst..