Rotation and scale change invariant point pattern relaxation matching by the Hopfield neural network

Relaxation matching is one of the most relevant methods for image matching. The original relaxation matching technique using point patterns is sensitive to rotations and scale changes. We improve the original point pattern relaxation matching technique to be invariant to rotations and scale changes. A method that makes the Hopfield neural network perform this matching process is discussed. An advantage of this is that the relaxation matching process can be performed in real time with the neural network's massively parallel capability to process infor- mation. Experimental results with large simulated images demonstrate the effectiveness and feasibility of the method to perform point pattern relaxation matching invariant to rotations and scale changes and the method to perform this matching by the Hopfield neural network. In ad- dition, we show that the method presented can be tolerant to small ran- dom error. © 1997 Society of Photo-Optical Instrumentation Engineers. (S0091-3286(97)02212-5)

[1]  Azriel Rosenfeld,et al.  Point pattern matching by relaxation , 1980, Pattern Recognit..

[2]  Rae-Hong Park,et al.  Relaxation algorithm for shape matching of two-dimensional objects , 1989, Pattern Recognit. Lett..

[3]  Michel Levy.  A new theoretical approach to relaxation, application to edge detection , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[4]  Marc Berthod.  Global Optimization of a Consistent Labeling , 1983, IJCAI.

[5]  Wen-Hsiang Tsai,et al.  Relaxation by the Hopfield neural network , 1992, Pattern Recognit..

[6]  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.

[7]  Ramakant Nevatia,et al.  Matching Images Using Linear Features , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Guoyou Wang,et al.  Relaxation matching by the Hopfield neural network , 1996, Electronic Imaging.

[9]  R. Poeckert,et al.  A control point matching algorithm , 1993, Pattern Recognit..

[10]  Hsi-Jian Lee,et al.  Region matching and depth finding for 3D objects in stereo aerial photographs , 1990, Pattern Recognit..

[11]  Tianxu Zhang,et al.  Point pattern relaxation matching: invariant to rotations and scale changes , 1997, Defense, Security, and Sensing.

[12]  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.