Shape matching using fuzzy discrete particle swarm optimization

In this paper an efficient shape matching approach based on fuzzy discrete particle swarm optimization (FDPSO) is proposed. Based on fuzzy theory and PSO method, we applied this optimization method to a special combinatorial optimization problem: shape matching and recognition. Firstly, an original shape is approximated to a polygone and a shape representation of invariant attributes sequence is used. Then fuzzy matrices were adopted to represent the position and velocity of the particles in PSO. Finally, the superiority of our proposed method over traditional approaches to shape matching is demonstrated by experiments. The experimental results showed that our proposed method can achieve good results due to its robustness.

[1]  Zheru Chi,et al.  A hypersphere method for plant leaves classification , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[2]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[3]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[4]  Russell C. Eberhart,et al.  A discrete binary version of the particle swarm algorithm , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[5]  Thomas S. Huang,et al.  Modified Fourier Descriptors for Shape Representation - A Practical Approach , 1996 .

[6]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..