Discrete particle swarm optimization based on estimation of distribution for polygonal approximation problems

The polygonal approximation is an important topic in the area of pattern recognition, computer graphics and computer vision. This paper presents a novel discrete particle swarm optimization algorithm based on estimation of distribution (DPSO-EDA), for two types of polygonal approximation problems. Estimation of distribution algorithms sample new solutions from a probability model which characterizes the distribution of promising solutions in the search space at each generation. The DPSO-EDA incorporates the global statistical information collected from local best solution of all particles into the particle swarm optimization and therefore each particle has comprehensive learning and search ability. Further, constraint handling methods based on the split-and-merge local search is introduced to satisfy the constraints of the two types of problems. Simulation results on several benchmark problems show that the DPSO-EDA is better than previous methods such as genetic algorithm, tabu search, particle swarm optimization, and ant colony optimization.