Application of Particle Swarm Optimization to Pattern Identification

作     者：Zhang Ying~(1,2) Chen Xuebo~2, Wu Qinghong~2, Wang Wei~1 (1.School of Electronic and Information Engineering, Dalian University of Technology, Dalian 116024, China) (2. School of Electronic and Information Engineering, Anshan University of Science and Technology, Liaoning, 114044, China) 

会议名称：《第二十四届中国控制会议》

会议日期：2005年

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 071102[理学-系统分析与集成] 081103[工学-系统工程] 

基　　金：Supported by National Natural Science Foundation of China (No. 60474058) 

关 键 词：pattern identification PSO binarization thinning 

摘      要：正 A new algorithm for supervised pattern identification based on Particle Swarm Optimization （PSO） is proposed in this paper. At first, an image database with training image samples is set up. Secondly, image samples to be identified and stored in the database are preprocessed. Then, point matching is made between the identified images after preprocesing with the training images after preprocesing by using PSO, respectively. Finally, the identification is realized by seeking the minimum of a defined classification function. This algorithm is approved to be effective, accurate and simple by the experiments.