Application of Artificial Immune System in Handwritten Greek Character Recognition
Artificial immune system which is based upon models of the natural immune system is a new computational intelligence approach after artificial neural network and evolutionary computation. It has been appfied gradually in many fields upon powerful abilities of information processing and problem solution. In this paper, handwritten Greek character recognition strategy using artificial immune system was proposed and carefully experimented. With 64 feature coefficients extracted from the handwritten Greek character image using 3*3 sub-meshing as its feature vector, 24 antibody . Libraries were trained and built to recognize handwritten characters with artificial immune algorithm. The contrast experiment was done using BP neural network. The experimental results indicated that the artificial immune system model has more advantages than BP neural network in handwritten Greek character recognition。
pattern recognition artificial immune system BP neural network
YUY ANG
Basic Department The Chinese Peoples Armed Police Forces Academy, Langfang, China
国际会议
重庆
英文
1707-1709
2011-08-20（万方平台首次上网日期，不代表论文的发表时间）