The Research Of Off-line Hand Written Chinese Character Recognition Based On Fuzzy Stroke Directional Feature

Chinese character recognition is automatically recognizing Chinese characters printed or written on paper with the help of computer.It is pertain to pattern recognition and artificial intelligence. It deals with pattern recognition,image processing,artificial intelligence, formal language and automata, fuzzy mathematics, compounding mathematics, informatics,Chinese information processing,as well as linguistics, psychology, bionics.It is a universal technology.In this article,fisrt,We studied the preproeessing of the handwritten recognition, including standardization,separation,erasing the redundancy information and thiriningit.A fuzzy stroke extraction method is proposed to resolve the unsteadiness because of the unconstrained written fashion. First calculating the attribution feature of boundary point related to the four fuzzy strokes—horizontal,vertical,left diagonal and right diagonal,then combing fuzzy mesh with fuzzy sub-stroke attribution feature of boundary points to obtain the fuzzy sub-stroke statistical feature of a Chinese character.In the designing of recognition classifier, we discussed the structer recognition and the number chice of nerve cells and the paramenters o the improved BP netural netwok,etc. We discussed the realization of BP netual network on MATLAB,and presented the foundation,training and simulating of the improved BP netural network.In this article,we collect the capital handwritten Chinese characters"零,壹,贰,叁,肆,伍,陆,�',捌,玖,拾"as the stylebook,and they are used for the simulation experiments,. The experimental rensults show that resolve the unsteadiness because of the unconstrained written fashion.