Research On Chinese Characters Code Of Bearable Mistakes Method For Off-line Handwritten Chinese Characters Recognition

Human ocular apperceive is truly a robust character recognition system with fine bearable mistake ability which can adapts to all kinds of noises. Recently, much about handwritten Chinese characters recognition has been made. It is a significative research on how the classify-related image feature is extracted and how the bearable mistakes code is made to improve the bearable mistake ability of the computer.The following are the major contents in the thesis:1 , The classification and recognition of Chinese characters form. A two level compartmentalization method is presented. The method based on the combination of horizontal and vertical projection with connected component is adopted to recognize the form classification of the Chinese characters image. Form classification code is given. The form of handwritten Chinese characters can be accurately classified with this arithmetic.2,The bearable mistakes code method for Chinese characters. A kind of Chinese characters codes which agree with the mechanism of apery imitation for computer cognition is presented in this paper. Elements groups of Chinese characters are made for machine cognition. Bearable mistakes codes of various categories are given for the elements which are easily confused. Rules for judging stroke sequence are given. 36 kinds of subsidiary configurations codes and bearable mistakes codes are constructed. The code principles and multi-template dictionary of Chinese characters which agree with apery imitation are established to apply to the deformation factors of handwritten Chinese characters.3 , Chinese characters recognition based on the code. The method about Chinese characters recognition based on the bearable mistakes code is proposed here. Comparison rules about the three characteristic are constructed. A set of Chinese characters bearable mistakes recognition method with reaction are constructed, based on and using the error estimation approach of Chinese characters outlines feature.4, Classification capability and the analysis about the rate of repeated codes. The rate of standard Chinese characters repeated codes and the type of repeated codeChinese characters are given.5, The analysis about the capability of bearable mistakes. Theoretics analysis is given for the capability of bearable mistakes of the whole codes. The recognition result about handwritten Chinese characters is given. The styles of the rejective and wrong recognition Chinese characters are analyzed.The research in this article shows that: The bearable mistakes code method can well token and differentiate the Chinese characters. Handwritten Chinese characters recognition based on the bearable mistakes code can apply to the deformation factors of handwritten Chinese characters and effectively improve the noise immunity and correct rate of the system.