Handwritten English Character Recognition Based On Support Vector Machine

Handwritten Character Recognition research is a branch of the area of Optical Character Recognition (OCR), which deals with the recognition of handwritten English character or digits using computer. Support Vector Machine (SVM) is used as the implementation basis, which is a tool of Statistical Learning Theory (SLT).SLT is a machine learning theory based on samples, which was started by V. Vapnik in the 1970s and matured to form a complete theoretical architecture in the middle of 1990s. SVM, developed from that theoretical architecture, is a highly adaptive method, which is applied in the areas of Pattern Recognition, Regression Estimation, Function Approximation and Density Estimation. Independent Component Analysis was first proposed by Comon in 1994 to solve the problem of blind source separation, which is now widely used in the area of Pattern Recognition, Image Processing and Medical Science. Some new ideas are proposed in this thesis based on SVM and ICA:Firstly, a modified SVM method based on posteriori probability theory is given, which makes the classification super plane corrected from the original one. A better classification result is obtained without finding the best quadric optimization algorithm and large scale training datasets are reduced to small scale training datasets at the same time.Secondly, ICA is applied to the preprocessing period of the recognition character images for purpose of feature extraction and dimension reduction. A finely trimmed input datasets to SVM is formed to get a higher recognition rate and speed.The combination of SVM and ICA is highly effective in the recognition process. The dimension reduction of ICA is the fundamental factor in the recognition rate and speed improvement and the modified SVM method gives an amazing result in this area.