| Chinese Characters recognition is one aspect of pattern recognition field. SVM (Support Vector machine) , the theory of small-sample statistical learning proposed by Vapnik, is an important research direction in pattern recognition. Based on the idea of Experience Risk Minimization, it is a good learning method for especially studying small-sample prediction. A new structural learning method has be developed by SVM. It can well solve the construction issue of a high dimensional model of small-sample set. It can get a biggish theory meaning and practice value that the SVM theory is used for the off-line Handwritten Chinese Characters Recognizing.The primary contents of this paper are:(1) Chinese Characters Image pretreatment. The image de-noise and normalization are researched in this phase. The wavelet high frequency coefficient is researched. After this ,a wavelet part thresholding method is designed in image de-noise. The test shows that the method is in evidence effective. While in the image normalization, the Bicubic interpolation method is used in it.(2) Characters feature extraction. A new feature extraction method based on fuzzy statistic feature is proposed. The feature date is extracted by three methods (the density of Chinese characters stokes, wavelet transform and elastic meshing, and fuzzy statistic feature). Characters statistic feature and strokes feature can be denotation by the three methods inosculated date. The inosculated date is more useful in SVM recognition.(3) Characters recognition machine. A recognition machine is designed based on the SVM method. The effect of recognition is satisfy by using small number of off-line hand written Chinese Characters samples.The test and simulation indicate: The SVM method can be used practically in SCUT-IRAC off-line handwritten Chinese characters recognition. It is effective and scientific that the handwritten Chinese characters is recognized on the feature small-sample. |
PDF Full Text Request