Chinese Minority Script Recognition Using Radial Basis Function Network

The existing Chinese Minorities OCR system is mainly oriented in the "literacy" level, the script recognition has not attracted the attention it deserves, and the area of recognizing the kinds of Chinese minority scripts is still in a blank. The method of recognizing the kinds of Chinese minority scripts based on wavelet analysis and Radial Basis Function Network (RBFN) is presented which adopts wavelet decomposition that obtains feature descriptor of wavelet energy and wavelet energy distribution proportion. Combined with the texture feature of Chinese minority scripts, and construct multivariate classification in Radial Basis Function Network (RBFN). By building a data set which contains Tibetan, Tai Lue, Naxi Pictographs, Uighur, Tai Le, Yi 6 kinds common Chinese Minority Script, Chinese and English 8 kinds in total, we take a test to the Data Set of Chinese Minority by means of method in this paper, and the result shows that the method in the paper outperforms the traditional Bayes and KNN classification.

[1]  David S. Broomhead,et al.  Systolic array for nonlinear multidimensional interpolation using radial basis functions , 1990 .

[2]  David Zhang,et al.  A novel face recognition approach based on kernel discriminative common vectors (KDCV) feature extraction and RBF neural network , 2008, Neurocomputing.

[3]  Bedrich J. Hosticka,et al.  Unsupervised texture segmentation of images using tuned matched Gabor filters , 1995, IEEE Trans. Image Process..

[4]  Jian Fan,et al.  Texture Classification by Wavelet Packet Signatures , 1993, MVA.

[5]  Trac D. Tran,et al.  Rational Coefficient Dual-Tree Complex Wavelet Transform: Design and Implementation , 2008, IEEE Transactions on Signal Processing.

[6]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[7]  Fergus McInnes,et al.  A comparative study of continuous speech recognition using neural networks and hidden Markov models , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[8]  Li Zhen.  The Research of Printed Mongolian Character Recognition , 2003 .

[9]  Wang Hua.  Multi-font multi-size printed Uyghur character recognition , 2004 .

[10]  S. Renals,et al.  Phoneme classification experiments using radial basis functions , 1989, International 1989 Joint Conference on Neural Networks.

[11]  M. M. Leung,et al.  Scale and rotation invariant texture classification , 1992, [1992] Conference Record of the Twenty-Sixth Asilomar Conference on Signals, Systems & Computers.

[12]  Rangasami L. Kashyap,et al.  A Model-Based Method for Rotation Invariant Texture Classification , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Wang Weilan.  Study on Printed Tibetn Character Recognition , 2003 .

[14]  C.-C. Jay Kuo,et al.  Texture analysis and classification with tree-structured wavelet transform , 1993, IEEE Trans. Image Process..

[15]  Xu Jianfeng.  Web Embedding Fonts Technology of Naxi Pictographs , 2005 .