基于小波分析及KNN的民族文字分类方法

A Chinese Minority Script Recognition Method Based on Wavelet Feature and KNN

摘要: 提出一种基于小波分析的少数民族文字文字分类识别方法.该方法采用多辨识小波分解, 从而获得小波能量和小波能量比例分布的特征描述, 结合少数民族文字文本图片的纹理特征, 选择加权KNN分类器.实验证明:该识别方法对藏文、西双版纳傣文、纳西象形文、维吾尔文、德宏傣文和彝文6种常用的少数民族文字及汉字、英语共8种文字的分类测试达到96%的识别效果.

Abstract: The method of recognizing the kinds of Chinese minority scripts based on wavelet analysis and K-Nearest Neighbour (KNN) 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, radially classification in Feature-Weighted K-Nearest Neighbour (FWKNN) .Among Chinese, English and Chinese minority scripts such as Tibetan, Tai Lue, Naxi Pictographs, Uighur, Tai Le, Yi, the experimental results show the recognition rate is up to 96%.