基于矩和Gabor变换的手写体汉字识别方法

Handwritten chinese character recognition basedon moment and gabor transformation

特征提取是手写体汉字识别的一个研究难点。本文提出了一种基于特征融合的新提取方法,即将Gabor变换和正交矩变换结合起来,用正交Zernike矩提取全局特征,用Gabor变换提取局部特征,然后使用主成分分析的方法进行特征压缩。由此得到的特征向量能从整体上和局部上反映汉字的特征。实验证明该方法是行之有效的。

Feature extraction is the difficulty of handwritten chinese character recognition. In this paper, a novel feature extraction method based on feature fusion is proposed. First, Gabor transformation and Zernike moments are used to extract local and global feature. Then, principal component analysis is taken to compress the local feature. This mothod has been proved to be effective.