基于弹性网格和Legendre矩的手写体汉字识别方法

Handwritten Chinese Character Recognition Based on Elastic Mesh and Legendre Moment

特征提取是手写体汉字识别的关键环节。论文提出了一种新的特征提取方法,即基于特征融合技术将弹性网格变换和Legendre矩变换结合起来,用弹性网格变换提取局部特征,用正交Legendre矩提取全局特征,然后使用K-L变换进行特征压缩,消除冗余信息。实验证明该方法是行之有效的。

Feature extraction is the key part of handwritten chinese character recognition.In this paper,a novel feature extraction method is proposed.First,elastic mesh transformation and legendre moment transformation are used to extract local and global feature on the basis of feature fusion.Then ,K-L transformation is taken to compress the feature.This mothod has been proved to be effective by experiment.