基于优化分割重建图像的文本无关笔迹鉴定

笔迹鉴定的主要过程首先是系统把手写的笔迹文字通过扫描仪输入计算机，然后对原始笔迹的图像进行预处理。在预处理阶段，本文提出了优化分割重建图像的归一化预处理方法，在参数提取阶段，本文采用多通道二维G2bro滤波器，通过计算4个方向每个方向4个频率来提取的笔迹特征。本文对10个人任意书写的笔迹进行实验，鉴别正确率得到较好的提高。

Text-Independent Writer Identification based on Optimized Segmentation and Reconstructed Handwriting Image

The main processions of writer identification are scanning handwriting images, normalization pre-procession, writer texture features extraction, training writer model, writer identification. We use the method of optimized segmentation and reconstructed handwriting images. We apply the well-established multi-channel Gabor filtering technique to extract features and a Weighted Euclidean Distance classifier to fulfill the identification task. Experiments are made using Chinese handwritings from 10 different persons and very promising results are achieved.