基于优化分割重建图像的文本无关笔迹鉴定  

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

作　　者：黄创光[1] 欧贵文[1] 

机构地区：[1]中山大学计算机科学系,广州510275

出　　处：《现代计算机》2003年第9期6-9,共4页Modern Computer

摘　　要：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Gabor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。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.

关 键 词：计算机视觉 模式识别 手写体笔迹 鉴定 图像重建 图像分割 优化 文本无关笔迹 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]