基于Bandelet和分形维的手写签名鉴别系统  

Feature Extraction in Character Recognition based on Lifting Wavelet

作　　者：杨明[1] 陈玲玲[1] 

机构地区：[1]吉林化工学院信息与控制工程学院,吉林吉林132022

出　　处：《吉林化工学院学报》2014年第7期61-63,共3页Journal of Jilin Institute of Chemical Technology

基　　金：吉林化工学院科学技术研究项目(2013120)

摘　　要：签名鉴别分为联机鉴别和脱机鉴别.脱机鉴别丢失了手写过程中的动态信息,鉴别难度大.利用Bandlet小波分解,提取分解后图像的网格特征,借助分形维,得到了签名图像的特征向量.运用K—L变换,将特征向量降维之后,输入支持向量机进行分类鉴别.实验表明,本文算法是有效的.Handwritten signature verification（ HSV） can be classified into two categories： on-line HSV and off-line HSV. Off-line HSV is more difficult due to the loss of dynamic writing information. In this paper,a new feature extraction method is presented based on Bandlet and fractal dimension. After dimensionality reduction with K- L transform,genuine signatures and forgeries are distinguished with support vector machines（ SVM）.The result confirms the effectiveness of our method.

关 键 词：手写签名鉴别 特征向量提取 Bandlet变换 分形维 

分 类 号：TP391.43[自动化与计算机技术—计算机应用技术]