椭球基函数神经网络的指纹识别方法  

EBF neural network based on fingerprint recognition

作　　者：罗菁[1,2] 林树忠[2] 詹湘琳[3] 

机构地区：[1]天津工业大学计算机技术与自动化学院,天津300160 [2]天津工业大学天津市现代机电装备技术重点实验室,天津300160 [3]中国民航大学电子信息工程学院,天津300300

出　　处：《计算机工程与应用》2008年第34期219-222,共4页Computer Engineering and Applications

基　　金：国家自然科学基金重大项目No.60534050~~

摘　　要：椭球基函数(Ellipsoidal Basis Function,EBF)使网络划分输入空间成为封闭有界的局部作用的空间,与径向基函数(Radial Basis Function,RBF)神经网络的高斯函数相比,它对空间的划分更明确。因此,它的模式识别能力将有所提高。提出了一种基于EBF神经网络的指纹识别方法。首先,利用小波变换(Wavelet Transform,WT)直接从二值化指纹图像中提取细节特征,简化了复杂的预处理步骤,极大地减少了计算量,提高了识别的速度。同时利用EBF神经网络进行分类识别,有效提高了识别精度。该算法在FVC2000(国际指纹竞赛数据库)上作了测试。并与文献[9]中的WT-RBF算法进行比较。实验结果表明,提出的算法获取了较高的识别率,并且缩短了识别时间。An Ellipsoidal Basis Function（EBF） can make the partition of input space and make a limitary and bounded.Compared with the Gaussian function of Radial Basis Function（RBF） neural network,the EBF can make the partition of input space more specific.So,it has the higher capability of pattern recognition.A novel fingerprint recognition algorithm has been proposed in this paper,which is based on EBF neural network.Firstly,wavelet feature is extracted on the binary fingerprint images with the help of Wavelet Transform（WT）,which has made the preprocessing simple and improved the speed of fingerprint recognition. Then,fingerprint recognition can be realized by EBF neural network and the rate of fingerprint recognition has been improved.The experimental results based on FVC2000 have verified that the proposed algorithm has higher recognition rate and speed than WT-RBF.

关 键 词：指纹识别 椭球基函数 神经网络川 波变换(WT) 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]