Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (20): 216-218.DOI: 10.3778/j.issn.1002-8331.2010.20.059

• 人工智能 • Previous Articles     Next Articles

Gabor fingerprint enhancement method based on adaptive mask size

LI Tie-jun,QIN Wei   

  1. School of Computer Science and Technology,Shandong University,Jinan 250101,China
  • Received:2010-04-15 Revised:2010-05-18 Online:2010-07-11 Published:2010-07-11
  • Contact: LI Tie-jun

自适应模板大小的Gabor指纹增强方法

李铁军,秦 伟   

  1. 山东大学 计算机科学与技术学院,济南 250101
  • 通讯作者: 李铁军

Abstract: In Gabor method,the enhancement mask size is constant for a fingerprint impression.This may lead to the changing of ridge structure in the blocks where ridge direction varies significantly.A new method using adaptive mask size is proposed.Larger mask size will be used when ridge direction varies less.Experimental results show that the proposed method is more effective to improve the clarity of ridge and valley structure.This paper conducts the experiments on 3 databases of FVC 2004 and the ROC curves indicate that the accuracy of fingerprint system will be improved when the method is introduced.

Key words: fingerprint recognition, fingerprint enhancement, Gabor filters, adaptive mask size

摘要: 对一幅图像而言,现有的Gabor增强方法对各个分块使用的增强模板大小是定值,这可能会破坏纹线方向变化较大的分块的纹线信息。提出了自适应模板大小的Gabor指纹增强方法,使增强模板的大小与块内纹线方向的稳定程度成正相关。实验表明,相比固定模板大小的方法,该文方法具有更好的连接断线和去除粘连的能力,同时不会破坏纹线方向变化较大的分块的纹线信息。在FVC2004的3个指纹库上分别进行了实验,ROC曲线显示,将该文方法用于指纹增强能够提高系统的识别率。

关键词: 指纹识别, 指纹增强, Gabor滤波器, 自适应模板大小

CLC Number: