J4

• 计算机科学 • 上一篇    下一篇

基于脊波变换的手背静脉图像增强及特征提取

韩笑, 马驷良, 张忠波   

  1. 吉林大学 数学研究所, 长春 130012
  • 收稿日期:2006-03-13 修回日期:1900-01-01 出版日期:2006-05-26 发布日期:2006-05-26
  • 通讯作者: 韩笑

Image Enhancement and Extracting Features ofthe Dorsal Hand Vein Patterns Based on Ridgelet Transform

HAN Xiao, MA Si-liang, ZHANG Zhong-bo   

  1. Institute of Mathematics, Jilin University, Changchun 130012, China
  • Received:2006-03-13 Revised:1900-01-01 Online:2006-05-26 Published:2006-05-26
  • Contact: HAN Xiao

摘要: 根据人体手背静脉图像的结构及特点, 提出一种基于脊波变换的手背静脉图像增强方法, 并应用局部互联神经网络提取静脉图像特征, 加强了该生物识别系统对模糊图像的识别能力. 实验结果表明, 该方法与传统的拉普拉斯法、 平滑算法及小波变换相比有更加显著的效果.

关键词: 生物识别, 静脉, 模式识别, 脊波

Abstract: Firstly, this paper presents a method of the dorsal hand vein pattern recognition based on ridgelet transform according to the structure and features of human hand vein patterns images. Secondly, a neural network with local interconnection structure described for its application to extracting the features of hand vein patterns images in order to improve the recognition ability of this biometric system for the unclear image. The experimental data show that this method has more perfect results. 

Key words: biometrics, vein pattern, pattern recognition, ridgelet

中图分类号: 

  • TP301