计算机应用 ›› 2009, Vol. 29 ›› Issue (11): 3048-3050.

• 模式识别 • 上一篇    下一篇

基于中值夹角链码的掌静脉特征提取

杨闯,陈家新,黎蔚   

  1. 河南科技大学 电子信息工程学院
  • 收稿日期:2009-05-08 修回日期:2009-07-01 出版日期:2009-11-01 发布日期:2009-11-26
  • 通讯作者: 杨闯
  • 基金资助:
    河南省科技厅自然科学基金资助项目

Palm vein features extraction based on median-length included angle chain

Chuang YANG,Jia-xin CHEN,Wei LI   

  • Received:2009-05-08 Revised:2009-07-01 Online:2009-11-01 Published:2009-11-26
  • Contact: Chuang YANG

摘要: 结合夹角链码的特点,提出一种改进的提取手掌静脉结构特征的方法:中值夹角链码。通过中值迭代将细化后的静脉纹理曲线段用一组变长线段拟合,用距离法计算其拟合误差,在允许的误差下,根据相邻线段间的斜度差形成一串角度序列并计算中值夹角链码。实验结果表明,该方法保证了拟合精度,有效地提取出掌静脉结构特征,同时减少了计算量。

关键词: 中值夹角链码, 中值迭代, 特征提取, 手掌静脉, 拒识率, 误识率

Abstract: An improved approach: median-length included angle chain, combined with the included angle chain was presented to extract the structural features of the palm vein. The way is to model a curve segment of palm vein textures by a number of variable-length line segments through media value iteration and let distance criterion control the fitting error, under permitted error, using the included angles sequence between a pair of neighboring line segments to represent the curve segment. Experimental results show that while the computation precision is ensured, the proposed algorithm still can reduce the computation and acquire the structural features of the palm vein.

Key words: media-length included angle chain, media value iteration, feature extraction, palm vein, False Reject Rate (FRR), False Accept Rate (FAR)