计算机应用 ›› 2015, Vol. 35 ›› Issue (4): 1129-1132.DOI: 10.11772/j.issn.1001-9081.2015.04.1129

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于稀疏编码的手背静脉识别算法

贾旭1, 王锦凯1, 崔建江2, 孙福明1, 薛定宇2   

  1. 1. 辽宁工业大学 电子与信息工程学院, 辽宁 锦州 121001;
    2. 东北大学 信息科学与工程学院, 沈阳 110819
  • 收稿日期:2014-10-20 修回日期:2014-12-09 出版日期:2015-04-10 发布日期:2015-04-08
  • 通讯作者: 贾旭
  • 作者简介:贾旭(1983-),男,辽宁开原人,副教授,博士,主要研究方向:生物特征识别; 王锦凯(1982-),男,辽宁锦州人,讲师,硕士,主要研究方向:模式识别、图像处理; 崔建江(1964-),男,辽宁沈阳人,副教授,博士,主要研究方向:生物特征识别; 孙福明(1972-),男,辽宁锦州人,教授,博士,主要研究方向:模式识别、机器学习; 薛定宇(1963-),男,辽宁沈阳人,教授,博士,主要研究方向:模式识别、系统仿真。
  • 基金资助:

    国家自然科学基金资助项目(61272214); 辽宁省教育厅资助项目(L2013241)。

Dorsal hand vein recognition algorithm based on sparse coding

JIA Xu1, WANG Jinkai1, CUI Jianjiang2, SUN Fuming1, XUE Dingyu2   

  1. 1. School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou Liaoning 121001, China;
    2. College of Information Science and Engineering, Northeastern University, Shenyang Liaoning 110819, China
  • Received:2014-10-20 Revised:2014-12-09 Online:2015-04-10 Published:2015-04-08

摘要:

为提高静脉特征提取的有效性,提出了基于稀疏编码的手背静脉识别算法。首先,在图像采集过程中,依据实时的质量评价结果对采集系统参数进行自适应调整,获取高质量静脉图像;其次,针对主观选择的特征有效性主要依赖于经验的缺陷,提出了基于稀疏编码的特征学习机制,从而获得客观优质的静脉特征。实验结果表明,基于所提算法获得的静脉特征具有较好的类间区分性与类内紧凑性,令使用该算法的系统具有较高的识别率。

关键词: 静脉识别, 质量评价, Gabor变换, 稀疏编码, 特征优化

Abstract:

In order to improve the effectiveness of vein feature extraction, a dorsal hand vein recognition method based on sparse coding was proposed. Firstly, during image acquisition process, acquisition system parameters were adaptively adjusted in real-time according to image quality assessment results, and the vein image with high quality could be acquired. Then concerning that the effectiveness of subjective vein feature mainly depends on experience, a feature learning mechanism based on sparse coding was proposed, thus high-quality objective vein features could be extracted. Experiments show that vein features obtained by the proposed method have good inter-class separableness and intra-class compactness, and the system using this algorithm has a high recognition rate.

Key words: vein recognition, quality assessment, Gabor transform, sparse coding, feature optimization

中图分类号: