›› 2014, Vol. 23 ›› Issue (9): 96401-096401.doi: 10.1088/1674-1056/23/9/096401

• CONDENSED MATTER: STRUCTURAL, MECHANICAL, AND THERMAL PROPERTIES • 上一篇    下一篇

Biometric feature extraction using local fractal auto-correlation

陈熙a, 张家树b   

  1. a School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650051, China;
    b Key Lab of Signal & Information Processing of Sichuan Province, Southwest Jiaotong University, Chengdu 610031, China
  • 收稿日期:2013-10-10 修回日期:2014-02-23 出版日期:2014-09-15 发布日期:2014-09-15
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61262040, 61271341, 81360230, and 61271007) and the Applied Basic Research Projects of Yunnan Province, China (Grant No. KKSY201203062).

Biometric feature extraction using local fractal auto-correlation

Chen Xi (陈熙)a, Zhang Jia-Shu (张家树)b   

  1. a School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650051, China;
    b Key Lab of Signal & Information Processing of Sichuan Province, Southwest Jiaotong University, Chengdu 610031, China
  • Received:2013-10-10 Revised:2014-02-23 Online:2014-09-15 Published:2014-09-15
  • Contact: Chen Xi E-mail:xcbiometrics@126.com
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61262040, 61271341, 81360230, and 61271007) and the Applied Basic Research Projects of Yunnan Province, China (Grant No. KKSY201203062).

PDF (PC)

784

赞

摘要： Image texture feature extraction is a classical means for biometric recognition. To extract effective texture feature for matching, we utilize local fractal auto-correlation to construct an effective image texture descriptor. Three main steps are involved in the proposed scheme: (i) using two-dimensional Gabor filter to extract the texture features of biometric images; (ⅱ) calculating the local fractal dimension of Gabor feature under different orientations and scales using fractal auto-correlation algorithm; and (ⅲ) linking the local fractal dimension of Gabor feature under different orientations and scales into a big vector for matching. Experiments and analyses show our proposed scheme is an efficient biometric feature extraction approach.

关键词: fractal auto-correlation, fractal dimension, Gabor filter, biometric recognition

Abstract: Image texture feature extraction is a classical means for biometric recognition. To extract effective texture feature for matching, we utilize local fractal auto-correlation to construct an effective image texture descriptor. Three main steps are involved in the proposed scheme: (i) using two-dimensional Gabor filter to extract the texture features of biometric images; (ⅱ) calculating the local fractal dimension of Gabor feature under different orientations and scales using fractal auto-correlation algorithm; and (ⅲ) linking the local fractal dimension of Gabor feature under different orientations and scales into a big vector for matching. Experiments and analyses show our proposed scheme is an efficient biometric feature extraction approach.

Key words: fractal auto-correlation, fractal dimension, Gabor filter, biometric recognition

中图分类号:  (Fractal and multifractal systems)

  • 64.60.al
42.30.-d (Imaging and optical processing) 42.30.Sy (Pattern recognition)