Side-by-side Chinese-English

基于视频的掌纹掌脉联合识别系统

王浩1 康文雄1 陈晓鹏1

(1.华南理工大学自动化科学与工程学院, 广东广州 510641)

【摘要】搭建了基于视频的掌纹掌脉联合识别系统。首先对掌纹掌脉采用新的注册和识别方式,用系统获取的手掌运动视频来代替传统采集方式所获取的静态图像,认证时手掌无需刻意停留,只需横扫而过,有效地增强了认证的亲和性。提出了将旋转视频和横扫视频进行融合注册的新策略,从而确保了注册特征的丰富性和完整性,增强了系统对不同认证姿态的稳健性。为了提升已注册用户的识别速度,提出一种级联融合策略来进行识别。构建了一个包含100个手掌、1200段带有运动模糊的掌纹掌脉视频数据库,并在数据库上进行了大量仿真,结果显示新系统在915ms的期望耗时内能够达到1.51%的等误率,验证了所构建新系统的有效性和实用性。

【关键词】 机器视觉;生物特征认证;掌纹识别;掌脉识别;级联融合;

【DOI】

【基金资助】 国家自然科学基金(61573151); 广东省自然科学基金(2016A030313468); 广东省科技计划(2017A010101026); 广州市科技计划(201510010088);

Palm Print and Palm Vein Joint Recognition System Based on Video

WANG Hao1 KANG Wenxiong1 CHEN Xiaopeng1

(1.School of Automation Science and Engineering, South China University of Technology, Guangzhou, Guangdong, China 510641)

【Abstract】A novel palm print and palm vein joint recognition system based on video is built. First of all, a novel registration and identification approach is proposed. Instead of getting static image by traditional collection method, we obtain the palm motion video though the proposed system. The approach allows the users to simply sweep their palms over the acquisition platform without stop, which effectively enhances the affinity of authentication. A new strategy of fusing rotating videos with sweeping videos to generate the register feature set is proposed, which ensures the abundance and integrality of the register feature and enhances the robustness of the system to various palm postures in authentication. A cascade fusion strategy is presented to improve the recognition speed of the registered users. We construct a palm print and palm vein database containing 1 200 videos with motion blur from 100 palms and carry out a series of simulations. The results show that the proposed system can achieve a low equal error rate of 1.51% within the expected time consumption of 915 ms, which demonstrates the effectiveness and practicality of the new system.

【Keywords】 machine vision; biometrics authentication; palm print recognition; palm vein recognition; cascade fusion;

【DOI】

【Funds】 National Natural Science Foundation of China (61573151); Natural Science Foundation of Guangdong Province (2016A030313468); Science and Technology Program of Guangdong Province (2017A010101026); Science and Technology Program of Guangzhou City (201510010088);

Download this article
    References

    [1] Song W, Kim T, Kim H C, et al. A finger-vein verification system using mean curvature [J]. Pattern Recognition Letters, 2011 32 (11): 1541–1547.

    [2] Li Q, Qiu Z D, Sun D M, et al. A novel biometric: Knuckleprint [J]. Acta Automatica Sinica, 2007, 33 (6): 596–601(in Chinese).

    [3] Kang B J, Park K R. Multimodal biometric method based on vein and geometry of a single finger [J]. IETComputer Vision, 2010, 4 (3): 209–217.

    [4] Kang B J, Kang B P, Yoo J H, et al. Multimodal biometric method that combines veins, prints, and shape of a finger [J]. Optical Engineering, 2011, 50 (2): 029801.

    [5] Zhu L Q, Zhang S Y. Multimodal biometric identification system based on finger geometry, knuckle print and palm print [J]. Pattern Recognition Letters, 2010, 31 (12): 1641–1649.

    [6] Kong A, Zhang D, Kamel M. A survey of palmprint recognition [J]. Pattern Recognition, 2009, 42 (7): 1408–1418.

    [7] Jia W, Zhang B, Lu J, et al. Palmprint recognition based on complete direction representation [J]. IEEE Transactions on Image Processing, 2017, 26 (9): 4483–4498.

    [8] Fei L, Xu Y, Zhang D. Half-orientation extraction of palmprint features [J]. Pattern Recognition Letters, 2016, 69: 35–41.

    [9] Paula A, Rajeswari E, Lakshmi S S, et al. Robust palm vein pattern recognition system based on hybrid texture descriptors [J]. Biometrics and Bioinformatics, 2016, 8: 186–189.

    [10] Wang L, Leedham G, Cho S Y. Minutiae feature analysis for infrared hand vein pattern biometrics [J]. Pattern Recognition, 2008, 41 (3): 920–929.

    [11] Zhao S, Wang B, Tang C Y. Arm vein feature extraction and matching based on chain code [J]. Acta Optica Sinica, 2016, 36 (5): 0515003 (in Chinese).

    [12] Zhang D, Guo Z, Lu G, et al. Online joint palmprint and palmvein verification [J]. Expert Systems with Applications, 2011, 38 (3): 2621–2631.

    [13] Kumar A, Zhang D. Personal recognition using hand shape and texture [J]. IEEE Transactions on Image Processing, 2006, 15 (8): 2454–2461.

    [14] Qin W, Yin Y L, Liu L L. Video-based fingerprint verification [J]. Sensors, 2012, 13 (9): 11660–11686.

    [15] Fang Y X, Kang W X, Wu Q X, et al. A novel videobased system for in-air signature verification [J]. Computers & Electrical Engineering, 2017, 57: 1-14.

    [16] Kang W X, Wu Q X. Contactless palm vein recognition using a mutual foreground-based local binary pattern [J]. IEEE Transactions on Information Forensics and Security, 2014, 9 (11): 1974–1985.

    [17] Miura N, Nagasaka A, Miyatake T. Extraction of finger-vein patterns using maximum curvature points in image profiles [J]. IEICE Transactions on Information and Systems, 2007, E90D (8): 1185–1194.

    [18] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 (7): 971–987.

    [19] Kang W X, Chen X P. Fast representation based on a double orientation histogram for local image descriptors [J]. IEEE Transactions on Image Processing, 2015, 24 (10): 2915–2927.

    [20] Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60 (2): 91–110.

    [21] Yan X K, Kang W X, Deng F Q, et al. Palm vein recognition based on multi-sampling and feature-level fusion [J]. Neurocomputing, 2015, 151 (2): 798–807.

This Article

ISSN:0253-2239

CN:31-1252/O4

Vol 38, No. 02, Pages 248-256

February 2018

Downloads:0

Share
Article Outline

Abstract

  • 1 Introduction
  • 2 Introduction to the palm print and palm vein recognition system
  • 3 Video frame screening
  • 4 Extraction and matching of palm texture template
  • 5 Extraction and matching of local invariant features of palm print
  • 6 Cascade fusion in decision-making level
  • 7 Simulation results analysis
  • 8 Conclusion
  • References