基于图像采集质量评价的指纹与指静脉双模态识别决策级融合方法

摘要
图/表
参考文献
相关文章 (12)

全文: PDF (816 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对单一模态生物特征识别系统性能受图像质量影响较大问题，提出一种基于图像采集质量评价的指纹与指静脉识别的决策级融合方法。该方法不仅对指纹图像进行质量评价，并首次根据指静脉图像特性设计图像采集质量评价指标，以达到克服图像质量对识别结果影响的目的。再针对这两种模态图像特点分别进行分类器设计，得出各自的识别结果后，结合上述得到的图像采集质量评价分数进行决策级融合，将融合后的结果作为最终的识别结果。实验表明，该方法有效克服图像质量对识别结果的影响，提高识别系统的性能，为多生物特征身份识别提供一种有效途径。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王科俊
	马慧
	管凤旭
	李雪峰

关键词 ：多模态生物特征识别, 指纹识别, 静脉识别, 图像质量评价

Abstract：To overcome the influence of the image quality on the single modal recognition system, a fingerprint and finger vein dual-mode recognition method based on image quality evaluation is proposed. The image quality scores of the fingerprint are obtained by the proposed method. And according to its characteristics, the finger vein image quality assessment is designed for the first time to overcome the influence of image quality on identification results. Two classifiers are then designed for fingerprint and finger vein recognition respectively. The final recognition is achieved by the fusion of two quality scores and the recognition results of the classifiers at the decision level. The proposed method overcomes the limitations of image quality on single-modal biometrics, and effectively improves the recognition performance of the system. Thus, the validity of the method for multimodal biometric identification is demonstrated.

Key words： Multibiometric Fingerprint Identification Finger Vein Identification Image Quality Evaluation

收稿日期: 2010-05-24

ZTFLH:

TP391.41

基金资助:国家自然科学基金项目(No.60975022)、国家863计划项目(No.2008AA01Z148)、黑龙江省杰出青年科学基金项目(No.JC200703)资助

作者简介: 王科俊，男，1962年生，教授，博士生导师，主要研究方向为模式识别、模糊混沌神经网络、智能控制等。马慧，女，1982年生，博士，讲师，主要研究方向为模式识别、生物特征识别、图像处理等。E-mail:mahui929@126。com。管凤旭，男，1973年生，博士，副教授，主要研究方向为生物特征识别。李雪峰，男，1984年生，硕士，主要研究方向为图像处理。

引用本文:

王科俊，马慧，管凤旭，李雪峰. 基于图像采集质量评价的指纹与指静脉双模态识别决策级融合方法[J]. 模式识别与人工智能, 2012, 25(4): 669-675. WANG Ke-Jun, MA Hui, GUAN Feng-Xun, LI Xue-Feng. Dual-Modal Decision Fusion for Fingerprint and Finger Vein Recognition Based on Image Capture Quality Evaluation. , 2012, 25(4): 669-675.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/ 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2012/V25/I4/669

[1] Bigun E S,BigunI J,Duc B,et al.Expert Conciliation for Multimodal Person Authentication Systems by Bayesian Statistics // Proc of the 1st International Conference on Audio- and Video-Based Personal Authentication.Crans-Montana,Switzerland,1997: 765-771
[2] Kumar A,Wong D C M,Shen H C,et al.Personal Verification using Palm Print and Hand Geometry Biometric // Proc of the 4th International Conference on Audio-and Video-Based Biometric Person Authentication.Crans-Montana,Switzerland,2003: 668-678
[3] Chen C H,Chu C T.Fusion of Face and Iris Features for Multimodal Biometrics // Proc of the International Conference on Biometric Authentication,Hong Kong,China,2006: 571-580
[4] Jain A K,Ross A.Multibiometric Systems.Communication of the ACM: Special Issue on Multimodal Interfaces,2004,47(l): 34-40
[5] Xu Xiaona,Mu Zhichun.Fusion in Multimodal Recognition Using Ear and Face Profile.Application Research of Computers,2007,24(10): 169-171 (in Chinese)
(徐晓娜,穆志纯.人耳和侧面人脸融合的多模态身份识别.计算机应用研究,2007,24(10): 169-171)
[6] Toh K A.Fingerprint and Speaker Verification Decisions Fusion // Proc of the 12th International Conference on Image Analysis and Processing.Mantova,Italy,2003: 626-631
[7] Liu Hongyi,Wang Yunhong,Tan Tieniu.Multi-Modal Data Fusion for Person Authentication Based on Improved ENN.Acta Automatica Sinica,2004,30(1): 78-85 (in Chinese)
(刘红毅,王蕴红,谭铁牛.基于改进ENN算法的多生物特征融合的身份验证.自动化学报,2004,30(1): 78-85)
[8] Yang Jinfeng,Zhang Xu.Feature-Level Fusion of Fingerprint and Finger-Vein for Personal Identification.Pattern Recognition Letters,2011,33(5): 623-628
[9] Li Xueyan.Study of Multibiometric System Based on Fingerprint and Finger Vein.Ph.D Dissertation.Jilin,China: Jilin University,2008 (in Chinese)
(李雪妍.融合指纹和指静脉的多模态生物识别技术的研究.博士学位论文.吉林:吉林大学,2008)
[10] Park Y H,Tien D N,Lee H C,et al.A Multimodal Biometric Recognition of Touched Fingerprint and Finger-Vein // Proc of the International Conference on Multimedia and Signal Processing.Guilin,China,2011,I: 247-250
[11] Lu Wen,Gao Xinbo,Wang Tisheng.A Natural Image Quality Assessment Metric Based on Wavelet-Based Contourlet Transform.Acta Electronica Sinica,2008,36(2): 303-308 (in Chinese)
(路文,高新波,王体胜.一种基于WBCT的自然图像质量评价方法.电子学报,2008,36(2): 303-308)
[12] Zhao Xianyun,Cai Anni.Fingerprint Image Quality Analysis.Journal of Computer-Aided Design Computer Graphics,2006,18(5): 644-650 (in Chinese)
(赵衍运,蔡安妮.指纹图像质量分析.计算机辅助设计与图形学学报,2006,18(5): 644-650)
[13] Pan Lili,Xie Mei.The Algorithm of Iris Image Quality Evaluation.IEEE Trans on Circuits and Systems for Video Technology,2007,14(2): 616-619
[14] Li Xuefeng.Research of Dual-Mode Recognition Algorithm Based on Fingerprint and Finger Vein.Master Dissertation.Harbin,China: Harbin Engineering University,2009 (in Chinese)
(李雪峰.基于指纹与手指静脉的双模态识别算法研究.硕士学位论文.哈尔滨:哈尔滨工程大学,2009)
[15] Wang Kejun,Ma Hui.Method of Dual-Modal Decision Fusion for Fingerprint and Finger Vein Recognition.Journal of Huazhong University of Science Technology,2011,39(4): 90-93 (in Chinese)
(王科俊,马慧.指纹与指静脉双模态识别决策级融合方法.华中科技大学学报,2011,39(4): 90-93)
[16] Wang Kejun,Yuan Zhi.Finger-Vein Recognition Based on Wavelet Moment Fused with PCA Transform.Pattern Recognition and Artificial Intelligence,2007,20(5): 692-697 (in Chinese)
(王科俊,袁智.基于小波矩融合PCA变换的手指静脉识别.模式识别与人工智能,2007,20(5): 692-697)
[17] Xiong Xinyan.Study of the Multibiometric-Systems Based on Fingerprint and Hand Vein.Ph.D Dissertation.Harbin,China: Harbin Engineering University,2007 (in Chinese)
(熊新炎.基于指纹和手背静脉的多模态生物特征识别系统研究.博士学位论文.哈尔滨:哈尔滨工程大学,2007)
[18] Wang Jiegui,Jing Xueming,Luo Jingqing.Airborne Emitter Recognition Based on Multisensor Data Fusion of ESM and ELINT.Acta Electronica Sinica,2006,34(3): 424-428 (in Chinese)
(王杰贵,靳学明,罗景青.基于ESM与ELINT信息融合的机载辐射源识别.电子学报,2006,34(3): 424-428)