基于图像质量加权的D-S证据理论多生物特征融合识别

doi:10.3724/SP.J.1087.2012.00264

计算机应用 ›› 2012, Vol. 32 ›› Issue (01): 264-268.DOI: 10.3724/SP.J.1087.2012.00264

基于图像质量加权的D-S证据理论多生物特征融合识别

肖宾杰¹,²

1. 上海市城市建设设计研究总院电气自动化分院，上海 200125
2. 同济大学电子与信息工程学院，上海 200092

收稿日期:2011-06-13 修回日期:2011-08-08 发布日期:2012-02-06 出版日期:2012-01-01
通讯作者: 肖宾杰
作者简介:肖宾杰(1979-),男,河南洛阳人，工程师，博士研究生，CCF会员，主要研究方向：图像处理、模式识别、图像融合。

Multi-biometric feature fusion identification based on D-S evident theory of image quality with different weights

XIAO Bin-jie¹,²

1. College of Electronics and Information Engineering, Tongji University, Shanghai 200092, China
2. Electricity Automation Department, Shanghai Urban Construction Design and Research Institute, Shanghai 200125, China

Received:2011-06-13 Revised:2011-08-08 Online:2012-02-06 Published:2012-01-01
Contact: XIAO Bin-jie

摘要/Abstract

摘要： 对人脸和指静脉在决策层的融合识别，给出一种新的组合图像质量评价方法，并采用一种改进的基于图像质量加权的D-S证据理论融合这两种生物特征。首先，组合图像质量评价法采用清晰度和对比度、相关系数的组合方法来评价生物特征图像质量；其次，应用改进的基于图像质量的匹配值增强方法和D-S证据理论，减少了极大值图像质量指标的影响，使图像质量加权与实际情况更趋一致。实验结果表明，与没有考虑图像质量因素相比，考虑了图像质量信息的D-S证据理论融合方法提高了识别效果。

关键词: 人脸, 指静脉, 独立成分分析, 主元分析, 图像质量, D-S证据理论

Abstract: For the fusing recognition with face and finger-vein at decision level, a new quality score of image by combining three indexes was presented, and an improved fusion strategy based on D-S evident theory was adopted to fuse two biometric characteristics. At first, the quality score of image was computed by combining index of distinct, contrast and coefficient. Then an improved method based on image quality and D-S evident theory was adopted. This improved method reduced the impact of maximum of image quality score and made the weighted parameter with the actual situation more consistent. Compared with the result of D-S evident theory with no regard to image quality, the results reveal that the fusion method in this paper based on D-S evident theory taking account of image quality information improves the performance.

Key words: human face, finger-vein, Independent Component Analysis (ICA), Principal Component Analysis (PCA), image quality, D-S evident theory

中图分类号:

TP391.413

肖宾杰. 基于图像质量加权的D-S证据理论多生物特征融合识别[J]. 计算机应用, 2012, 32(01): 264-268.

XIAO Bin-jie. Multi-biometric feature fusion identification based on D-S evident theory of image quality with different weights[J]. Journal of Computer Applications, 2012, 32(01): 264-268.

参考文献

[1]

ROSS A, JAIN A K, QIAN J Z. Information fusion in biometries ［J］. Pattern Recognition Letters, 2003, 24(13): 2115-2125.

[2]

HONG L, JAIN A, PANKANTI S. Can multibiometrics improve performance? ［C］// Proceedings of 1999 IEEE Workshop on Automatic Identification Advanced Technologies. Piscataway: IEEE, 1999: 59-64.

[3]

JAIN A K, PANKANTI S, PRABHAKAR S, et al. Biometrics: A grand challenge ［C］// Proceedings of the 17th International Conference on Pattern Recognition. Washington, DC: IEEE Computer Society, 2004: 935-942.

[4]

NANDAKUMAR K, CHEN Y, Jain A K, et al. Quality-based score level fusion in multibiometric systems ［C］// Proceedings of the 18th International Conference on Pattern Recognition. Washington, DC: IEEE Computer Society, 2006, (4): 473-476.

[5]

MAURER D E, BAKER J P. Fusing multimodal biometrics with quality estimates via a Bayesian belief network ［J］. Pattern Recognition, 2008, 41(3): 821-832.

[6]

VATSA M, SINGH R, NOORE A, et al. Quality-augmented fusion of level-2 and level-3 fingerprint information using DSM theory ［J］. International Journal of Approximate Reasoning, 2009, 50(1): 51-61.

[7]

FIERREZ-AGUILAR J, CHEN Y, ORTEGA-GARCIA J, et al. Incorporating image quality in multi-algorithm fingerprint verification ［C］// Proceedings of the International Conference on Biometrics. Berlin: Springer-Verlag, 2006: 213-220.

[8]

RICHIARDI J, KRYSZCZUK K, DRYGAJLO A. Quality measures in unimodal and multimodal biometric verification ［C］// Proceedings of the 15th European Conference on Signal Processing. Poznan, Poland: EURASIP, 2007: 301-310.

[9]

SINGH R, VATSA M, NOORE A, et al. DS theory classifier fusion with update rule to minimize training time ［J］. IEICE Electronics Express, 2006, 3(20): 429-435.

[10]

FIERREZ-AGUILAR J, ORTEGA-GARCIA J, GONZALEZ-RO-DRIGUEZ J, et al. Discriminative multimodal biometric authentication based on quality measures ［J］. Pattern Recognition, 2005, 38 (5): 777-779.

[11]

AT&T Laboratories Cambridge. The ORL database of faces ［EB/OL］. ［2011-03-25］. http://www.cam-orl.co.uk/facedatabase.html.

[12]

余成波，秦华锋.手指静脉识别技术［M］.北京：清华大学出版社，2009.

[13]

MIURA N, NAGASAKA A, MIYATAKE T. Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification ［J］. Machine Vision and Applications, 2004, 15(4): 194-203.

[14]

WAN LINGYU, LEEDHAM G, CHO D S-Y, et al. Minutiae feature analysis for infrared hand vein pattern biometrics ［J］. Pattern Recognition, 2008, 41(3): 920-929.

[15]

WAN LINGYU, LEEDHAM G. A thermal hand vein pattern verification system ［C］// Proceedings of the Third International Conference on Advances in Pattern Recognition and Image Analysis. Berlin: Springer-Verlag, 2005: 58-65.

[16]

YANG JINFENG, SHI YIHUA, YANG JINLI. Personal identification based on finger-vein features ［J］. Computers in Human Behavior, 2011, 27(5): 1565-1570.

[17]

BARTLETT M S, MOVELLAN J R, SEJNOWSKI T J. Face recognition by independent component analysis ［J］. IEEE Transactions on Neural Network, 2002, 13(6): 1450-1464.

[18]

DENIZ O, CASTRILLON M, HERNANDEZ M, et al. Face recognition using independent component analysis and support vector machines ［J］. Pattern Recognition Letters, 2003, 24(13): 2153-2157.

[19]

HURRI J. FastICA ［EB/OL］. ［2011-04-19］. http://www.cis.hut.fi/projects/ica/fastica.

[20]

TURK M, PENTLAND A. Eigenfaces for recognition ［J］. Journal of Cognitive Neuroscience, 1991, 3(1): 71-86.

[21]

李奇,冯华君,徐之海,等.数字图象清晰度评价函数研究［J］.光子学报,2002,31(6):736-738.

[22]

王鸿南,钟文,汪静,等.图像清晰度评价方法研究［J］.中国图象图形学报,2004,9(7):828-892.

[23]

WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity ［J］. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

[24]

PARIKH C R, PONT M J, JONES N B. Application of Dempster-Shafer theory in condition monitoring systems: A case study ［J］. Pattern Recognition Letters, 2001, 22 (6/7): 777-785.

[25]

DEZERT J. Foundations for a new theory of a plausible and paradoxical reasoning ［J］. Information and Security Journal, 2002, 12(1): 13-57.

基于图像质量加权的D-S证据理论多生物特征融合识别

Multi-biometric feature fusion identification based on D-S evident theory of image quality with different weights

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	高工, 杨红雨, 刘洪. 基于深度学习的三维点云人脸识别[J]. 计算机应用, 2021, 41(9): 2736-2740.
[2]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[3]	戴嫣然, 戴国庆, 袁玉波. 基于肤色学习的多人脸前景抽取方法[J]. 计算机应用, 2021, 41(6): 1659-1666.
[4]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[5]	赵津, 宋文爱, 邰隽, 杨吉江, 王青, 李晓丹, 雷毅, 邱悦. 儿童阻塞性睡眠呼吸暂停计算机人脸辅助诊断综述[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3394-3401.
[6]	赵青, 余元辉. 基于分层特征化网络的三维人脸识别[J]. 计算机应用, 2020, 40(9): 2514-2518.
[7]	方书雅, 刘守印. 基于学生人体检测的无感知课堂考勤方法[J]. 计算机应用, 2020, 40(9): 2519-2524.
[8]	王思宇, 高炜欣, 李璐. 环口焊X射线焊缝图像质量评定模型[J]. 计算机应用, 2020, 40(9): 2748-2753.
[9]	陈佛计, 朱枫, 吴清潇, 郝颖明, 王恩德. 基于生成对抗网络的红外图像数据增强[J]. 计算机应用, 2020, 40(7): 2084-2088.
[10]	邓茜文, 冯子亮, 邱晨鹏. 基于近红外与可见光双目视觉的活体人脸检测方法[J]. 计算机应用, 2020, 40(7): 2096-2103.
[11]	邓雄, 王洪春. 基于深度学习和特征融合的人脸活体检测算法[J]. 计算机应用, 2020, 40(4): 1009-1015.
[12]	任海培, 李腾. 面向移动平台人脸检测的FaceYoLo算法[J]. 计算机应用, 2020, 40(4): 1002-1008.
[13]	张俊升, 徐晶晶, 余伟. 面部美化图像质量无参考评价方法[J]. 计算机应用, 2020, 40(4): 1184-1190.
[14]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[15]	龚锐, 丁胜, 章超华, 苏浩. 基于深度学习的轻量级和多姿态人脸识别方法[J]. 计算机应用, 2020, 40(3): 704-709.