Abstract
Biometric system has been widely adopted for human verification or identification, so inherently it requires the characteristics like high security, accuracy and acceptability. However, most of existing unimodal biometric systems provide low-middle security and are vulnerable to attacks. Therefore, multimodal biometric system fuses information from multiple modalities to break these limitations. This paper presents a novel hybrid fusion model for a multimodal biometric system. The hybrid fusion model includes an improved feature fusion algorithm and a novel weighting vote strategy. It captures canonical characteristics with multi-set structure and utilizes score distribution information to help guiding decision-making. The system was examined on databases from CASIA, PolyU and SDU respectively, which provided high precision and strong robustness over previous work. Experimental results showed that the proposed approach achieved an average accuracy of 99.33%, which outperformed other fusion strategies in multimodal biometric systems.
Similar content being viewed by others
References
Ahmad MI, Woo WL, Dlay S (2016) Non-stationary feature fusion of face and palmprint multimodal biometrics. Neurocomputing 177:49–61
Ahonen T, Hadid A, Pietikäinen M (2006) Face recognition with local binary patterns. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041
Al-Maadeed S, Bourif M, Bouridane A, Jiang R (2016) Low-quality facial biometric verification via dictionary-based random pooling. Pattern Recogn 52:238–248
Al-Tayyan A, Assaleh K, Shanableh T (2017) Decision-level fusion for single-view gait recognition with various carrying and clothing conditions. Image Vis Comput 61:54–69
Al-Waisy AS, Qahwaji R, Ipson S, Al-Fahdawi S, Nagem TAM (2017) A multi-biometric iris recognition system based on a deep learning approach. Pattern Anal Applic 21(4):1–20
Bo S, Li L, Xuewen W, Zuo T, Chen Y, Zhou G, He J, Zhu X (2016) Combining feature-level and decision-level fusion in a hierarchical classifier for emotion recognition in the wild. J Multimodal User Interfaces 10(2):125–137
Chen Z, You X, Zhong B, Li J, Tao D (2017) Dynamically modulated mask sparse tracking. IEEE Transactions on Cybernetics 47(11):3706–3718
Cui F, Yang G (2011) Score level fusion of fingerprint and finger vein recognition. Journal of Computational Information Systems 7:5723–5731
Dass SC, Nandakumar K, Jain AK (2005) A principled approach to score level fusion in multimodal biometric systems. In: Audio- and video-based biometric person authentication, 5th international conference, AVBPA 2005, hilton rye town, NY, USA, July 20-22, 2005, Proceedings
Gao Y, Ma J, Yuille AL (2017) Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples. IEEE Trans Image Process 26(5):2545–2560
Gopal, Smriti S (2017) Accurate human recognition by score-level and feature-level fusion using palm cphalanges print. Arab J Sci Eng 43(6):1–12
Gopal, Smriti S, Saurabh B, Sandeep B (2016) Fusion of palm-phalanges print with palmprint and dorsal hand vein. Applied Soft Computing, pp. S1568494616302496
Grover J, Hanmandlu M (2015) Hybrid fusion of score level and adaptive fuzzy decision level fusions for the finger-knuckle-print based authentication. Appl Soft Comput 31(C):1–13
Guan X, Liu G, Huang C, Liu Q, Wu C, Jin Y, Li Y (2017) An object-based linear weight assignment fusion scheme to improve classification accuracy using landsat and modis data at the decision level. IEEE Trans Geosci Remote Sens 55(12):6989–7002
Haghighat M, Abdel-Mottaleb M, Alhalabi W (2016) Discriminant correlation analysis: Real-time feature level fusion for multimodal biometric recognition. IEEE Trans Inf Foren Sec 11(9):1984–1996
Jeng R, Chen W (2016) Two feature-level fusion methods with feature scaling and hashing for multimodal biometrics. IETE Tech Rev 34(1):11
Jing X, Yao Y, Zhang D, Yang J, Li M (2007) Face and palmprint pixel level fusion and kernel dcv-rbf classifier for small sample biometric recognition. Pattern Recogn 40(11):3209–3224
Kabir W, Omair AM, Swamy MNS (2018) Normalization and weighting techniques based on genuine-impostor score fusion in multi-biometric systems. IEEE Trans Inf Foren Sec 13(8):1989–2000
Khaled R, Hamza R, Hongyang Y (2019) Sensitive and energetic iot access control for managing cloud electronic health records. IEEE Acess 7:86384–86393
Khellat-Kihel S, Abrishambaf R, Monteiro JL, Benyettou M (2016) Multimodal fusion of the finger vein, fingerprint and the finger-knuckle-print using kernel fisher analysis. Appl Soft Comput 42(C):439–447
Kittler J, Alkoot FM (2003) Sum versus vote fusion in multiple classifier systems. IEEE Trans Pattern Anal Mach Intell 25(1):110–115
Kumar A, Shekhar S (2011) Personal identification using multibiometrics rank-level fusion. IEEE Trans Syst Man Cy Part C 41(5):743–752
Kun S, Yang G, Bo W, Yang L, Li D, Peng S, Yin Y (2019) Human identification using finger vein and ecg signals. Neurocomputing 332:111–118
Lin H, Jain A (1998) Integrating faces and fingerprints for personal identification. IEEE Trans Pattern Anal Mach Intell 20(12):1295–1307
Modak S, Jha V (2018) Multibiometric fusion strategy and its applications: a review. Information Fusion 49:174–204
Ojala T, Pietikäinen M, Mäenpää T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987
Perlibakas V (2004) Distance measures for pca-based face recognition. Pattern Recogn Lett 25(6):711–724
Pinar AJ, Rice J, Hu L, Anderson DT, Havens TC (2017) Efficient multiple kernel classification using feature and decision level fusion. IEEE Trans Fuzzy Syst 25(6):1403–1416
Qiu J, Li H, Zhao C (2019) Cancelable palmprint templates based on random measurement and noise data for security and privacy-preserving authentication. Computer and Security 82:1–14
Hamza R, Yan Z, Muhammad K, Bellavista P, Titouna F (2019) A privacy-preserving cryptosystem for iot e-healthcare. Information Sciences
Regouid M, Touahria M, Benouis M (2019) Multimodal biometric system for ecg, ear and iris recognition based on local descriptors. Multimed Tools Appl 78(16):22509–22535
Ribaric S, Fratric I (2005) A biometric identification system based on eigenpalm and eigenfinger features. IEEE Trans Pattern Anal Mach Intell 27(11):1698–1709
Singh WG, Tarandeep S, Kuldeep S, Neelam V (2019) Robust multimodal biometric system based on optimal score level fusion model. Expert Syst Appl 116:364–376
Sinha A, Chen H, Danu DG, Kirubarajan T, Farooq M (2008) Estimation and decision fusion: a survey. Neurocomputing 71(13):2650–2656
Snelick R, Uludag U, Mink A, Indovina M, Jain AK (2005) Large-scale evaluation of multimodal biometric authentication using state-of-the-art systems. IEEE Trans Pattern Anal Mach Intell 27(3):450–455
Sun Q, Shenggen Z, Yan L, Heng PA, Deshen X (2005) A new method of feature fusion and its application in image recognition. Pattern Recogn 38(12):2437–2448
Tao Qian, Veldhuis Raymond (2009) Threshold-optimized decision-level fusion and its application to biometrics. Pattern Recogn 42(5):823–836
The finger vein database from shandong university (sdumla). http://mla.sdu.edu.cn/info/1006/1195.htm
The iris database. http://biometrics.idealtest.org/findTotalDbByMode.do?mode=Iris
The palm vein database. https://www4.comp.polyu.edu.hk/biometrics/
Toygar Ö, Alqaralleh E, Afaneh A (2018) Symmetric ear and profile face fusion for identical twins and non-twins recognition. Signal Image and Video Processing 12(6):1157–1164
Wild P, Radu P, Chen L, Ferryman J (2015) Robust multimodal face and fingerprint fusion in the presence of spoofing attacks. Pattern Recogn 50:17–25
Yan X, Kang W, Deng F, Qiuxia W (2015) Palm vein recognition based on multi-sampling and feature-level fusion. Neurocomputing 151:798–807
Yang G, Xi X, Yin Y (2012) Finger vein recognition based on a personalized best bit map. Sensors 12(2):1738–1757
Yang J, Luo L, Qian J, Tai Y, Zhang F, Xu Y (2016) Nuclear norm based matrix regression with applications to face recognition with occlusion and illumination changes. IEEE Trans Pattern Anal Mach Intell 39(1):156–171
Yang J, Sun Q (2017) A novel generalized fuzzy canonical correlation analysis framework for feature fusion and recognition. Neural Process Lett 46 (2):521–536
Yang J, Yang J (2002) Generalized k cl transform based combined feature extraction. Pattern Recogn 35(1):295–297
Yang J, Yang J, Zhang D, Lu J (2003) Feature fusion: parallel strategy vs. serial strategy. Pattern Recogn 36(6):1369–1381
Yang Lu, Yang G, Yin Y, Xi X (2018) Finger vein recognition with anatomy structure analysis. IEEE Transactions on Circuits and Systems for Video Technology 28(8):1892–1905
Yang W, Song W, Jiankun Hu, Zheng G, Valli C (2017) A fingerprint and finger-vein based cancelable multi-biometric system. Pattern Recogn 78:242–251
Yang X, Kong L, Zhi L, Wang C, Xiaoke X (2018) Multimodal feature-level fusion for biometrics identification system on iomt platform. IEEE Access 6:21418–21426
Yao Y, Jing X, Wong H (2007) Face and palmprint feature level fusion for single sample biometrics recognition
You X, Guo W, Yu S, Li K, Príncipe JC, Tao D (2016) Kernel learning for dynamic texture synthesis. IEEE Trans Image Process 25 (10):4782–4795
You X, Wang R, Tao D (2014) Diverse expected gradient active learning for relative attributes. IEEE Trans Image Process 23(7):3203–3217
You X, Weihua O, Chen CLP, Li Q, Zhu Z, Tang Y (2015) Robust nonnegative patch alignment for dimensionality reduction. IEEE Trans Neur Net Lear Syst 26(11):2760–2774
Yue Z, You X, Yu S, Chang X, Tao D (2018) Multi-view manifold learning with locality alignment. Pattern Recogn 78:154–166
Zifeng W, Huang Y, Wang L, Wang X, Tan T (2016) A comprehensive study on cross-view gait based human identification with deep cnns. IEEE Trans Pattern Anal Mach Intell 39(2):209–226
Acknowledgments
The authors would like to thank Prof. M. Haghighat for providing his source code to implement [15]. We would also want to express thanks to Chinese Academy of Sciences for sharing CASIA-IrisV4 Database [39], Hong Kong Poly University for sharing their database [40] and Shandong University for sharing SDUMLA-HMT Database [44]. This study is partially financed by the National Natural Science Foundation of China (NSFC: 61771233 and 81000642), Science and Technology Planning Project of Guangdong Province, China (Grant no. 2013B090500104).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhou, C., Huang, J., Yang, F. et al. A hybrid fusion model of iris, palm vein and finger vein for multi-biometric recognition system. Multimed Tools Appl 79, 29021–29042 (2020). https://doi.org/10.1007/s11042-020-08914-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08914-6