Abstract
Recently, as one of the most promising biometric traits, the vein has attracted the attention of both academia and industry because of its living body identification and the convenience of the acquisition process. State-of-the-art techniques can provide relatively good performance, yet they are limited to specific light sources. Besides, it still has poor adaptability to multispectral images. Despite the great success achieved by convolutional neural networks (CNNs) in various image understanding tasks, they often require large training samples and high computation that are infeasible for palm-vein identification. To address this limitation, this work proposes a palm-vein identification system based on lightweight CNN and adaptive multi-spectral method with explainable AI. The principal component analysis on symmetric discrete wavelet transform (SMDWT-PCA) technique for vein images augmentation method is adopted to solve the problem of insufficient data and multispectral adaptability. The depth separable convolution (DSC) has been applied to reduce the number of model parameters in this work. To ensure that the experimental result demonstrates accurately and robustly, a multispectral palm image of the public dataset (CASIA) is also used to assess the performance of the proposed method. As result, the palm-vein identification system can provide superior performance to that of the former related approaches for different spectrums.
- [1] 2014. Sample space dimensionality refinement for symmetrical object detection. IEEE Transactions on Information Forensics and Security 9, 11 (2014), 1953–1961. Google Scholar
Digital Library
- [2] . 2018. Robust rgb-d hand tracking using deep learning priors. IEEE Transactions on Circuits and Systems for Video Technology 28, 9 (2018), 2289–2301.Google Scholar
Cross Ref
- [3] . 2012. Contact-free hand geometry-based identification system. Expert Systems with Applications 39, 14 (2012), 11728–11736. Google Scholar
Digital Library
- [4] . 2011. Improved iris recognition through fusion of hamming distance and fragile bit distance. IEEE Transactions on Pattern Analysis and Machine Intelligence 33, 12 (2011), 2465–2476. Google Scholar
Digital Library
- [5] . 2003. Learning fingerprint minutiae location and type. Pattern Recognition 36, 8 (2003), 1847–1857.Google Scholar
Cross Ref
- [6] . 2009. Phase congruency features for palm-print verification. IET Signal Processing 3, 4 (2009), 258–268.Google Scholar
Cross Ref
- [7] . 2012. Human action recognition and retrieval using sole depth information. In 2012 ACM 20th International Conference on Multimedia. ACM, 1053–1056. Google Scholar
Digital Library
- [8] . 2020. AU-assisted graph attention convolutional network for micro-expression recognition. In 2020 ACM 28th International Conference on Multimedia. ACM, 2871–2880. Google Scholar
Digital Library
- [9] . 2017. New verification strategy for finger-vein recognition system. IEEE Sensors Journal 18, 2 (2017), 790–797.Google Scholar
Cross Ref
- [10] . 2018. Robust authentication using dorsal hand vein images. IEEE Intelligent Systems 34, 2 (2018), 25–35. Google Scholar
Digital Library
- [11] . 2019. Low-cost biometric recognition system based on nir palm vein image. IET Biometrics 8, 3 (2019), 206–214.Google Scholar
Cross Ref
- [12] . 2018. Deepmasterprints: Generating masterprints for dictionary attacks via latent variable evolution. In 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS). IEEE, 1–9.Google Scholar
Cross Ref
- [13] . 2015. Detection of face spoofing using visual dynamics. IEEE Transactions on Information Forensics and Security 10, 4 (2015), 762–777.Google Scholar
Digital Library
- [14] . 2015. Deep representations for iris, face, and fingerprint spoofing detection. IEEE Transactions on Information Forensics and Security 10, 4 (2015), 864–879.Google Scholar
Digital Library
- [15] . 2017. Spoof detection on face and palmprint biometrics. Signal, Image and Video Processing 11, 7 (2017), 1253–1260.Google Scholar
Cross Ref
- [16] . 2009. Driver identification using finger-vein patterns with radon transform and neural network. Expert Systems with Applications 36, 3 (2009), 5793–5799. Google Scholar
Digital Library
- [17] . 2017. Research on multi-spectral adaptive method for palm vein capturing based on image quality. In 2017 32nd Youth Academic Annual Conference of Chinese Association of Automation (YAC). IEEE, 1154–1157.Google Scholar
Cross Ref
- [18] . 2011. Human identification using palm-vein images. IEEE Transactions on Information Forensics and Security 6, 4 (2011), 1259–1274. Google Scholar
Digital Library
- [19] . 2014. Contactless palm vein recognition using a mutual foreground-based local binary pattern. IEEE Transactions on Information Forensics and Security 9, 11 (2014), 1974–1985. Google Scholar
Digital Library
- [20] . 2018. Palm vein recognition using a high dynamic range approach. IET Biometrics 7, 5 (2018), 439–446.Google Scholar
Cross Ref
- [21] . 2020. An Automated biometric identification system using cnn-based palm vein recognition. In 2020 IEEE 8th International Conference on Advanced Robotics and Intelligent Systems (ARIS). IEEE, 1–6.Google Scholar
Cross Ref
- [22] . 2011. Human identification using finger images. IEEE Transactions on Image Processing 21, 4 (2011), 2228–2244. Google Scholar
Digital Library
- [23] . 2019. Finger-vein recognition based on deep densenet using composite image. IEEE Access 7 (2019), 66845–66863.Google Scholar
Cross Ref
- [24] . 2017. Finger vein identification using convolutional neural network and supervised discrete hashing. In Deep Learning for Biometrics. Springer, 109–132.Google Scholar
Cross Ref
- [25] . 2018. Spatial pyramid pooling of selective convolutional features for vein recognition. IEEE Access 6 (2018), 28563–28572.Google Scholar
Cross Ref
- [26] . 2010. Capturing hand or wrist vein images for biometric authentication using low-cost devices. In 2010 6th International Conference on Intelligent Information Hiding and Multimedia Signal Processing. IEEE, 318–322. Google Scholar
Digital Library
- [27] . 2020. FYO: A novel multimodal vein database with palmar, dorsal and wrist biometrics. IEEE Access 8 (2020), 82461–82470.Google Scholar
Cross Ref
- [28] . 2012. Matching vein patterns from color images for forensic investigation. In 2012 IEEE 5th International Conference on Biometrics: Theory, Applications and Systems (BTAS). IEEE, 77–84.Google Scholar
Cross Ref
- [29] . 2004. Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification. Machine Vision and Applications 15, 4 (2004), 194–203. Google Scholar
Digital Library
- [30] . 2014. Palm vein recognition with local texture patterns. IET Biometrics 3, 4 (2014), 198–206.Google Scholar
Cross Ref
- [31] . 2007. Vein pattern recognitions by moment invariants. In 2007 1st International Conference on Bioinformatics and Biomedical Engineering. IEEE, 612–615.Google Scholar
Cross Ref
- [32] . 2014. Contact-free palm-vein recognition based on local invariant features. PloS One 9, 5 (2014), e97548.Google Scholar
Cross Ref
- [33] . 2017. Sift based vein recognition models: Analysis and improvement. Computational and Mathematical Methods in Medicine 17 (2017), 1–14.Google Scholar
- [34] 2016. Finger-vein biometric identification using convolutional neural network. Turkish Journal of Electrical Engineering & Computer Sciences 24, 3 (2016), 1863–1878.Google Scholar
Cross Ref
- [35] 2003. Best practices for convolutional neural networks applied to visual document analysis. In Icdar 3, 2003. Google Scholar
Digital Library
- [36] . 2017. Convolutional neural network-based finger-vein recognition using nir image sensors. Sensors 17, 6 (2017), 1297.Google Scholar
Cross Ref
- [37] . 2015. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR). 77–84.Google Scholar
- [38] 2018. Convolutional neural network for finger-vein- vein-based biometric identification. IEEE Transactions on Information Forensics and Security 14, 2 (2018), 360–373.Google Scholar
- [39] . 2017. Imagenet classification with deep convolutional neural networks. Communications of the ACM 60, 6 (2017), 84–90. Google Scholar
Digital Library
- [40] . 2018. A novel finger vein verification system based on two-stream convolutional network learning. Neurocomputing 290, 17 (2018), 100–107.Google Scholar
- [41] . 2019. Understanding the disharmony between dropout and batch normalization by variance shift. In 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2677–2685.Google Scholar
Cross Ref
- [42] . 2016. Why should I trust you?" explaining the predictions of any classifier. In 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1135–1144. Google Scholar
Digital Library
- [43] . Retrieved from http://biometrics.idealtest.org/.Google Scholar
- [44] . 2019. AutoAugment: learning augmentation strategies from data. 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 113–123.Google Scholar
Cross Ref
- [45] . 2020. Randaugment: Practical automated data augmentation with a reduced search space. 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 3008–3017.Google Scholar
Cross Ref
- [46] . 2018. Single-sensor hand-vein multimodal biometric recognition using multiscale deep pyramidal approach. Machine Vision and Applications 18, 7 (2018), 1269–1286. Google Scholar
Digital Library
- [47] . 2019. Pvsnet: Palm-vein authentication Siamese network trained using triplet loss and adaptive hard mining by learning enforced domain specific features. In 2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA). IEEE, 1–8.Google Scholar
Cross Ref
Index Terms
Explainable AI: A Multispectral Palm-Vein Identification System with New Augmentation Features
Recommendations
A secure palm vein recognition system
With the increasing needs in security systems, vein recognition is one of the important and reliable solutions of identity security for biometrics-based identification systems. The obvious and stable line-feature-based approach can be used to clearly ...
Applications of Different CNN Architectures for Palm Vein Identification
Modeling Decisions for Artificial IntelligenceAbstractIn this paper a palm vein identification system is presented, which exploits the strength of convolutional neural network (CNN) architectures. We built and compared six different CNN approaches for biometric identification based on palm images. ...
Biometric recognition using finger and palm vein images
In recent times, biometrics is the best alternative for the token-based and knowledge-based security systems. Out of the existing biometric modalities, the vascular biometric modalities are preferred for authenticating the person, because of its ...






Comments