Finger-Vein Quality Assessment by Representation Learning from Binary Images

Finger-vein quality assessment is an important issue in finger-vein verification systems as spurious and missing features in poor quality images may increase the verification error. Despite recent advances, current solutions depend on domain knowledge and are typically driven by visual inspection. In this work, we propose a deep Neural Network (DNN) for representation learning from binary images to predict vein quality. First, driven by the primary target of biometric quality assessment, i.e. verification error minimization, we assume that low quality images are false rejected finger-vein images in a verification system. Based on this assumption, the low and high quality images are labeled automatically. Second, as image processing approaches such as enhancement and segmentation may produce false features and ignore actual ones thus degrading verification accuracy, we train a DNN on binary images and derive deep features from its last hidden layer for quality assessment. Our experiments on two large public finger-vein databases show that the proposed scheme accurately identifies high and low quality images and significantly outperform existing approaches in terms of the impact on equal error rate (EER) improvement.

[1]  Ajay Kumar,et al.  Human Identification Using Finger Images , 2012, IEEE Transactions on Image Processing.

[2]  Alex ChiChung Kot,et al.  Quality assessment of finger-vein image , 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

[3]  Xiaogang Wang,et al.  Deep Learning Face Representation from Predicting 10,000 Classes , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Julian Fiérrez,et al.  A Comparative Study of Fingerprint Image-Quality Estimation Methods , 2007, IEEE Transactions on Information Forensics and Security.

[5]  Tien Dat Nguyen,et al.  New Finger-vein Recognition Method Based on Image Quality Assessment , 2013, KSII Trans. Internet Inf. Syst..

[6]  Shahrel Azmin Suandi,et al.  Fusion of Band Limited Phase Only Correlation and Width Centroid Contour Distance for finger based biometrics , 2014, Expert Syst. Appl..

[7]  Gongping Yang,et al.  Finger vein image quality evaluation using support vector machines , 2013 .

[8]  Yu Deng,et al.  Face Image Quality Assessment Based on Learning to Rank , 2015, IEEE Signal Processing Letters.

[9]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Sharath Pankanti,et al.  Biometrics: a tool for information security , 2006, IEEE Transactions on Information Forensics and Security.

[12]  Hugo Proença,et al.  Quality Assessment of Degraded Iris Images Acquired in the Visible Wavelength , 2011, IEEE Transactions on Information Forensics and Security.

[13]  Elham Tabassi,et al.  Performance of Biometric Quality Measures , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Xiamu Niu,et al.  A Novel Finger Vein Image Quality Evaluation Method Based on Triangular Norm , 2014, 2014 Tenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.