Deep expectation for estimation of fingerprint orientation fields

Estimation of the orientation field is one of the key challenges during biometric feature extraction from a fingerprint sample. Many important processing steps rely on an accurate and reliable estimation. This is especially challenging for samples of low quality, for which in turn accurate preprocessing is essential. Regressional Convolutional Neural Networks have shown their superiority for bad quality samples in the independent benchmark framework FVC-ongoing. This work proposes to incorporate Deep Expectation. Options for further improvements are evaluated in this challenging environment of low quality images and small amount of training data. The findings from the results improve the new algorithm called DEX-OF. Incorporating Deep Expectation, improved regularization, and slight model changes DEX-OF achieves an RMSE of 7.52° on the bad quality dataset and 4.89° at the good quality dataset at FVC-ongoing. These are the best reported error rates so far.

[1]  Anil K. Jain,et al.  Adaptive flow orientation-based feature extraction in fingerprint images , 1995, Pattern Recognit..

[2]  Bernadette Dorizzi,et al.  Fingerprint and On-Line Signature Verification Competitions at ICB 2009 , 2009, ICB.

[3]  Christoph Busch,et al.  ConvNet Regression for Fingerprint Orientations , 2017, SCIA.

[4]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[5]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[6]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

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

[8]  Andrew G. Howard,et al.  Some Improvements on Deep Convolutional Neural Network Based Image Classification , 2013, ICLR.

[9]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[10]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[11]  Anil K. Jain,et al.  Latent orientation field estimation via convolutional neural network , 2015, 2015 International Conference on Biometrics (ICB).

[12]  Dario Maio,et al.  Improving Fingerprint Orientation Extraction , 2011, IEEE Transactions on Information Forensics and Security.

[13]  Jie Tian,et al.  A div-curl regularization model for fingerprint orientation extraction , 2012, 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[14]  Jiankun Hu,et al.  A Fingerprint Orientation Model Based on 2D Fourier Expansion (FOMFE) and Its Application to Singular-Point Detection and Fingerprint Indexing , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Luc Van Gool,et al.  Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks , 2016, International Journal of Computer Vision.

[16]  Jie Zhou,et al.  Localized Dictionaries Based Orientation Field Estimation for Latent Fingerprints. , 2014, IEEE transactions on pattern analysis and machine intelligence.

[17]  Anoop M. Namboodiri,et al.  Learning Fingerprint Orientation Fields Using Continuous Restricted Boltzmann Machines , 2013, 2013 2nd IAPR Asian Conference on Pattern Recognition.

[18]  Jianping Yin,et al.  Fingerprint ridge orientation estimation based on neural network , 2006 .

[19]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).