Cycle-consistent generative adversarial neural networks based low quality fingerprint enhancement

Distortions such as dryness, wetness, blurriness, physical damages and presence of dots in fingerprints are a detriment to a good analysis of them. Even though fingerprint image enhancement is possible through physical solutions such as removing excess grace on the fingerprint or recapturing the fingerprint after some time, these solutions are usually not user-friendly and time consuming. In some cases, the enhancements may not be possible if the cause of the distortion is permanent. In this paper, we are proposing an unpaired image-to-image translation using cycle-consistent adversarial networks for translating images from distorted domain to undistorted domain, namely, dry to not-dry, wet to not-wet, dotted to not-dotted, damaged to not-damaged, blurred to not-blurred. We use a database of low quality fingerprint images containing 11541 samples with dryness, wetness, blurriness, damages and dotted distortions. The database has been prepared by real data from VISA application centres and have been provided for this research by GEYCE Biometrics. For the evaluation of the proposed enhancement technique, we use VGG16 based convolutional neural network to assess the percentage of enhanced fingerprint images which are labelled correctly as undistorted. The proposed quality enhancement technique has achieved the maximum quality improvement for wetness fingerprints in which 94% of the enhanced wet fingerprints were detected as undistorted.

[1]  Sergio Escalera,et al.  Convolutional Neural Network Super Resolution for Face Recognition in Surveillance Monitoring , 2016, AMDO.

[2]  Davide Maltoni,et al.  Minutia Cylinder-Code: A New Representation and Matching Technique for Fingerprint Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[4]  A. J. Willis,et al.  A cost-effective fingerprint recognition system for use with low-quality prints and damaged fingertips , 2001, Pattern Recognit..

[5]  Hiroshi Nakajima,et al.  A fingerprint recognition algorithm using phase-based image matching for low-quality fingerprints , 2005, IEEE International Conference on Image Processing 2005.

[6]  Sergio Escalera,et al.  Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification , 2018, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

[7]  Massimo Tistarelli,et al.  MCC: A baseline algorithm for fingerprint verification in FVC-onGoing , 2010, 2010 11th International Conference on Control Automation Robotics & Vision.

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  Gholamreza Anbarjafari,et al.  Real-time ensemble based face recognition system for NAO humanoids using local binary pattern , 2017, Analog Integrated Circuits and Signal Processing.

[10]  Nalini K. Ratha,et al.  Automatic Fingerprint Recognition Systems , 2011, Springer New York.

[11]  Xin Yang,et al.  Define a fingerprint Orientation Field pattern , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[12]  HerreraFrancisco,et al.  A survey on fingerprint minutiae-based local matching for verification and identification , 2015 .

[13]  Jufu Feng,et al.  Deep Dense Multi-level feature for partial high-resolution fingerprint matching , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[14]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[15]  Gholamreza Anbarjafari,et al.  Data Fusion Boosted Face Recognition Based on Probability Distribution Functions in Different Colour Channels , 2009, EURASIP J. Adv. Signal Process..

[16]  Qiang Ji,et al.  Video Analytics. Face and Facial Expression Recognition and Audience Measurement - Third International Workshop, VAAM 2016, and Second International Workshop, FFER 2016, Cancun, Mexico, December 4, 2016, Revised Selected Papers , 2017, VAAM/FFER@ICPR.

[17]  Sergio Escalera,et al.  Dominant and Complementary Multi-Emotional Facial Expression Recognition Using C-Support Vector Classification , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[18]  Christoph Busch,et al.  Intrinsic Limitations of Fingerprint Orientation Estimation , 2017, 2017 International Conference of the Biometrics Special Interest Group (BIOSIG).

[19]  Jianjiang Feng,et al.  Combining minutiae descriptors for fingerprint matching , 2008, Pattern Recognit..

[20]  Sergio Escalera,et al.  A novel deep network architecture for reconstructing RGB facial images from thermal for face recognition , 2019, Multimedia Tools and Applications.

[21]  Pauli Kuosmanen,et al.  Fingerprint Matching Using an Orientation-Based Minutia Descriptor , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Karthik Nandakumar,et al.  Fingerprint matching based on minutiae phase spectrum , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[23]  Arun Ross,et al.  A Survey on Anti-Spoofing Schemes for Fingerprint Recognition Systems , 2014 .

[24]  Zhang Yi,et al.  Fingerprint orientation field estimation using ridge projection , 2008, Pattern Recognit..

[25]  Francisco Herrera,et al.  A survey on fingerprint minutiae-based local matching for verification and identification: Taxonomy and experimental evaluation , 2015, Inf. Sci..

[26]  Samiran Chattopadhyay,et al.  An Efficient Fingerprint Matching Approach Based on Minutiae to Minutiae Distance Using Indexing with Effectively Lower Time Complexity , 2014, 2014 International Conference on Information Technology.

[27]  Jie Zhou,et al.  A model-based method for the computation of fingerprints' orientation field , 2004, IEEE Transactions on Image Processing.

[28]  Anil K. Jain,et al.  Benchmarking Fingerprint Minutiae Extractors , 2017, 2017 International Conference of the Biometrics Special Interest Group (BIOSIG).

[29]  Arun Kumar Sangaiah,et al.  Face expression recognition system based on ripplet transform type II and least square SVM , 2017, Multimedia Tools and Applications.

[30]  Albert Niel,et al.  A Fingerprint Matching Using Minutiae Triangulation , 2004, ICBA.

[31]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[32]  Naixue Xiong,et al.  Two-Stage Enhancement Scheme for Low-Quality Fingerprint Images by Learning From the Images , 2013, IEEE Transactions on Human-Machine Systems.

[33]  Davide Maltoni,et al.  Fingerprint verification competition at IJCB2011 , 2011, 2011 International Joint Conference on Biometrics (IJCB).

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

[35]  Sergio Escalera,et al.  Automatic Access Control Based on Face and Hand Biometrics in a Non-cooperative Context , 2018, 2018 IEEE Winter Applications of Computer Vision Workshops (WACVW).

[36]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[37]  Jufu Feng,et al.  Aggregating minutia-centred deep convolutional features for fingerprint indexing , 2019, Pattern Recognit..

[38]  Eryun Liu,et al.  Fingerprint matching by incorporating minutiae discriminability , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[39]  Christophe Rosenberger,et al.  Literature review of fingerprint quality assessment and its evaluation , 2016, IET Biom..

[40]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[41]  Gholamreza Anbarjafari,et al.  Low-quality fingerprint classification using deep neural network , 2018, IET Biom..

[42]  Anil K. Jain,et al.  Fingerprint Image Enhancement: Algorithm and Performance Evaluation , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[43]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[44]  Zaixing He,et al.  Low-quality fingerprint recognition using a limited ellipse-band-based matching method. , 2015, Journal of the Optical Society of America. A, Optics, image science, and vision.

[45]  Anil K. Jain,et al.  Automated Latent Fingerprint Recognition , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.