Convolutional Neural Network-Based Periocular Recognition in Surveillance Environments

Visible light surveillance cameras are currently deployed on a large scale to prevent crime and accidents in public urban environments. For this reason, various human identification studies using biometric data are underway in surveillance environments. The most active research area is face recognition, which generally shows excellent performance; however, aging, changes in facial expression, and occlusions by accessories cause a rapid decline in recognition performance. To resolve these problems, we propose a periocular recognition method in surveillance environments that is based on the convolutional neural network. In this paper, experiments were performed using the custom-made Dongguk periocular database and the open database of ChokePoint database. It was confirmed that the proposed method performs better than existing techniques used in periocular recognition. It was also found to perform better than conventional techniques in face recognition when an occlusion is present.

[1]  Kaushik Roy,et al.  Data augmentation in CNN-based periocular authentication , 2016, 2016 6th International Conference on Information Communication and Management (ICICM).

[2]  Damon L. Woodard,et al.  Periocular region appearance cues for biometric identification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[3]  Umut Uludag,et al.  On identification from periocular region utilizing SIFT and SURF , 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

[4]  Sambit Bakshi,et al.  Phase Intensive Global Pattern for periocular recognition , 2014, 2014 Annual IEEE India Conference (INDICON).

[5]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[6]  Fernando Alonso-Fernandez,et al.  A survey on periocular biometrics research , 2016, Pattern Recognit. Lett..

[7]  Hugo Proença,et al.  Periocular recognition: Analysis of performance degradation factors , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[8]  Lina J. Karam,et al.  A Study and Comparison of Human and Deep Learning Recognition Performance under Visual Distortions , 2017, 2017 26th International Conference on Computer Communication and Networks (ICCCN).

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

[10]  Kang Ryoung Park,et al.  A robust eyelash detection based on iris focus assessment , 2007, Pattern Recognit. Lett..

[11]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[12]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[14]  Edmundo Hoyle,et al.  A fusion approach to unconstrained iris recognition , 2012, Pattern Recognit. Lett..

[15]  Kiran B. Raja,et al.  Binarized statistical features for improved iris and periocular recognition in visible spectrum , 2014, 2nd International Workshop on Biometrics and Forensics.

[16]  Karl Ricanek,et al.  LBP-based periocular recognition on challenging face datasets , 2013, EURASIP J. Image Video Process..

[17]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[18]  Arun Ross,et al.  Periocular Biometrics in the Visible Spectrum , 2011, IEEE Transactions on Information Forensics and Security.

[19]  Yongkang Wong,et al.  Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition , 2011, CVPR 2011 WORKSHOPS.

[20]  Himanshu S. Bhatt,et al.  Periocular biometrics: When iris recognition fails , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[21]  Damon L. Woodard,et al.  Genetic-Based Type II Feature Extraction for Periocular Biometric Recognition: Less is More , 2010, 2010 20th International Conference on Pattern Recognition.

[22]  Kang Ryoung Park,et al.  Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors , 2017, Sensors.

[23]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[24]  Damon L. Woodard,et al.  Soft biometric classification using periocular region features , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[25]  Damon L. Woodard,et al.  Personal identification using periocular skin texture , 2010, SAC '10.

[26]  David Menotti,et al.  Deep periocular representation aiming video surveillance , 2017, Pattern Recognit. Lett..

[27]  Zia Saquib,et al.  Person recognition based on fusion of iris and periocular biometrics , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[28]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[29]  Damon L. Woodard,et al.  Performance evaluation of local appearance based periocular recognition , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[30]  Ajay Kumar,et al.  Accurate Periocular Recognition Under Less Constrained Environment Using Semantics-Assisted Convolutional Neural Network , 2017, IEEE Transactions on Information Forensics and Security.

[31]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[32]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[33]  Arun Ross,et al.  Mitigating effects of plastic surgery: Fusing face and ocular biometrics , 2012, 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS).

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

[35]  Marios Savvides,et al.  Unconstrained periocular biometric acquisition and recognition using COTS PTZ camera for uncooperative and non-cooperative subjects , 2012, 2012 IEEE Workshop on the Applications of Computer Vision (WACV).

[36]  B. V. K. Vijaya Kumar,et al.  What Is a "Good" Periocular Region for Recognition? , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[37]  Anil K. Jain,et al.  Periocular biometrics in the visible spectrum: A feasibility study , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.

[38]  Arun Ross,et al.  On the Fusion of Periocular and Iris Biometrics in Non-ideal Imagery , 2010, 2010 20th International Conference on Pattern Recognition.

[39]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[40]  Fernando Alonso-Fernandez,et al.  Periocular Recognition Using Retinotopic Sampling and Gabor Decomposition , 2012, ECCV Workshops.

[41]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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