A Robust Iris Segmentation Scheme Based on Improved U-Net

Iris segmentation plays an important role in the iris recognition system, and the accurate segmentation of iris can lay a good foundation for the follow-up work of iris recognition and can improve greatly the efficiency of iris recognition. We proposed four new feasible network schemes, and the best network model fully dilated convolution combining U-Net (FD-UNet) is obtained by training and testing on the same datasets. The FD-UNet uses dilated convolution instead of original convolution to extract more global features so that the details of images can be processed better. The proposed method is tested in the near-infrared illumination iris datasets (CASIA-iris-interval-v4.0 and ND-IRIS-0405) and the visible light illumination iris dataset (UBIRIS.v2). The f1 scores of our model on the CASIA-iris-interval-v4.0, ND-IRIS-0405, and UBIRIS.v2 datasets reached 97.36%, 96.74%, and 94.81%, respectively. The experimental results show that our network model improves the accuracy and reduces the error rate, which performs well on both near-infrared illumination and visible light illumination iris datasets with good robustness.

[1]  Peter Corcoran,et al.  An End to End Deep Neural Network for Iris Segmentation in Unconstraint Scenarios , 2017, Neural Networks.

[2]  Xin Li,et al.  Iris R-CNN: Accurate Iris Segmentation in Non-cooperative Environment , 2019, ArXiv.

[3]  Tieniu Tan,et al.  Toward Accurate and Fast Iris Segmentation for Iris Biometrics , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[5]  Michal Haindl,et al.  Unsupervised detection of non-iris occlusions , 2015, Pattern Recognit. Lett..

[6]  Andreas Uhl,et al.  Segmentation-Level Fusion for Iris Recognition , 2015, 2015 International Conference of the Biometrics Special Interest Group (BIOSIG).

[7]  Automated, non-invasive iris recognition system and method - European Patent Office - EP 1126403 A2 , 2001 .

[8]  Tao Zhou,et al.  Automatic lung nodule detection using a 3D deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs , 2018, Comput. Biol. Medicine.

[9]  David Zhang,et al.  Accurate iris segmentation based on novel reflection and eyelash detection model , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).

[10]  Tieniu Tan,et al.  Iris recognition using circular symmetric filters , 2002, Object recognition supported by user interaction for service robots.

[11]  Lixin Gao,et al.  Automatic lung nodule detection using multi-scale dot nodule-enhancement filter and weighted support vector machines in chest computed tomography , 2019, PloS one.

[12]  Zhenan Sun,et al.  Accurate iris segmentation in non-cooperative environments using fully convolutional networks , 2016, 2016 International Conference on Biometrics (ICB).

[13]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[14]  Luís A. Alexandre,et al.  The UBIRIS.v2: A Database of Visible Wavelength Iris Images Captured On-the-Move and At-a-Distance , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Patrick J. Flynn,et al.  A Survey of Iris Biometrics Research: 2008-2010 , 2013, Handbook of Iris Recognition.

[16]  Huangjian Yi,et al.  Semi-Supervised Cerebrovascular Segmentation by Hierarchical Convolutional Neural Network , 2018, IEEE Access.

[17]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Fernando Alonso-Fernandez,et al.  IrisSeg: A fast and robust iris segmentation framework for non-ideal iris images , 2016, 2016 International Conference on Biometrics (ICB).

[19]  Andreas Uhl,et al.  Weighted adaptive Hough and ellipsopolar transforms for real-time iris segmentation , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[20]  Chi Chen,et al.  A Robust Iris Segmentation Using Fully Convolutional Network with Dilated Convolutions , 2018, 2018 IEEE International Symposium on Multimedia (ISM).

[21]  Yao Lu,et al.  RIC-Unet: An Improved Neural Network Based on Unet for Nuclei Segmentation in Histology Images , 2019, IEEE Access.

[22]  Andreas Uhl,et al.  Iris Segmentation Using Fully Convolutional Encoder--Decoder Networks , 2017 .

[23]  Alice J. O'Toole,et al.  FRVT 2006 and ICE 2006 Large-Scale Experimental Results , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Peter Peer,et al.  End-to-End Iris Segmentation Using U-Net , 2018, 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI).

[25]  Andreas Uhl,et al.  A Ground Truth for Iris Segmentation , 2014, 2014 22nd International Conference on Pattern Recognition.