Abstract
Applications of fully convolutional networks (FCN) in iris segmentation have shown promising advances. For mobile and embedded systems, a significant challenge is that the proposed FCN architectures are extremely computationally demanding. In this article, we propose a resource-efficient, end-to-end iris recognition flow, which consists of FCN-based segmentation and a contour fitting module, followed by Daugman normalization and encoding. To attain accurate and efficient FCN models, we propose a three-step SW/HW co-design methodology consisting of FCN architectural exploration, precision quantization, and hardware acceleration. In our exploration, we propose multiple FCN models, and in comparison to previous works, our best-performing model requires 50× fewer floating-point operations per inference while achieving a new state-of-the-art segmentation accuracy. Next, we select the most efficient set of models and further reduce their computational complexity through weights and activations quantization using an 8-bit dynamic fixed-point format. Each model is then incorporated into an end-to-end flow for true recognition performance evaluation. A few of our end-to-end pipelines outperform the previous state of the art on two datasets evaluated. Finally, we propose a novel dynamic fixed-point accelerator and fully demonstrate the SW/HW co-design realization of our flow on an embedded FPGA platform. In comparison with the embedded CPU, our hardware acceleration achieves up to 8.3× speedup for the overall pipeline while using less than 15% of the available FPGA resources. We also provide comparisons between the FPGA system and an embedded GPU showing different benefits and drawbacks for the two platforms.
- Biometrics. 2010. CASIA Iris V4 Dataset. Retrieved September 1, 2018 from http://biometrics.idealtest.org/dbDetailForUser.do?id=4Google Scholar
- Mohammed A. M. Abdullah, Satnam S. Dlay, Wai L. Woo, and Jonathon A. Chambers. 2017. Robust iris segmentation method based on a new active contour force with a noncircular normalization. IEEE Transactions on Systems, Man, and Cybernetics: Systems 47, 12, 3128--3141.Google ScholarCross Ref
- Fernando Alonso-Fernandez and Josef Bigun. 2012. Iris boundaries segmentation using the generalized structure tensor. A study on the effects of image degradation. In Proceedings of the IEEE International Conference on Biometrics: Theory, Applications, and Systems. 426--431.Google ScholarCross Ref
- Muhammad Arsalan, Rizwan Ali Naqvi, Dong Seop Kim, Phong Ha Nguyen, Muhammad Owais, and Kang Ryoung Park. 2018. IrisDenseNet: Robust iris segmentation using densely connected fully convolutional networks in the images by visible light and near-infrared light camera sensors. Sensors 18, 5, 1501.Google ScholarCross Ref
- Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. 2015. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561.Google Scholar
- Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L. Yuille. 2018. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence 40, 4, 834--848.Google ScholarCross Ref
- Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2014. Training deep neural networks with low precision multiplications. arXiv:1412.7024.Google Scholar
- John Daugman. 2007. New methods in iris recognition. IEEE Transactions on Systems, Man, and Cybernetics 37, 5, 1167--1175.Google ScholarDigital Library
- John Daugman. 2009. How iris recognition works. In The Essential Guide to Image Processing. Elsevier, 715--739.Google Scholar
- John G. Daugman. 1993. High confidence visual recognition of persons by a test of statistical independence. IEEE Transactions on Pattern Analysis and Machine Intelligence 15, 11, 1148--1161.Google ScholarDigital Library
- Abhishek Gangwar and Akanksha Joshi. 2016. DeepIrisNet: Deep iris representation with applications in iris recognition and cross-sensor iris recognition. In Proceedings of the IEEE International Conference on Image Processing. 2301--2305.Google ScholarCross Ref
- Abhishek Gangwar, Akanksha Joshi, Ashutosh Singh, Fernando Alonso-Fernandez, and Josef Bigun. 2016. IrisSeg: A fast and robust iris segmentation framework for non-ideal iris images. In Proceedings of the IEEE International Conference on Biometrics. 1--8.Google ScholarCross Ref
- Soheil Hashemi, Nicholas Anthony, Hokchhay Tann, R. Iris Bahar, and Sherief Reda. 2017. Understanding the impact of precision quantization on the accuracy and energy of neural networks. In Proceedings of the IEEE Design, Automation, and Test in Europe Conference and Exhibition. 1474--1479.Google ScholarCross Ref
- Soheil Hashemi, Hokchhay Tann, Francesco Buttafuoco, and Sherief Reda. 2018. Approximate computing for biometric security systems: A case study on iris scanning. In Proceedings of the IEEE Design, Automation, and Test in Europe Conference and Exhibition. 319--324.Google ScholarCross Ref
- Heinz Hofbauer, Fernando Alonso-Fernandez, Josef Bigun, and Andreas Uhl. 2016. Experimental analysis regarding the influence of iris segmentation on the recognition rate. IET Biometrics 5, 3, 200--211.Google ScholarCross Ref
- Heinz Hofbauer, Fernando Alonso-Fernandez, Peter Wild, Josef Bigun, and Andreas Uhl. 2014. A ground truth for iris segmentation. In Proceedings of the IEEE International Conference on Pattern Recognition. 527--532.Google ScholarDigital Library
- Ehsaneddin Jalilian and Andreas Uhl. 2017. Iris segmentation using fully convolutional encoder--decoder networks. In Deep Learning for Biometrics. Springer, 133--155.Google Scholar
- Ehsaneddin Jalilian, Andreas Uhl, and Roland Kwitt. 2017. Domain adaptation for CNN based iris segmentation. In Proceedings of the 2017 International Conference of the Biometrics Special Interest Group (BIOSIG’17). 1--6.Google ScholarCross Ref
- W. K. Kong and D. Zhang. 2001. Accurate iris segmentation based on novel reflection and eyelash detection model. In Proceedings of the IEEE International Symposium on Intelligent Multimedia, Video, and Speech Processing. 263--266.Google Scholar
- Ajay Kumar and Arun Passi. 2010. Comparison and combination of iris matchers for reliable personal authentication. Pattern Recognition 43, 3 (2010), 1016--1026.Google ScholarDigital Library
- Nianfeng Liu, Haiqing Li, Man Zhang, Jing Liu, Zhenan Sun, and Tieniu Tan. 2016. Accurate iris segmentation in non-cooperative environments using fully convolutional networks. In Proceedings of the IEEE International Conference on Biometrics. 1--8.Google ScholarCross Ref
- Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3431--3440.Google ScholarCross Ref
- Mariano López, John Daugman, and Enrique Cantó. 2011. Hardware-software co-design of an iris recognition algorithm. IET Information Security 5, 1, 60--68.Google ScholarCross Ref
- Li Ma, Yunhong Wang, and Tieniu Tan. 2002. Iris recognition using circular symmetric filters. In Proceedings of the IEEE International Conference on Pattern Recognition. 414--417.Google Scholar
- L. Masek and P. Kovesi. 2003. MATLAB Source Code for a Biometric Identification System Based on Iris Patterns. The School of Computer Science and Software Engineering, The University of Western Australia.Google Scholar
- D. Petrovska and A. Mayoue. 2007. Description and Documentation of the BioSecure Software Library. Project No IST-2002-507634-BioSecure, Deliverable.Google Scholar
- Ahmad Poursaberi and Babak N. Araabi. 2005. A novel iris recognition system using morphological edge detector and wavelet phase features. ICGST International Journal on Graphics, Vision and Image Processing 5, 6, 9--15.Google Scholar
- Hugo Proença and Luís A. Alexandre. 2007. The NICE. I: Noisy iris challenge evaluation-part I. In Proceedings of the IEEE International Conference on Biometrics: Theory, Applications, and Systems. 1--4.Google Scholar
- Christian Rathgeb, Andreas Uhl, and Peter Wild. 2012. Iris Biometrics: From Segmentation to Template Security. Vol. 59. Springer Science 8 Business Media.Google Scholar
- Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. Retrieved September 23, 2018 from http://pjreddie.com/darknet/.Google Scholar
- C. J. Van Rijsbergen. 1979. Information Retrieval (2nd ed.). Butterworth-Heinemann.Google ScholarDigital Library
- Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. 234--241.Google ScholarCross Ref
- Samir Shah and Arun Ross. 2009. Iris segmentation using geodesic active contours. IEEE Transactions on Information Forensics and Security 4, 4, 824--836.Google ScholarDigital Library
- Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, and Martin Riedmiller. 2014. Striving for simplicity: The all convolutional net. arXiv:1412.6806.Google Scholar
- Hokchhay Tann, Soheil Hashemi, R. Iris Bahar, and Sherief Reda. 2017. Hardware-software codesign of accurate, multiplier-free deep neural networks. In Proceedings of the IEEE Design Automation Conference. 1--6.Google ScholarDigital Library
- Christel-Loic Tisse, Lionel Martin, Lionel Torres, and Michel Robert. 2002. Person identification technique using human iris recognition. In Proceedings of the Vision Interface Conference, Vol. 294. 294--299.Google Scholar
- Andreas Uhl and Peter Wild. 2012. Weighted adaptive Hough and ellipsopolar transforms for real-time iris segmentation. In Proceedings of the IEEE International Conference on Biometrics. 283--290.Google ScholarCross Ref
- Richard P. Wildes, Jane C. Asmuth, Gilbert L. Green, Stephen C. Hsu, Raymond J. Kolczynski, James R. Matey, and Sterling E. McBride. 1994. A system for automated iris recognition. In Proceedings of the IEEE Workshop on Applications of Computer Vision. 121--128.Google Scholar
- Guangzhu Xu and Zaifeng Zang. 2008. An efficient iris recognition system based on intersecting cortical model neural network. International Journal of Cognitive Informatics and Natural Intelligence 2, 3, 43--56.Google ScholarCross Ref
- Zijing Zhao and Ajay Kumar. 2015. An accurate iris segmentation framework under relaxed imaging constraints using total variation model. In Proceedings of the IEEE International Conference on Computer Vision. 3828--3836.Google ScholarDigital Library
- Zijing Zhao and Ajay Kumar. 2017. Towards more accurate iris recognition using deeply learned spatially corresponding features. In Proceedings of the IEEE International Conference on Computer Vision. 3809--3818.Google ScholarCross Ref
Index Terms
- A Resource-Efficient Embedded Iris Recognition System Using Fully Convolutional Networks
Recommendations
Real-time Iris Recognition System for Non-Ideal Iris Images
ICCAE 2019: Proceedings of the 2019 11th International Conference on Computer and Automation EngineeringBiometrics is popular nowadays because of its very useful security applications. There are different biometric technologies but iris recognition system was considered the most reliable since human irises are unique and cannot be forged easily. The study ...
Floating-point accelerator for biometric recognition on FPGA embedded systems
This paper aims at presenting a Floating-Point Biometric Accelerator (FPBA) specially designed to speed-up processing kernels used in biometric algorithms. The FPBA was developed in order to facilitate its inclusion as part of an embedded system that ...
Rapid Implementation of Embedded Systems using Xilinx Zynq Platform
SEEDA-CECNSM '16: Proceedings of the SouthEast European Design Automation, Computer Engineering, Computer Networks and Social Media ConferenceIn any digital system design, it is crucial to achieve the lowest time-to-market possible. Indeed, that need has pushed large FPGA manufacturers to produce SoCs which will implement reprogrammable logic along with CPU and DSP cores. Especially, during ...
Comments