Constrained Design of Deep Iris Networks

Despite the promise of recent deep neural networks to provide more accurate and efficient iris recognition compared to traditional techniques, there are vital properties of the classic IrisCode which are almost unable to be achieved with current deep iris networks: the compactness of model and the small number of computing operations (FLOPs). This paper casts the iris network design process as a constrained optimization problem which takes model size and computation into account as learning criteria. On one hand, this allows us to fully automate the network design process to search for the optimal iris network architecture with the highest recognition accuracy confined to the computation and model compactness constraints. On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent deep iris networks. It also enables us to learn an optimal iris network and demonstrate state-of-the-art performance with less computation and memory requirements.

[1]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Kalyanmoy Deb,et al.  A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications , 2017, IEEE Transactions on Evolutionary Computation.

[3]  John Daugman,et al.  Searching for doppelgängers: assessing the universality of the IrisCode impostors distribution , 2016, IET Biom..

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

[5]  Sridha Sridharan,et al.  Iris Recognition With Off-the-Shelf CNN Features: A Deep Learning Perspective , 2018, IEEE Access.

[6]  Paolo Frasconi,et al.  Bilevel Programming for Hyperparameter Optimization and Meta-Learning , 2018, ICML.

[7]  Hugo Proença,et al.  IRINA: Iris Recognition (Even) in Inaccurately Segmented Data , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  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.

[9]  Tie-Yan Liu,et al.  Neural Architecture Optimization , 2018, NeurIPS.

[10]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[11]  Enrique Cantó,et al.  Hardware-software co-design of an iris recognition algorithm , 2011, IET Inf. Secur..

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

[13]  Tieniu Tan,et al.  DeepIris: Learning pairwise filter bank for heterogeneous iris verification , 2016, Pattern Recognit. Lett..

[14]  Sébastien Bubeck,et al.  Convex Optimization: Algorithms and Complexity , 2014, Found. Trends Mach. Learn..

[15]  Richard S. Zemel,et al.  Gradient-based Optimization of Neural Network Architecture , 2018, ICLR.

[16]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[17]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[18]  John Daugman,et al.  Information Theory and the IrisCode , 2016, IEEE Transactions on Information Forensics and Security.

[19]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.

[20]  John Daugman,et al.  New Methods in Iris Recognition , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  Bo Chen,et al.  NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications , 2018, ECCV.

[22]  Quoc V. Le,et al.  Large-Scale Evolution of Image Classifiers , 2017, ICML.

[23]  Elad Eban,et al.  MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  John Daugman,et al.  How iris recognition works , 2002, IEEE Transactions on Circuits and Systems for Video Technology.

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

[27]  David Zhang,et al.  An Analysis of IrisCode , 2010, IEEE Transactions on Image Processing.

[28]  Ajay Kumar,et al.  Towards More Accurate Iris Recognition Using Deeply Learned Spatially Corresponding Features , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[29]  Patrick J. Flynn,et al.  Improved Iris Recognition through Fusion of Hamming Distance and Fragile Bit Distance , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[31]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[32]  Abhishek Kumar Gangwar,et al.  DeepIrisNet: Deep iris representation with applications in iris recognition and cross-sensor iris recognition , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[33]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[34]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[35]  Bir Bhanu,et al.  Deep Learning for Biometrics , 2017, Advances in Computer Vision and Pattern Recognition.

[36]  Ramachandra Raghavendra,et al.  DeepIrisNet2: Learning Deep-IrisCodes from Scratch for Segmentation-Robust Visible Wavelength and Near Infrared Iris Recognition , 2019, ArXiv.

[37]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Andreas Uhl,et al.  Design Decisions for an Iris Recognition SDK , 2016 .