Deep Gender Classification and Visualization of Near-Infra-Red Periocular-Iris images

In this paper, we present an approach of automatic pixels feature extraction for Gender Classification using Near-Infra-Red Periocular iris images with Deep learning. Previous works on gender-from-iris have been tried to find manually the best feature extraction methods to represent the gender information of the iris texture from normalized and encoded images. The application of Soft Biometrics with Deep Learning from NIR Periocular-iris-images is a new topic due to the small number of gender labeled images available. In this work, we used bottleneck, fine-tuning and Convolutional Neural Network (CNN) trained from scratch approaches, to identify the most relevant areas on periocular iris images. Training a CNN from scratch with a small number of images using the Data Augmentation technique reached the best classification rate and automatically found the most relevant areas for this task. We concluded that training a model from scratch even with a small number of layers, performed better than using a pre-trained powerful model such as VGG and Resnet in this kind of problems. The best result reached from our CNN trained from scratch was 85.48% of accuracy for gender classification.

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

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  O. Abdel Alim,et al.  Texture classification of the human iris using artificial neural networks , 2002, 11th IEEE Mediterranean Electrotechnical Conference (IEEE Cat. No.02CH37379).

[4]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[5]  Juan E. Tapia,et al.  Gender classification from NIR iris images using deep learning , 2017 .

[6]  Tal Hassner,et al.  Age and gender classification using convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[7]  Tieniu Tan,et al.  Global Texture Analysis of Iris Images for Ethnic Classification , 2006, ICB.

[8]  Hugo Proença,et al.  Deep-PRWIS: Periocular Recognition Without the Iris and Sclera Using Deep Learning Frameworks , 2018, IEEE Transactions on Information Forensics and Security.

[9]  A. Ross,et al.  Iris or Periocular? Exploring Sex Prediction from Near Infrared Ocular Images , 2016, 2016 International Conference of the Biometrics Special Interest Group (BIOSIG).

[10]  Juan E. Tapia,et al.  Gender classification from periocular NIR images using fusion of CNNs models , 2018, 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA).

[11]  R. K. Sharma,et al.  SVM Based Gender Classification Using Iris Images , 2012, 2012 Fourth International Conference on Computational Intelligence and Communication Networks.

[12]  Marios Savvides,et al.  An exploration of gender identification using only the periocular region , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[13]  Xiaoming Liu,et al.  Demographic Estimation from Face Images: Human vs. Machine Performance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Claudio A. Perez,et al.  Gender Classification from Iris Images Using Fusion of Uniform Local Binary Patterns , 2014, ECCV Workshops.

[16]  Reza Derakhshani,et al.  Gender prediction from mobile ocular images: A feasibility study , 2017, 2017 IEEE International Symposium on Technologies for Homeland Security (HST).

[17]  Richa Singh,et al.  Gender and ethnicity classification of Iris images using deep class-encoder , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

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

[19]  Claudio A. Perez,et al.  Gender Classification From the Same Iris Code Used for Recognition , 2016, IEEE Transactions on Information Forensics and Security.

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

[21]  Claudio A. Perez,et al.  Gender Classification Based on Fusion of Different Spatial Scale Features Selected by Mutual Information From Histogram of LBP, Intensity, and Shape , 2013, IEEE Transactions on Information Forensics and Security.

[22]  K.W. Bowyer,et al.  Learning to predict gender from iris images , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[23]  Juan E. Tapia,et al.  Gender classification from multispectral periocular images , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[24]  K. Bowyer,et al.  Predicting ethnicity and gender from iris texture , 2011, 2011 IEEE International Conference on Technologies for Homeland Security (HST).

[25]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[26]  Andrey Kuehlkamp,et al.  Gender-from-Iris or Gender-from-Mascara? , 2017, 2017 IEEE Winter Conference on Applications of Computer Vision (WACV).

[27]  Alexander Binder,et al.  Understanding and Comparing Deep Neural Networks for Age and Gender Classification , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[28]  Claudio A. Perez,et al.  Gender Classification From Face Images Using Mutual Information and Feature Fusion , 2012 .

[29]  Michael C. Fairhurst,et al.  Exploring Gender Prediction from Iris Biometrics , 2015, 2015 International Conference of the Biometrics Special Interest Group (BIOSIG).

[30]  Michael S. Lew,et al.  Deep learning for visual understanding: A review , 2016, Neurocomputing.

[31]  Hazim Kemal Ekenel,et al.  How Transferable Are CNN-Based Features for Age and Gender Classification? , 2016, 2016 International Conference of the Biometrics Special Interest Group (BIOSIG).