Fusion of Handcrafted and Deep Learning Features for Large-Scale Multiple Iris Presentation Attack Detection

Daksha Yadav, Naman Kohli, Akshay Agarwal, Mayank Vatsa, Richa Singh, Afzel Noore; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 572-579

Abstract


Typical iris recognition systems may be vulnerable to presentation attacks such as textured contact lenses, print attacks, and synthetic iris images. Increasing applications of iris recognition have raised the importance of efficient presentation attack detection algorithms. In this paper, we propose a novel algorithm for detecting iris presentation attacks using a combination of handcrafted and deep learning based features. The proposed algorithm combines local and global Haralick texture features in multi-level Redundant Discrete Wavelet Transform domain with VGG features to encode the textural variations between real and attacked iris images. The proposed algorithm is extensively tested on a large iris dataset comprising more than 270,000 real and attacked iris images and yields a total error of 1.01%. The experimental evaluation demonstrates the superior presentation attack detection performance of the proposed algorithm as compared to state-of-the-art algorithms.

Related Material


[pdf]
[bibtex]
@InProceedings{Yadav_2018_CVPR_Workshops,
author = {Yadav, Daksha and Kohli, Naman and Agarwal, Akshay and Vatsa, Mayank and Singh, Richa and Noore, Afzel},
title = {Fusion of Handcrafted and Deep Learning Features for Large-Scale Multiple Iris Presentation Attack Detection},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}