Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks

TL;DR

This paper introduces robust iris segmentation methods using Fully Convolutional Networks and Generative Adversarial Networks, achieving state-of-the-art results across multiple datasets in both NIR and visible spectrum images.

Contribution

It presents novel iris segmentation approaches based on FCNs and GANs, outperforming existing techniques and providing a large labeled dataset for future research.

Findings

Achieved superior segmentation accuracy on multiple datasets.

Outperformed existing baseline methods in all evaluated datasets.

Provided a large manually labeled iris image dataset for research.

Abstract

The iris can be considered as one of the most important biometric traits due to its high degree of uniqueness. Iris-based biometrics applications depend mainly on the iris segmentation whose suitability is not robust for different environments such as near-infrared (NIR) and visible (VIS) ones. In this paper, two approaches for robust iris segmentation based on Fully Convolutional Networks (FCNs) and Generative Adversarial Networks (GANs) are described. Similar to a common convolutional network, but without the fully connected layers (i.e., the classification layers), an FCN employs at its end a combination of pooling layers from different convolutional layers. Based on the game theory, a GAN is designed as two networks competing with each other to generate the best segmentation. The proposed segmentation networks achieved promising results in all evaluated datasets (i.e., BioSec, CasiaI3, CasiaT4, IITD-1) of NIR images and (NICE.I, CrEye-Iris and MICHE-I) of VIS images in both non-cooperative and cooperative domains, outperforming the baselines techniques which are the best ones found so far in the literature, i.e., a new state of the art for these datasets. Furthermore, we manually labeled 2,431 images from CasiaT4, CrEye-Iris and MICHE-I datasets, making the masks available for research purposes.