6. Iris Segmentation Using Fully Convolutional Encoder–Decoder Networks

As a considerable breakthrough in artificial intelligence, deep learning has gained great success in resolving key computer vision challenges. Accurate segmentation of the iris region in the eye image plays a vital role in efficient performance of iris recognition systems, as one of the most reliable systems used for biometric identification. In this chapter, as the first contribution, we consider the application of Fully Convolutional Encoder–Decoder Networks (FCEDNs) for iris segmentation. To this extent, we utilize three types of FCEDN architectures for segmentation of the iris in the images, obtained from five different datasets, acquired under different scenarios. Subsequently, we conduct performance analysis, evaluation, and comparison of these three networks for iris segmentation. Furthermore, and as the second contribution, in order to subsidize the true evaluation of the proposed networks, we apply a selection of conventional (non-CNN) iris segmentation algorithms on the same datasets, and similarly evaluate their performances. The results then get compared against those obtained from the FCEDNs. Based on the results, the proposed networks achieve superior performance over all other algorithms, on all datasets.