Accurate iris segmentation and recognition using an end-to-end unified framework based on MADNet and DSANet

Due to their insufficient generalization ability, iris segmentation algorithms based on deep learning cannot accurately segment iris images without corresponding ground truth (GT) data. Moreover, prior to recognition, the segmented image requires normalization to reduce the influence of pupil deformation. However, normalization of nonconnected iris regions will introduce noise, thereby decreasing the recognition rate. This paper proposes an end-to-end unified framework based on deep learning that does not include normalization in order to achieve improved accuracy in iris segmentation and recognition. In this framework, a multiattention dense connection network (MADNet) and dense spatial attention network (DSANet) are designed for iris segmentation and recognition, respectively. Finally, numerous ablation experiments are conducted to demonstrate the effectiveness of MADNet and DSANet. Experiments on three employed databases show that our proposed method achieves the best segmentation and recognition performance on low-quality iris images without corresponding GT data.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

Iris segmentation algorithms based on deep learning lack generalization ability and cannot accurately segment iris images without corresponding ground truth data. Normalization is required to reduce the influence of pupil deformation, but it introduces noise in nonconnected iris regions and decreases recognition rate. This paper proposes an end-to-end unified framework based on deep learning that achieves improved accuracy in iris segmentation and recognition without normalization. The framework includes MADNet for iris segmentation and DSANet for iris recognition, and experiments show that it outperforms other methods on low-quality iris images without ground truth data.