Uncertainty-Aware Bilateral Transformer for Accurate and Reliable Iris Segmentation

Jianze Wei, Xingyu Gao, Yunlong Wang, Ran He, Zhenan Sun

Abstract: Iris segmentation is a deterministic and critical part of the iris recognition system. However, its performance is usually degraded by data uncertainty in acquisition and annotation, impeding more accurate recognition of the iris recognition system. In the paper, we propose a bilateral self-attention by exploring spatial and visual relationships to effectively distinguish between iris and non-iris regions, then design a bilateral Transformer by enhancing spatial perception and hierarchical feature fusion to mitigate the impact of acquisition uncertainty. Besides, iris segmentation uncertainty learning is developed to estimate the uncertainty map according to prediction discrepancy. With the estimated uncertainty, a weighting scheme and a regularization term are designed to minimize the effect of annotation uncertainty. To investigate data uncertainty, the paper presents a challenging near-infrared iris dataset named UTIris. It comprises 3,690 images with high acquisition uncertainty and provides rich segmentation masks to explore annotation uncertainty. Furthermore, we manually label a large-scale iris dataset, ND-0405, with additional binary maps of iris masks to evaluate segmentation performance. Experimental results on UTIris and four other databases demonstrate the effectiveness of the proposed method in iris segmentation, and its segmentation improvement consequently promotes recognition accuracy.