Toward Accurate and Reliable Iris Segmentation Using Uncertainty Learning
This work addresses a bottleneck in iris recognition systems by improving segmentation accuracy and reliability, though it appears to be an incremental advancement over existing methods.
The paper tackles the problem of unreliable iris segmentation, particularly in the limbic area, by proposing a bilateral transformer architecture with uncertainty learning, achieving better segmentation performance using only 20% of the FLOPs compared to the state-of-the-art IrisParseNet.
Iris segmentation is a deterministic part of the iris recognition system. Unreliable segmentation of iris regions especially the limbic area is still the bottleneck problem, which impedes more accurate recognition. To make further efforts on accurate and reliable iris segmentation, we propose a bilateral self-attention module and design Bilateral Transformer (BiTrans) with hierarchical architecture by exploring spatial and visual relationships. The bilateral self-attention module adopts a spatial branch to capture spatial contextual information without resolution reduction and a visual branch with a large receptive field to extract the visual contextual features. BiTrans actively applies convolutional projections and cross-attention to improve spatial perception and hierarchical feature fusion. Besides, Iris Segmentation Uncertainty Learning is developed to learn the uncertainty map according to prediction discrepancy. With the estimated uncertainty, a weighting scheme and a regularization term are designed to reduce predictive uncertainty. More importantly, the uncertainty estimate reflects the reliability of the segmentation predictions. Experimental results on three publicly available databases demonstrate that the proposed approach achieves better segmentation performance using 20% FLOPs of the SOTA IrisParseNet.