Iris Presentation Attack Detection by Attention-based and Deep Pixel-wise Binary Supervision Network
This addresses security vulnerabilities in iris recognition systems, particularly for deployment on mobile devices, though it is an incremental improvement over existing CNN-based methods.
The paper tackled iris presentation attack detection by proposing an attention-based deep pixel-wise binary supervision network to capture fine-grained local features and reduce overfitting, achieving a 6.50% HTER on the IIITD-WVU database and outperforming state-of-the-art methods.
Iris presentation attack detection (PAD) plays a vital role in iris recognition systems. Most existing CNN-based iris PAD solutions 1) perform only binary label supervision during the training of CNNs, serving global information learning but weakening the capture of local discriminative features, 2) prefer the stacked deeper convolutions or expert-designed networks, raising the risk of overfitting, 3) fuse multiple PAD systems or various types of features, increasing difficulty for deployment on mobile devices. Hence, we propose a novel attention-based deep pixel-wise binary supervision (A-PBS) method. Pixel-wise supervision is first able to capture the fine-grained pixel/patch-level cues. Then, the attention mechanism guides the network to automatically find regions that most contribute to an accurate PAD decision. Extensive experiments are performed on LivDet-Iris 2017 and three other publicly available databases to show the effectiveness and robustness of proposed A-PBS methods. For instance, the A-PBS model achieves an HTER of 6.50% on the IIITD-WVU database outperforming state-of-the-art methods.