The overlapping effect and fusion protocols of data augmentation techniques in iris PAD

Abstract

Iris Presentation Attack Detection (PAD) algorithms address the vulnerability of iris recognition systems to presentation attacks. With the great success of deep learning methods in various computer vision fields, neural network-based iris PAD algorithms emerged. However, most PAD networks suffer from overfitting due to insufficient iris data variability. Therefore, we explore the impact of various data augmentation techniques on performance and the generalizability of iris PAD. We apply several data augmentation methods to generate variability, such as shift, rotation, and brightness. We provide in-depth analyses of the overlapping effect of these methods on performance. In addition to these widely used augmentation techniques, we also propose an augmentation selection protocol based on the assumption that various augmentation techniques contribute differently to the PAD performance. Moreover, two fusion methods are performed for more comparisons: the strategy-level and the score-level combination. We demonstrate experiments on two fine-tuned models and one trained from the scratch network and perform on the datasets in the Iris-LivDet-2017 competition designed for generalizability evaluation. Our experimental results show that augmentation methods improve iris PAD performance in many cases. Our least overlap-based augmentation selection protocol achieves the lower error rates for two networks. Besides, the shift augmentation strategy also exceeds state-of-the-art (SoTA) algorithms on the Clarkson and IIITD-WVU datasets.

Intra and Cross-spectrum Iris Presentation Attack Detection in the NIR and Visible Domains Using Attention-based and Pixel-wise Supervised Learning

“…Even though PBS boosts iris PAD performance under intra-database/-spectrum, it shows imperfect invariation under more complicated cross-PA, cross-database, and cross-spectrum scenarios (See results in Table 5,11,and 10). As a result, it is worth finding the important regions to focus on, although it contradicts learning more discriminative features.…”

Iris Liveness Detection Using Fragmental Energy of Haar Transformed Iris Images Using Ensemble of Machine Learning Classifiers

“…Author Fang et al [20] apply many data augmentation methods to generate variability. The strategy-level and the score-level combination of fusion methods are used for Iris PAD.…”

Deep Learning for Iris Recognition: A Survey

“…Given the difficulty of collecting iris PAD data, most databases contain, at most, a few hundred subjects. To address this, Fang et al [47] studied data augmentation techniques that modify position, scale or illumination. Using three architectures (ResNet50, VGG16, MobileNetv3-small) and three databases with printouts and textured contact lenses, they found that data augmentation improves PAD performance significantly, but each technique has a positive role on a particular dataset or CNN.…”

“…Part of the problem lies into the limited size of existing databases, which is an issue for data-hungry DL approaches. Some solutions, as studied by some of the methods above, are data augmentation by geometric or illumination modifications [47], or creating additional synthetic data via generative methods [193]. Human-aided DL training is another promising avenue.…”