Deep palmprint recognition algorithm based on self-supervised learning and uncertainty loss

With the rapid development of deep learning technology, an increasing number of people are adopting palmprint recognition algorithms based on deep learning for identity authentication. However, these algorithms are susceptible to factors such as palm placement, light source, and insufficient data sampling, resulting in poor recognition accuracy. To address these issues, this paper proposes a new end-to-end deep palmprint recognition algorithm (SSLAUL), which introduces self-supervised representation learning based on contextual prediction, utilizing unlabeled palmprint data for pre-training before introducing the trained parameters into the downstream model for fine-tuning. An uncertainty loss function is introduced into the downstream model, using the homoskedastic uncertainty as a benchmark to do adaptive weight adjustment for different loss functions dynamically. Channel and spatial attention mechanisms are also introduced to extract highly discriminative local features. In this paper, the algorithm is validated on publicly available IITD, CASIA, and PolyU palmprint datasets. The method always achieves the best recognition performance compared to other state-of-the-art algorithms.