Towards open-set touchless palmprint recognition via weight-based meta metric learning. (January 2022)

• Record Type: Journal Article
• Authors: Shao, Huikai; Zhong, Dexing
• Is Part Of: Pattern recognition. Volume 121(2022)
• Publication Date: 2022-01
• Subjects: Biometrics -- Palmprint recognition -- Meta learning -- Metric learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108247
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Weight-based Meta Metric Learning (W2ML) is proposed for open-set palmprint recognition. Hard sample mining and weighting are adopted to improve the efficiency. Extensive experiments are conducted on four constrained and unconstrained benchmarks. By W2ML method, the identification accuracy is increased by up to 9.11%. By W2ML method, Equal Error Rates (EER) is reduced by up to 2.97%. Abstract: Touchless biometrics has become significant in the wake of novel coronavirus 2019 (COVID-19). Due to the convenience, user-friendly, and high-accuracy, touchless palmprint recognition shows great potential when the hygiene issues are considered during COVID-19. However, previous palmprint recognition methods are mainly focused on close-set scenario. In this paper, a novel Weight-based Meta Metric Learning (W2ML) method is proposed for accurate open-set touchless palmprint recognition, where only a part of categories is seen during training. Deep metric learning-based feature extractor is learned in a meta way to improve the generalization ability. Multiple sets are sampled randomly to define support and query sets, which are further combined into meta sets to constrain the set-based distances. Particularly, hard sample mining and weighting are adopted to select informative meta sets to improve the efficiency. Finally, embeddings with obvious inter-class and intra-class differences are obtained as features for palmprint identification and verification. Experiments are conducted on four palmprint benchmarks including fourteen constrained and unconstrained palmprint datasets. The results show that our W2ML method is more robust and efficient in dealing with open-set palmprint recognition issue as compared to the state-of-the-arts, where the accuracy is increased by up to 9.11% and the Equal Error Rate (EER) is decreased by up to 2.97%.