Distribution alignment for cross-device palmprint recognition

With the development of IoT and mobile devices, cross-device palmprint recognition is becoming an emerging research topic in multimedia for its great application potential. Due to the diverse character-istics of different devices, e.g.resolution or artifacts caused by post-processing, cross-device palmprint recognition remains a challenging problem. In this paper, we make efforts to improve cross-device palm -print recognition in two aspects: (1) we put forward a novel distribution-based loss to narrow the repre-sentation gap across devices, and (2) we establish a new cross-device benchmark based on existing palm -print recognition datasets. Different from many recent studies that only utilize instance-level or pairwise-level information between devices, the proposed progressive target distribution loss (PTD loss) uses the distributional information. Moreover, we establish a progressive target mechanism that will be dynamically updated during training, making the optimization easier and smoother. The newly established bench-mark contains more samples and more types of IoT devices than previous benchmarks, which can facil-itate cross-device palmprint research. Extensive comparisons on several benchmarks reveal that: (1) our method outperforms other cross-device biometric recognition approaches significantly; (2) our method presents superior performance compared to SOTA competitors on several general palmprint recognition benchmarks; Code and data are openly available at https://kaizhao.net/palmprint . (c) 2022 Elsevier Ltd. All rights reserved.