A Joint Pixel and Feature Alignment Framework for Cross-dataset Palmprint Recognition

TL;DR

This paper introduces a novel joint pixel and feature alignment framework for cross-dataset palmprint recognition, effectively reducing dataset gaps and improving accuracy in real-world scenarios involving different data sources.

Contribution

The paper proposes a new two-stage alignment framework combining style transfer and domain adaptation for cross-dataset palmprint recognition, outperforming existing methods.

Findings

Achieved up to 28.10% improvement in cross-dataset identification accuracy.

Reduced EER by up to 4.69% in cross-dataset verification.

Demonstrated state-of-the-art performance on multiple palmprint benchmarks.

Abstract

Deep learning-based palmprint recognition algorithms have shown great potential. Most of them are mainly focused on identifying samples from the same dataset. However, they may be not suitable for a more convenient case that the images for training and test are from different datasets, such as collected by embedded terminals and smartphones. Therefore, we propose a novel Joint Pixel and Feature Alignment (JPFA) framework for such cross-dataset palmprint recognition scenarios. Two stage-alignment is applied to obtain adaptive features in source and target datasets. 1) Deep style transfer model is adopted to convert source images into fake images to reduce the dataset gaps and perform data augmentation on pixel level. 2) A new deep domain adaptation model is proposed to extract adaptive features by aligning the dataset-specific distributions of target-source and target-fake pairs on feature level. Adequate experiments are conducted on several benchmarks including constrained and unconstrained palmprint databases. The results demonstrate that our JPFA outperforms other models to achieve the state-of-the-arts. Compared with baseline, the accuracy of cross-dataset identification is improved by up to 28.10% and the Equal Error Rate (EER) of cross-dataset verification is reduced by up to 4.69%. To make our results reproducible, the codes are publicly available at http://gr.xjtu.edu.cn/web/bell/resource.