As a discriminative biometric modality, palmprint accommodates two attributes of soft biometrics, namely chirality and gender. Our study reveals that the false matching of a pair of palmprint templates from two identities could be possible if their representations are mirror-insensitive or gender-insensitive, despite the palmprint images have significant distinctive appearances. This could seriously impair the accuracy performance of the palmprint recognition systems. As a remedy, the useful knowledge learned from the classification of soft palmprint attributes, namely chirality and gender, is transferred to palmprint recognition, which improves the accuracy of palmprint-based identity recognition. To be specific, this paper pre-trains a shared-weight multi-task network with soft palmprint attributes under transfer learning paradigm. The pre-trained network is then transferred to the down-stream identity recognition task. Several shared-weight architectures are explored and examined to determine the suitable model. Extensive experiments demonstrate that the proposed method can effectively avoid the false matching between the templates of different chiralities / genders. The proposed method can be applied to other biometric modalities, where their associated soft biometrics can be exploited for performance gain. The related codes will be released as soon as possible if the paper is accepted. The link is https://github.com/1119231393/Multi-task-Pre-training-with-Soft-Biometrics-for-Transfer-learning-Palmprint-Recognition.
Bibliographical noteFunding Information:
This research was funded by the National Natural Science Foundation of China (61866028), Technology Innovation Guidance Program Project (Special Project of Technology Cooperation, Science and Technology Department of Jiangxi Province) (20212BDH81003), and Open Foundation of Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition (ET201680245, TX201604002).
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Artificial Intelligence