Joint discriminative feature learning for multimodal finger recognition
作者：
Highlights：
• Proposed a feature learning framework for multimodal finger recognition.
• Dominant direction vector (DDV) was formed to express informative finger features.
• Presented a discriminant feature learning (JDFL) to jointly learn and encode DDVs.
• A JDFL-based fusion algorithm was designed for multimodal feature representation.
• Extensive experiments showed the effectiveness of JDFL over the state-of-the-art.
摘要
•Proposed a feature learning framework for multimodal finger recognition.•Dominant direction vector (DDV) was formed to express informative finger features.•Presented a discriminant feature learning (JDFL) to jointly learn and encode DDVs.•A JDFL-based fusion algorithm was designed for multimodal feature representation.•Extensive experiments showed the effectiveness of JDFL over the state-of-the-art.
论文关键词：Multimodal biometrics,Feature fusion,Inter-modality,Joint feature learning
论文评审过程：Received 17 April 2020, Revised 9 July 2020, Accepted 13 October 2020, Available online 14 October 2020, Version of Record 17 October 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107704
