HOS-FingerCode: Bispectral invariants based contactless multi-finger recognition system using ridge orientation and feature fusion
作者：
Highlights：
• Invariant features using ridge orientation and higher order spectra for multi-fingers.
• Investigation of fusion using six different sets of key-lines configurations.
• Investigation of feature fusion from multiple key-lines configurations.
• Performance evaluation with respect to geometrical variations of fingers.
• Feature fusion for multi-finger system with concatenation and compact bilinear pooling.
摘要
•Invariant features using ridge orientation and higher order spectra for multi-fingers.•Investigation of fusion using six different sets of key-lines configurations.•Investigation of feature fusion from multiple key-lines configurations.•Performance evaluation with respect to geometrical variations of fingers.•Feature fusion for multi-finger system with concatenation and compact bilinear pooling.
论文关键词：HOS-FingerCode,Bispectra,Ridge profile,Invariant features,Finger recognition,Compact bilinear pooling,Feature fusion
论文评审过程：Received 23 January 2021, Revised 16 January 2022, Accepted 28 March 2022, Available online 7 April 2022, Version of Record 25 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117054
