DOG-ADTCP: A new feature descriptor for protection of face identification system

作者：

Highlights：

• A modified version of DOG is proposed to eliminate noise and illumination.

• DOG-ADTCP descriptor obtains more spatial information in four directions.

• Proposed descriptor is robust and rotational invariant.

• Performance is evaluated on many standard face anti-spoofing datasets.

摘要

•A modified version of DOG is proposed to eliminate noise and illumination.•DOG-ADTCP descriptor obtains more spatial information in four directions.•Proposed descriptor is robust and rotational invariant.•Performance is evaluated on many standard face anti-spoofing datasets.

论文关键词：Face anti-spoofing,Angle directional ternary co-relation pattern,Texture analysis,Rotational invariant,Presentation attack detection,Difference of Gaussian (DOG)

论文评审过程：Received 4 September 2020, Revised 1 March 2022, Accepted 7 April 2022, Available online 12 April 2022, Version of Record 20 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117207