CNN-Based Anomaly Detection for Face Presentation Attack Detection with Multi-Channel Images

Yuge Zhang, Min Zhao, Longbin Yan, Tiande Gao, Jie Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Recently, face recognition systems have received significant attention, and there have been many works focused on presentation attacks (PAs). However, the generalization capacity of PAs is still challenging in real scenarios, as the attack samples in the training database may not cover all possible PAs. In this paper, we propose to perform the face presentation attack detection (PAD) with multi-channel images using the convolutional neural network based anomaly detection. Multi-channel images endow us with rich information to distinguish between different mode of attacks, and the anomaly detection based technique ensures the generalization performance. We evaluate the performance of our methods using the wide multi-channel presentation attack (WMCA) dataset.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages189-192
Number of pages4
ISBN (Electronic)9781728180670
DOIs
StatePublished - 1 Dec 2020
Event2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020 - Virtual, Macau, China
Duration: 1 Dec 20204 Dec 2020

Publication series

Name2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020

Conference

Conference2020 IEEE International Conference on Visual Communications and Image Processing, VCIP 2020
Country/TerritoryChina
CityVirtual, Macau
Period1/12/204/12/20

Keywords

  • anomaly detection
  • Face presentation attack detection
  • multi-channel CNN

Fingerprint

Dive into the research topics of 'CNN-Based Anomaly Detection for Face Presentation Attack Detection with Multi-Channel Images'. Together they form a unique fingerprint.

Cite this