Skip to main navigation Skip to search Skip to main content

Deepfake Detection Using Robust Spatial and Temporal Features from Facial Landmarks

  • Meng Li
  • , Beibei Liu
  • , Yongjian Hu
  • , Liepiao Zhang
  • , Shiqi Wang
  • South China University of Technology
  • GRGBanking
  • City University of Hong Kong

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

Abstract

Most current deepfake detectors may suffer the decrease of detection accuracy under common video processing like compression. To deal with this issue, we proposed a new way of using biometric features for robust deepfake detection. Our biometric features are derived from a set of selected facial landmarks. We first presented a metric to select robust facial landmarks, and then constructed facial feature vectors with the selected landmarks. The spatial angles and the temporal rotation angles are introduced to facilitate the construction of the SVM feature vector. In essence, we use the spatial angles and temporal rotation angles to characterize the inherent consistency of facial landmarks at both frame level and video level. Experimental results have demonstrated that our detector has the best robustness compared with 6 current methods. It also has good scores in AUC (Area Under the Receiver Operating Characteristic Curve) and detection accuracy.

Original languageEnglish
Title of host publicationProceedings - 9th International Workshop on Biometrics and Forensics, IWBF 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728195568
DOIs
StatePublished - 6 May 2021
Externally publishedYes
Event9th International Workshop on Biometrics and Forensics, IWBF 2021 - Rome, Italy
Duration: 6 May 20217 May 2021

Publication series

NameProceedings - 9th International Workshop on Biometrics and Forensics, IWBF 2021

Conference

Conference9th International Workshop on Biometrics and Forensics, IWBF 2021
Country/TerritoryItaly
CityRome
Period6/05/217/05/21

Keywords

  • Deepfake detection
  • Facial landmarks
  • Robustness
  • Spatial features
  • Temporal features

Fingerprint

Dive into the research topics of 'Deepfake Detection Using Robust Spatial and Temporal Features from Facial Landmarks'. Together they form a unique fingerprint.

Cite this