Design of a Facial Landmark Detection System Using a Dynamic Optical Flow Approach

Bing Fei Wu, Bo Rui Chen, Chun Fei Hsu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Many facial landmark methods based on convolutional neural networks (CNN) have been proposed to achieve favorable detection results. However, the instability landmarks that occur in video frames due to CNNs are extremely sensitive to input image noise. To solve this problem of landmark shaking, this study proposes a simple and effective facial landmark detection method comprising a lightweight U-Net model and a dynamic optical flow (DOF). The DOF uses the fast optical flow to obtain the optical flow vector of the landmark and uses dynamic routing to improve landmark stabilization. A lightweight U-Net model is designed to predict facial landmarks with a smaller model size and less computational complexity. The predicted facial landmarks are further fed to the DOF approach to deal with the unstable shaking. Finally, a comparison of several common methods and the proposed detection method is made on several benchmark datasets. Experimental evaluations and analyses show that not only can the lightweight U-Net model achieve favorable landmark prediction but also the DOF stabilizing method can improve the robustness of landmark prediction in both static images and video frames. It should be emphasized that the proposed detection system exhibits better performance than others without requiring heavy computational loadings.

Original languageEnglish
Article number9422692
Pages (from-to)68737-68745
Number of pages9
JournalIEEE Access
Volume9
DOIs
StatePublished - 2021

Keywords

  • dynamic routing
  • Facial landmark detection
  • fast optical flow
  • landmark stabilization
  • lightweight U-Net

Fingerprint

Dive into the research topics of 'Design of a Facial Landmark Detection System Using a Dynamic Optical Flow Approach'. Together they form a unique fingerprint.

Cite this