Journal
IEEE ACCESS
Volume 9, Issue -, Pages 68737-68745Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3077479
Keywords
Heating systems; Optical flow; Training; Predictive models; Face recognition; Computational modeling; Stability analysis; Facial landmark detection; lightweight U-Net; fast optical flow; dynamic routing; landmark stabilization
Categories
Funding
- Ministry of Science and Technology, Taiwan [MOST 108-2221-E-009-123-MY2, MOST 108-2221-E-032-039-MY2]
Ask authors/readers for more resources
A simple and effective facial landmark detection method was proposed in this study, utilizing a lightweight U-Net model and dynamic optical flow (DOF) for improved landmark stability. Experimental results demonstrate that the method performs well in predicting facial landmarks in both static images and video frames.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available