scholarly journals Facial Landmark Detection Using Generative Adversarial Network Combined with Autoencoder for Occlusion

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Hongzhe Liu ◽  
Weicheng Zheng ◽  
Cheng Xu ◽  
Teng Liu ◽  
Min Zuo
Keyword(s):  
Feature Maps ◽  
Landmark Detection ◽  
Generative Adversarial Network ◽  
Mutual Cooperation ◽  
Facial Landmark Detection ◽  
Detection Model ◽  
Adversarial Network ◽  
Face Region ◽  
Facial Landmark ◽  
Facial Shape

The performance of the facial landmark detection model will be in trouble when it is under occlusion condition. In this paper, we present an effective framework with the objective of addressing the occlusion problem for facial landmark detection, which includes a generative adversarial network with improved autoencoders (GAN-IAs) and deep regression networks. In this model, GAN-IA can restore the occluded face region by utilizing skip concatenation among feature maps to keep more details. Meanwhile, self-attention mechanism that is effective in modeling long-range dependencies is employed to recover harmonious images for occluded faces. Deep regression networks are used to learn a nonlinear mapping from facial appearance to facial shape. Benefited from the mutual cooperation of GAN-IA and deep regression networks, a robust facial landmark detection model is achieved for the occlusion problem and the performance of the model achieves obviously improvement on challenging datasets.

scholarly journals Detecting Facial Region and Landmarks at Once via Deep Network

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5360
Author(s):  
Taehyung Kim ◽  
Jiwon Mok ◽  
Euichul Lee
Keyword(s):  
Face Detection ◽  
Detection Method ◽  
Single Shot ◽  
Landmark Detection ◽  
Facial Landmark Detection ◽  
Facial Region ◽  
Facial Landmarks ◽  
Detection Model ◽  
Facial Landmark ◽  
Shot Detection

For accurate and fast detection of facial landmarks, we propose a new facial landmark detection method. Previous facial landmark detection models generally perform a face detection step before landmark detection. This greatly affects landmark detection performance depending on which face detection model is used. Therefore, we propose a model that can simultaneously detect a face region and a landmark without performing the face detection step before landmark detection. The proposed single-shot detection model is based on the framework of YOLOv3, a one-stage object detection method, and the loss function and structure are altered to learn faces and landmarks at the same time. In addition, EfficientNet-B0 was utilized as the backbone network to increase processing speed and accuracy. The learned database used 300W-LP with 64 facial landmarks. The average normalized error of the proposed model was 2.32 pixels. The processing time per frame was about 15 milliseconds, and the average precision of face detection was about 99%. As a result of the evaluation, it was confirmed that the single-shot detection model has better performance and speed than the previous methods. In addition, as a result of using the COFW database, which has 29 landmarks instead of 64 to verify the proposed method, the average normalization error was 2.56 pixels, which was also confirmed to show promising performance.

scholarly journals Soft Facial Landmark Detection by Label Distribution Learning

2019 ◽  
Vol 33 ◽  
pp. 5008-5015 ◽  
Author(s):  
Kai Su ◽  
Xin Geng
Keyword(s):  
Model Fitting ◽  
Ground Truth ◽  
Training Set ◽  
Landmark Detection ◽  
Facial Landmark Detection ◽  
Detection Algorithms ◽  
Facial Landmark ◽  
Facial Shape ◽  
Label Distribution ◽  
Better Than

Most existing facial landmark detection algorithms regard the manually annotated landmarks as precise hard labels, therefore, the accurate annotated landmarks are essential to the training of these algorithms. However, in many cases, there exist deviations in manual annotations, and the landmarks marked for facial parts with occlusion and large poses are not always accurate, which means that the “ground truth” landmarks are usually not annotated precisely. In such case, it is more reasonable to use soft labels rather than explicit hard labels. Therefore, this paper proposes to associate a bivariate label distribution (BLD) to each landmark of an image. A BLD covers the neighboring pixels around the original manually annotated point, alleviating the problem of inaccurate landmarks. After generating a BLD for each landmark, the proposed method firstly learns the mappings from an image patch to the BLD of each landmark, and then the predicted BLDs are used in a deformable model fitting process to obtain the final facial shape for the image. Experimental results show that the proposed method performs better than the compared state-of-the-art facial landmark detection algorithms. Furthermore, the proposed method appears to be much more robust against the landmark noise in the training set than other compared baselines.

scholarly journals 2D Wasserstein Loss for Robust Facial Landmark Detection

2021 ◽  
pp. 107945
Author(s):  
Yongzhe YAN ◽  
Stefan DUFFNER ◽  
Priyanka PHUTANE ◽  
Anthony BERTHELIER ◽  
Christophe BLANC ◽  
...  
Keyword(s):  
Landmark Detection ◽  
Facial Landmark Detection ◽  
Facial Landmark

Facial Landmark Detection Under Large Pose

2018 ◽  
pp. 684-696
Author(s):  
Yangyang Hao ◽  
Hengliang Zhu ◽  
Zhiwen Shao ◽  
Xin Tan ◽  
Lizhuang Ma
Keyword(s):  
Landmark Detection ◽  
Facial Landmark Detection ◽  
Facial Landmark
Sign in / Sign up

Export Citation Format

Share Document