TY - JOUR
T1 - FLSNet
T2 - Robust Facial Landmark Semantic Segmentation
AU - Kim, Hyungjoon
AU - Kim, Hyeonwoo
AU - Rew, Jehyeok
AU - Hwang, Eenjun
N1 - Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korean Government (MSIT) under Grant 2020R1F1A1074885, and in part by the Ministry of SMEs and Startups (MSS), South Korea, through the Technology Development Program, under Grant S2796678.
Publisher Copyright:
© 2013 IEEE.
PY - 2020
Y1 - 2020
N2 - The human face is one of the most viewed visual objects in a person's life and is used for identifying a person through facial landmarks, which includes the eyes, nose, mouth, and ears that make up a face. It is also possible to communicate nonverbally through the movements of facial landmarks; that is, change of facial expression. Thus, facial landmarks play a crucial role in human-related image analysis. Automatic facial landmark detection is a challenging problem in the field of computer vision, and various studies are underway. The emergence of Deep Neural Networks has played an important role in solving difficult problems in computer vision. Semantic segmentation is a field in which images are classified into pixel units and has also developed rapidly by incorporating deep learning. In this paper, we propose a method for accurately extracting facial landmarks using semantic segmentation. First, we introduce a semantic segmentation architecture for sophisticated landmark detection, and datasets composed of facial images and ground truth pairs. Then, we suggest how improve the performance of pixel classification by adjusting the imbalance of the number of pixels according to the face landmark. Through extensive experiments, we evaluated our approach using the metrics pixel accuracy and intersection over union.
AB - The human face is one of the most viewed visual objects in a person's life and is used for identifying a person through facial landmarks, which includes the eyes, nose, mouth, and ears that make up a face. It is also possible to communicate nonverbally through the movements of facial landmarks; that is, change of facial expression. Thus, facial landmarks play a crucial role in human-related image analysis. Automatic facial landmark detection is a challenging problem in the field of computer vision, and various studies are underway. The emergence of Deep Neural Networks has played an important role in solving difficult problems in computer vision. Semantic segmentation is a field in which images are classified into pixel units and has also developed rapidly by incorporating deep learning. In this paper, we propose a method for accurately extracting facial landmarks using semantic segmentation. First, we introduce a semantic segmentation architecture for sophisticated landmark detection, and datasets composed of facial images and ground truth pairs. Then, we suggest how improve the performance of pixel classification by adjusting the imbalance of the number of pixels according to the face landmark. Through extensive experiments, we evaluated our approach using the metrics pixel accuracy and intersection over union.
KW - Facial landmark
KW - deep neural networks
KW - network architecture
KW - pixel unbalance
KW - semantic segmentation
KW - weighted feature map
UR - http://www.scopus.com/inward/record.url?scp=85087820177&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.3004359
DO - 10.1109/ACCESS.2020.3004359
M3 - Article
AN - SCOPUS:85087820177
VL - 8
SP - 116163
EP - 116175
JO - IEEE Access
JF - IEEE Access
SN - 2169-3536
M1 - 9123397
ER -