Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network
Facial landmarks represent prominent feature points on the face that can be used as anchor points in many face-related tasks. So far, a lot of research has been done with the aim of achieving efficient extraction of landmarks from facial images. Employing a large number of feature points for landmar...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/7/2253 |
id |
doaj-a37d96cff05c4db3a91e329b88926bb7 |
---|---|
record_format |
Article |
spelling |
doaj-a37d96cff05c4db3a91e329b88926bb72020-11-25T01:44:36ZengMDPI AGApplied Sciences2076-34172020-03-01107225310.3390/app10072253app10072253Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection NetworkHyeon-Woo Kim0Hyung-Joon Kim1Seungmin Rho2Eenjun Hwang3School of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, KoreaDepartment of Software, Sejong University, Seoul 05006, KoreaSchool of Electrical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, KoreaFacial landmarks represent prominent feature points on the face that can be used as anchor points in many face-related tasks. So far, a lot of research has been done with the aim of achieving efficient extraction of landmarks from facial images. Employing a large number of feature points for landmark detection and tracking usually requires excessive processing time. On the contrary, relying on too few feature points cannot accurately represent diverse landmark properties, such as shape. To extract the 68 most popular facial landmark points efficiently, in our previous study, we proposed a model called EMTCNN that extended the multi-task cascaded convolutional neural network for real-time face landmark detection. To improve the detection accuracy, in this study, we augment the EMTCNN model by using two convolution techniques—dilated convolution and CoordConv. The former makes it possible to increase the filter size without a significant increase in computation time. The latter enables the spatial coordinate information of landmarks to be reflected in the model. We demonstrate that our model can improve the detection accuracy while maintaining the processing speed.https://www.mdpi.com/2076-3417/10/7/2253facial landmark extractionconvolutional neural networkscascaded structureface detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hyeon-Woo Kim Hyung-Joon Kim Seungmin Rho Eenjun Hwang |
spellingShingle |
Hyeon-Woo Kim Hyung-Joon Kim Seungmin Rho Eenjun Hwang Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network Applied Sciences facial landmark extraction convolutional neural networks cascaded structure face detection |
author_facet |
Hyeon-Woo Kim Hyung-Joon Kim Seungmin Rho Eenjun Hwang |
author_sort |
Hyeon-Woo Kim |
title |
Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network |
title_short |
Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network |
title_full |
Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network |
title_fullStr |
Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network |
title_full_unstemmed |
Augmented EMTCNN: A Fast and Accurate Facial Landmark Detection Network |
title_sort |
augmented emtcnn: a fast and accurate facial landmark detection network |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-03-01 |
description |
Facial landmarks represent prominent feature points on the face that can be used as anchor points in many face-related tasks. So far, a lot of research has been done with the aim of achieving efficient extraction of landmarks from facial images. Employing a large number of feature points for landmark detection and tracking usually requires excessive processing time. On the contrary, relying on too few feature points cannot accurately represent diverse landmark properties, such as shape. To extract the 68 most popular facial landmark points efficiently, in our previous study, we proposed a model called EMTCNN that extended the multi-task cascaded convolutional neural network for real-time face landmark detection. To improve the detection accuracy, in this study, we augment the EMTCNN model by using two convolution techniques—dilated convolution and CoordConv. The former makes it possible to increase the filter size without a significant increase in computation time. The latter enables the spatial coordinate information of landmarks to be reflected in the model. We demonstrate that our model can improve the detection accuracy while maintaining the processing speed. |
topic |
facial landmark extraction convolutional neural networks cascaded structure face detection |
url |
https://www.mdpi.com/2076-3417/10/7/2253 |
work_keys_str_mv |
AT hyeonwookim augmentedemtcnnafastandaccuratefaciallandmarkdetectionnetwork AT hyungjoonkim augmentedemtcnnafastandaccuratefaciallandmarkdetectionnetwork AT seungminrho augmentedemtcnnafastandaccuratefaciallandmarkdetectionnetwork AT eenjunhwang augmentedemtcnnafastandaccuratefaciallandmarkdetectionnetwork |
_version_ |
1725027631645065216 |