Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models

In this paper, we aim to improve one of the current state-of-the-art models for facial components detection/localization. The objectives are to increase the amount of landmark points detected and improve the landmark extraction accuracy for frontal faces. The model is following Zhu and Ramanan'...

Full description

Bibliographic Details
Main Authors: Liang, Antoni, Liu, Wan-Quan, Li, Ling, Farid, M., Le, V.
Other Authors: Prof. Michael Felsberg, Linköping University
Format: Conference Paper
Published: I E E E Computer Society 2014
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/19239
_version_ 1848749975939317760
author Liang, Antoni
Liu, Wan-Quan
Li, Ling
Farid, M.
Le, V.
author2 Prof. Michael Felsberg, Linköping University
author_facet Prof. Michael Felsberg, Linköping University
Liang, Antoni
Liu, Wan-Quan
Li, Ling
Farid, M.
Le, V.
author_sort Liang, Antoni
building Curtin Institutional Repository
collection Online Access
description In this paper, we aim to improve one of the current state-of-the-art models for facial components detection/localization. The objectives are to increase the amount of landmark points detected and improve the landmark extraction accuracy for frontal faces. The model is following Zhu and Ramanan's approach with a tree-structure. The popular AR dataset is chosen as an alternative training dataset as it provides more landmark points requested. Our extension models are compared with Zhu and Ramanan's frontal face models in terms of detection accuracy. We also compare our models with another robust facial components detector called CompASM. Our experiments show that our models can achieve lower error rate on some fiducial points by providing more landmarks, and these accurate fiducial points will provide more accurate features for some applications related to facial shapes. The impact of image colour spaces other than RGB on the proposed detector is also investigated.
first_indexed 2025-11-14T07:29:29Z
format Conference Paper
id curtin-20.500.11937-19239
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:29:29Z
publishDate 2014
publisher I E E E Computer Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-192392017-09-13T13:46:47Z Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models Liang, Antoni Liu, Wan-Quan Li, Ling Farid, M. Le, V. Prof. Michael Felsberg, Linköping University CompASM. fiducial points landmark points landmark extraction accuracy AR dataset RGB facial components detection/localization Zhu and Ramanan's frontal face models tree-structure In this paper, we aim to improve one of the current state-of-the-art models for facial components detection/localization. The objectives are to increase the amount of landmark points detected and improve the landmark extraction accuracy for frontal faces. The model is following Zhu and Ramanan's approach with a tree-structure. The popular AR dataset is chosen as an alternative training dataset as it provides more landmark points requested. Our extension models are compared with Zhu and Ramanan's frontal face models in terms of detection accuracy. We also compare our models with another robust facial components detector called CompASM. Our experiments show that our models can achieve lower error rate on some fiducial points by providing more landmarks, and these accurate fiducial points will provide more accurate features for some applications related to facial shapes. The impact of image colour spaces other than RGB on the proposed detector is also investigated. 2014 Conference Paper http://hdl.handle.net/20.500.11937/19239 10.1109/ICPR.2014.103 I E E E Computer Society restricted
spellingShingle CompASM. fiducial points
landmark points
landmark extraction accuracy
AR dataset
RGB
facial components detection/localization
Zhu and Ramanan's frontal face models
tree-structure
Liang, Antoni
Liu, Wan-Quan
Li, Ling
Farid, M.
Le, V.
Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models
title Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models
title_full Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models
title_fullStr Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models
title_full_unstemmed Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models
title_short Accurate Facial Landmarks Detection for Frontal Faces with Extended Tree-Structured Models
title_sort accurate facial landmarks detection for frontal faces with extended tree-structured models
topic CompASM. fiducial points
landmark points
landmark extraction accuracy
AR dataset
RGB
facial components detection/localization
Zhu and Ramanan's frontal face models
tree-structure
url http://hdl.handle.net/20.500.11937/19239