Robust and flexible landmarks detection for uncontrolled frontal faces in the wild

In this paper, we propose a robust facial landmarking scheme for frontal faces which can be applied on both controlled and uncontrolled environ-ment. This scheme is based on improvement/extension of the tree-structured facial landmarking scheme proposed by Zhu and Ramanan. The whole system is divide...

Full description

Bibliographic Details
Main Authors: Liang, A., Wang, C., Liu, Wan-Quan, Li, L.
Format: Journal Article
Published: American Institute of Mathematical Sciences 2016
Online Access:http://hdl.handle.net/20.500.11937/10316
_version_ 1848746199331373056
author Liang, A.
Wang, C.
Liu, Wan-Quan
Li, L.
author_facet Liang, A.
Wang, C.
Liu, Wan-Quan
Li, L.
author_sort Liang, A.
building Curtin Institutional Repository
collection Online Access
description In this paper, we propose a robust facial landmarking scheme for frontal faces which can be applied on both controlled and uncontrolled environ-ment. This scheme is based on improvement/extension of the tree-structured facial landmarking scheme proposed by Zhu and Ramanan. The whole system is divided into two main parts: face detection and face landmarking. In the face detection part, we proposed a Tree-structured Filter Model (TFM) combined with Viola and Jones face detector to significantly reduce the false positives while maintaining high accuracy. For the facial landmarking step, we improve the accuracy and the amount of the facial landmarks by readjusting the face structure to provide better geometrical information. Furthermore, we expand the face models into Multi-Resolution (MR) models with the adaptive land-mark approach via landmark reduction to train the face models to be able to detect facial landmarks on face images with resolutions as low as 30x30 pixels. Our experiments show that our proposed approaches can improve the accuracy of facial landmark detection on both controlled and uncontrolled environment. Furthermore, they also show that our MR models are more robust on detecting facial components (eyebrows, eyes, nose, and mouth) on very small faces.
first_indexed 2025-11-14T06:29:27Z
format Journal Article
id curtin-20.500.11937-10316
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:29:27Z
publishDate 2016
publisher American Institute of Mathematical Sciences
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-103162017-09-13T14:49:27Z Robust and flexible landmarks detection for uncontrolled frontal faces in the wild Liang, A. Wang, C. Liu, Wan-Quan Li, L. In this paper, we propose a robust facial landmarking scheme for frontal faces which can be applied on both controlled and uncontrolled environ-ment. This scheme is based on improvement/extension of the tree-structured facial landmarking scheme proposed by Zhu and Ramanan. The whole system is divided into two main parts: face detection and face landmarking. In the face detection part, we proposed a Tree-structured Filter Model (TFM) combined with Viola and Jones face detector to significantly reduce the false positives while maintaining high accuracy. For the facial landmarking step, we improve the accuracy and the amount of the facial landmarks by readjusting the face structure to provide better geometrical information. Furthermore, we expand the face models into Multi-Resolution (MR) models with the adaptive land-mark approach via landmark reduction to train the face models to be able to detect facial landmarks on face images with resolutions as low as 30x30 pixels. Our experiments show that our proposed approaches can improve the accuracy of facial landmark detection on both controlled and uncontrolled environment. Furthermore, they also show that our MR models are more robust on detecting facial components (eyebrows, eyes, nose, and mouth) on very small faces. 2016 Journal Article http://hdl.handle.net/20.500.11937/10316 10.3934/naco.2016011 American Institute of Mathematical Sciences unknown
spellingShingle Liang, A.
Wang, C.
Liu, Wan-Quan
Li, L.
Robust and flexible landmarks detection for uncontrolled frontal faces in the wild
title Robust and flexible landmarks detection for uncontrolled frontal faces in the wild
title_full Robust and flexible landmarks detection for uncontrolled frontal faces in the wild
title_fullStr Robust and flexible landmarks detection for uncontrolled frontal faces in the wild
title_full_unstemmed Robust and flexible landmarks detection for uncontrolled frontal faces in the wild
title_short Robust and flexible landmarks detection for uncontrolled frontal faces in the wild
title_sort robust and flexible landmarks detection for uncontrolled frontal faces in the wild
url http://hdl.handle.net/20.500.11937/10316