A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild

Abhinav DHALL, Karan Sikka, Gwen Littlewort, Roland GOECKE, Marion Bartlett

Research output: A Conference proceeding or a Chapter in BookConference contribution

5 Citations (Scopus)
2 Downloads (Pure)

Abstract

This paper proposes a method for parts-based view-invariant head pose normalisation, which works well even in difficult real-world conditions. Handling pose is a classical problem in facial analysis. Recently, parts-based models have shown promising performance for facial landmark points detection ‘in the wild’. Leveraging on the success of these models, the proposed data-driven regression framework computes a constrained normalised virtual frontal head pose. The response maps of a discriminatively trained part detector are used as texture information. These sparse texture maps are projected from non-frontal to frontal pose using block-wise structured regression. Finally, a facial kinematic shape constraint is achieved by applying a shape model. The advantages of the proposed approach are: a) no explicit dependence on the outputs of a facial parts detector and, thus, avoiding any error propagation owing to their failure; (b) the application of a shape prior on the reconstructed frontal maps provides an anatomically constrained facial shape; and c) modelling head pose as a mixture-of-parts model allows the framework to work without any prior pose information. Experiments are performed on the Multi-PIE and the ‘in the wild’ SFEW databases. The results demonstrate the effectiveness of the proposed method.
Original languageEnglish
Title of host publication2014 IEEE Winter Conference on Applications of Computer Vision
Place of PublicationPiscataway
PublisherIEEE
Pages1028-1035
Number of pages8
ISBN (Electronic)9781479949854
ISBN (Print)9781479949847
DOIs
Publication statusPublished - 2014
Event2014 IEEE Winter Conference on Applications of Computer Vision: WACV 2014 - Steamboat Springs, Steamboat Springs, United States
Duration: 24 Mar 201426 Mar 2014

Publication series

Name2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

Conference

Conference2014 IEEE Winter Conference on Applications of Computer Vision
Abbreviated titleWACV 2014
CountryUnited States
CitySteamboat Springs
Period24/03/1426/03/14

Fingerprint

Textures
Detectors
Kinematics
Experiments

Cite this

DHALL, A., Sikka, K., Littlewort, G., GOECKE, R., & Bartlett, M. (2014). A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild. In 2014 IEEE Winter Conference on Applications of Computer Vision (pp. 1028-1035). (2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014). Piscataway: IEEE. https://doi.org/10.1109/WACV.2014.6835991
DHALL, Abhinav ; Sikka, Karan ; Littlewort, Gwen ; GOECKE, Roland ; Bartlett, Marion. / A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild. 2014 IEEE Winter Conference on Applications of Computer Vision. Piscataway : IEEE, 2014. pp. 1028-1035 (2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014).
@inproceedings{2acb6e1532f4475094ed106aa2e27ef3,
title = "A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild",
abstract = "This paper proposes a method for parts-based view-invariant head pose normalisation, which works well even in difficult real-world conditions. Handling pose is a classical problem in facial analysis. Recently, parts-based models have shown promising performance for facial landmark points detection ‘in the wild’. Leveraging on the success of these models, the proposed data-driven regression framework computes a constrained normalised virtual frontal head pose. The response maps of a discriminatively trained part detector are used as texture information. These sparse texture maps are projected from non-frontal to frontal pose using block-wise structured regression. Finally, a facial kinematic shape constraint is achieved by applying a shape model. The advantages of the proposed approach are: a) no explicit dependence on the outputs of a facial parts detector and, thus, avoiding any error propagation owing to their failure; (b) the application of a shape prior on the reconstructed frontal maps provides an anatomically constrained facial shape; and c) modelling head pose as a mixture-of-parts model allows the framework to work without any prior pose information. Experiments are performed on the Multi-PIE and the ‘in the wild’ SFEW databases. The results demonstrate the effectiveness of the proposed method.",
keywords = "head-pose-estimation, parts-based-model",
author = "Abhinav DHALL and Karan Sikka and Gwen Littlewort and Roland GOECKE and Marion Bartlett",
year = "2014",
doi = "10.1109/WACV.2014.6835991",
language = "English",
isbn = "9781479949847",
series = "2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014",
publisher = "IEEE",
pages = "1028--1035",
booktitle = "2014 IEEE Winter Conference on Applications of Computer Vision",

}

DHALL, A, Sikka, K, Littlewort, G, GOECKE, R & Bartlett, M 2014, A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild. in 2014 IEEE Winter Conference on Applications of Computer Vision. 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014, IEEE, Piscataway, pp. 1028-1035, 2014 IEEE Winter Conference on Applications of Computer Vision, Steamboat Springs, United States, 24/03/14. https://doi.org/10.1109/WACV.2014.6835991

A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild. / DHALL, Abhinav; Sikka, Karan; Littlewort, Gwen; GOECKE, Roland; Bartlett, Marion.

2014 IEEE Winter Conference on Applications of Computer Vision. Piscataway : IEEE, 2014. p. 1028-1035 (2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild

AU - DHALL, Abhinav

AU - Sikka, Karan

AU - Littlewort, Gwen

AU - GOECKE, Roland

AU - Bartlett, Marion

PY - 2014

Y1 - 2014

N2 - This paper proposes a method for parts-based view-invariant head pose normalisation, which works well even in difficult real-world conditions. Handling pose is a classical problem in facial analysis. Recently, parts-based models have shown promising performance for facial landmark points detection ‘in the wild’. Leveraging on the success of these models, the proposed data-driven regression framework computes a constrained normalised virtual frontal head pose. The response maps of a discriminatively trained part detector are used as texture information. These sparse texture maps are projected from non-frontal to frontal pose using block-wise structured regression. Finally, a facial kinematic shape constraint is achieved by applying a shape model. The advantages of the proposed approach are: a) no explicit dependence on the outputs of a facial parts detector and, thus, avoiding any error propagation owing to their failure; (b) the application of a shape prior on the reconstructed frontal maps provides an anatomically constrained facial shape; and c) modelling head pose as a mixture-of-parts model allows the framework to work without any prior pose information. Experiments are performed on the Multi-PIE and the ‘in the wild’ SFEW databases. The results demonstrate the effectiveness of the proposed method.

AB - This paper proposes a method for parts-based view-invariant head pose normalisation, which works well even in difficult real-world conditions. Handling pose is a classical problem in facial analysis. Recently, parts-based models have shown promising performance for facial landmark points detection ‘in the wild’. Leveraging on the success of these models, the proposed data-driven regression framework computes a constrained normalised virtual frontal head pose. The response maps of a discriminatively trained part detector are used as texture information. These sparse texture maps are projected from non-frontal to frontal pose using block-wise structured regression. Finally, a facial kinematic shape constraint is achieved by applying a shape model. The advantages of the proposed approach are: a) no explicit dependence on the outputs of a facial parts detector and, thus, avoiding any error propagation owing to their failure; (b) the application of a shape prior on the reconstructed frontal maps provides an anatomically constrained facial shape; and c) modelling head pose as a mixture-of-parts model allows the framework to work without any prior pose information. Experiments are performed on the Multi-PIE and the ‘in the wild’ SFEW databases. The results demonstrate the effectiveness of the proposed method.

KW - head-pose-estimation

KW - parts-based-model

UR - http://www.scopus.com/inward/record.url?scp=84904646370&partnerID=8YFLogxK

U2 - 10.1109/WACV.2014.6835991

DO - 10.1109/WACV.2014.6835991

M3 - Conference contribution

SN - 9781479949847

T3 - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

SP - 1028

EP - 1035

BT - 2014 IEEE Winter Conference on Applications of Computer Vision

PB - IEEE

CY - Piscataway

ER -

DHALL A, Sikka K, Littlewort G, GOECKE R, Bartlett M. A Discriminative Parts Based Model Approach for Fiducial Points Free and Shape Constrained Head Pose Normalisation in the Wild. In 2014 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE. 2014. p. 1028-1035. (2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014). https://doi.org/10.1109/WACV.2014.6835991