Change search
ReferencesLink to record
Permanent link

Direct link
One Millisecond Face Alignment with an Ensemble of Regression Trees
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0003-4181-2753
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2014 (English)In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, 2014, 1867-1874 p.Conference paper (Refereed)
Abstract [en]

This paper addresses the problem of Face Alignment for a single image. We show how an ensemble of regression trees can be used to estimate the face's landmark positions directly from a sparse subset of pixel intensities, achieving super-realtime performance with high quality predictions. We present a general framework based on gradient boosting for learning an ensemble of regression trees that optimizes the sum of square error loss and naturally handles missing or partially labelled data. We show how using appropriate priors exploiting the structure of image data helps with efficient feature selection. Different regularization strategies and its importance to combat overfitting are also investigated. In addition, we analyse the effect of the quantity of training data on the accuracy of the predictions and explore the effect of data augmentation using synthesized data.

Place, publisher, year, edition, pages
IEEE Computer Society, 2014. 1867-1874 p.
, IEEE Conference on Computer Vision and Pattern Recognition. Proceedings, ISSN 1063-6919
Keyword [en]
Decision Trees, Face Alignment, Gradient Boosting, Real-Time
National Category
Computer Vision and Robotics (Autonomous Systems)
URN: urn:nbn:se:kth:diva-144334DOI: 10.1109/CVPR.2014.241ISI: 000361555601116ScopusID: 2-s2.0-84911391543ISBN: 978-147995117-8OAI: diva2:713097
27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, United States, 23 June 2014 through 28 June 2014
Swedish Foundation for Strategic Research , 6246

QC 20140423

Available from: 2014-04-20 Created: 2014-04-20 Last updated: 2015-10-26Bibliographically approved
In thesis
1. Correspondence Estimation in Human Face and Posture Images
Open this publication in new window or tab >>Correspondence Estimation in Human Face and Posture Images
2014 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Many computer vision tasks such as object detection, pose estimation,and alignment are directly related to the estimation of correspondences overinstances of an object class. Other tasks such as image classification andverification if not completely solved can largely benefit from correspondenceestimation. This thesis presents practical approaches for tackling the corre-spondence estimation problem with an emphasis on deformable objects.Different methods presented in this thesis greatly vary in details but theyall use a combination of generative and discriminative modeling to estimatethe correspondences from input images in an efficient manner. While themethods described in this work are generic and can be applied to any object,two classes of objects of high importance namely human body and faces arethe subjects of our experimentations.When dealing with human body, we are mostly interested in estimating asparse set of landmarks – specifically we are interested in locating the bodyjoints. We use pictorial structures to model the articulation of the body partsgeneratively and learn efficient discriminative models to localize the parts inthe image. This is a common approach explored by many previous works. Wefurther extend this hybrid approach by introducing higher order terms to dealwith the double-counting problem and provide an algorithm for solving theresulting non-convex problem efficiently. In another work we explore the areaof multi-view pose estimation where we have multiple calibrated cameras andwe are interested in determining the pose of a person in 3D by aggregating2D information. This is done efficiently by discretizing the 3D search spaceand use the 3D pictorial structures model to perform the inference.In contrast to the human body, faces have a much more rigid structureand it is relatively easy to detect the major parts of the face such as eyes,nose and mouth, but performing dense correspondence estimation on facesunder various poses and lighting conditions is still challenging. In a first workwe deal with this variation by partitioning the face into multiple parts andlearning separate regressors for each part. In another work we take a fullydiscriminative approach and learn a global regressor from image to landmarksbut to deal with insufficiency of training data we augment it by a large numberof synthetic images. While we have shown great performance on the standardface datasets for performing correspondence estimation, in many scenariosthe RGB signal gets distorted as a result of poor lighting conditions andbecomes almost unusable. This problem is addressed in another work wherewe explore use of depth signal for dense correspondence estimation. Hereagain a hybrid generative/discriminative approach is used to perform accuratecorrespondence estimation in real-time.

Place, publisher, year, edition, pages
Stockholm, Sweden: KTH Royal Institute of Technology, 2014. vii, 32 p.
TRITA-CSC-A, ISSN 1653-5723 ; 2014:14
National Category
Computer Vision and Robotics (Autonomous Systems)
Research subject
Computer Science
urn:nbn:se:kth:diva-150115 (URN)978-91-7595-261-1 (ISBN)
Public defence
2014-10-10, Kollegiesalen, Brinellvägen 8, KTH, Stockholm, 10:00 (English)

QC 20140919

Available from: 2014-09-19 Created: 2014-08-29 Last updated: 2014-09-19Bibliographically approved

Open Access in DiVA

fulltext(4921 kB)540 downloads
File information
File name FULLTEXT01.pdfFile size 4921 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusConference website

Search in DiVA

By author/editor
Kazemi, VahidJosephine, Sullivan
By organisation
Computer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 540 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 691 hits
ReferencesLink to record
Permanent link

Direct link