One millisecond face alignment with an ensemble of regression trees

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 pre...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2014 IEEE Conference on Computer Vision and Pattern Recognition S. 1867 - 1874
Hauptverfasser: Kazemi, Vahid, Sullivan, Josephine
Format: Tagungsbericht Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2014
Schlagworte:
Alignment
Boosting
Computer vision
Decision Trees
Estimates
Face
Face Alignment
Gradient Boosting
Landmarks
Pattern recognition
Real-Time
Regression
Regression tree analysis
Regularization
Shape
Training
Training data
Trees
Vectors
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2014.241