Real-time multi-view facial landmark detector learned by the structured output SVM

Michal Uřičář, Vojtěch Franc, Diego Thomas, Akihiro Sugimoto, Václav Hlaváč

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

While the problem of facial landmark detection is getting big attention in the computer vision community recently, most of the methods deal only with near-frontal views and there is only a few really multi-view detectors available, that are capable of detection in a wide range of yaw angle (e.g. φ ∈ (−90, 90)). We describe a multi-view facial landmark detector based on the Deformable Part Models, which treats the problem of the simultaneous landmark detection and the viewing angle estimation within a structured output classification framework. We present an easily extensible and flexible framework which provides a real-time performance on the “in the wild” images, evaluated on a challenging “Annotated Facial Landmarks in the Wild” database. We show that our detector achieves better results than the current state of the art in terms of the localization error.

Original languageEnglish
Title of host publication2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479960262
DOIs
Publication statusPublished - Jul 17 2015
Externally publishedYes
Event11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2015 - Ljubljana, Slovenia
Duration: May 4 2015May 8 2015

Publication series

Name2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2015
Volume2015-January

Conference

Conference11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, FG 2015
CountrySlovenia
CityLjubljana
Period5/4/155/8/15

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Real-time multi-view facial landmark detector learned by the structured output SVM'. Together they form a unique fingerprint.

Cite this