Real-time facial expression recognition system based-on geometric features

Qiqiang Zhou*, Xiangzhou Wang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

This paper presents a real-time facial expression recognition system based on geometric features. The geometric feature extraction is based on a hybrid method. This method first uses ASM to track the fiducial points coarsely and then applies a method based on threshold segmentation and deformable model to correct the mouth fiducial points due to the incorrect locations in the presence of non-linear image variations such as those caused by large facial expression changes. The geometric features extracted from the fiducial points are classified in one of the seven basic expressions by SVM classifier. The experiment shows the recognition speed can achieve about 12 fps.

Original languageEnglish
Title of host publicationProceedings of the 2012 International Conference on Information Technology and Software Engineering - Software Engineering and Digital Media Technology
Pages449-456
Number of pages8
DOIs
Publication statusPublished - 2013
Event2012 International Conference on Information Technology and Software Engineering, ITSE 2012 - Beijing, China
Duration: 8 Dec 201210 Dec 2012

Publication series

NameLecture Notes in Electrical Engineering
Volume212 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference2012 International Conference on Information Technology and Software Engineering, ITSE 2012
Country/TerritoryChina
CityBeijing
Period8/12/1210/12/12

Keywords

  • Active shape model
  • Facial expression recognition
  • Geometric feature extraction
  • Lip tracking

Fingerprint

Dive into the research topics of 'Real-time facial expression recognition system based-on geometric features'. Together they form a unique fingerprint.

Cite this