Video-based emotion identification using face alignment and support vector machines

Gil Jin Jang, Ahra Jo, Jeong Sik Park

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

1 Scopus citations

Abstract

This abstract introduces an efficient method for identifying various facial expressions from image inputs. To recognize the emotions of the facial expressions, a number of facial feature points were extracted. The extracted feature points are then transformed to 49-dimensional feature vectors which are robust to scale and translational variations, and the facial emotions are recognized by a support vector machine (SVM). Based on the experimental results, SVM performance was obtained by 50.8% for 6 emotion classification, and 78.0% for 3 emotions.

Original languageEnglish
Title of host publicationHAI 2014 - Proceedings of the 2nd International Conference on Human-Agent Interaction
PublisherAssociation for Computing Machinery
Pages285-286
Number of pages2
ISBN (Electronic)9781450330350
DOIs
StatePublished - 29 Oct 2014
Event2nd International Conference on Human-Agent Interaction, HAI 2014 - Tsukuba, Japan
Duration: 29 Oct 201431 Oct 2014

Publication series

NameHAI 2014 - Proceedings of the 2nd International Conference on Human-Agent Interaction

Conference

Conference2nd International Conference on Human-Agent Interaction, HAI 2014
Country/TerritoryJapan
CityTsukuba
Period29/10/1431/10/14

Keywords

  • Active Shape Model
  • Emotion Recognition
  • Support Vector Machine.

Fingerprint

Dive into the research topics of 'Video-based emotion identification using face alignment and support vector machines'. Together they form a unique fingerprint.

Cite this