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

Authors:

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.
Funding Information
  • Kyungpook National University (2014)

This publication has 2 references indexed in Scilit: