Facial expression recognition using optical flow without complex feature extraction

Mu Chun Su, Yi Jwu Hsieh, De Yuan Huang

Research output: Contribution to journalArticlepeer-review

4 Scopus citations


Automatic facial expression recognition systems can be applied to many practical applications such as human-computer interaction, stress-monitoring systems, low-bandwidth videoconferencing, human behavior analysis, etc. Thus in recent years, the research of developing automatic facial expression recognition systems has attracted a lot of attention from varied fields. Many different approaches have been proposed for developing methods of automatic facial expression analysis. In this paper, an optical-flow-based approach to automatic facial expression recognition without the need of complex feature extraction is presented. The proposed system is able to automatically perform human face detection, optical flow tracking and facial expression recognition from image sequences. To recognize facial expressions we first separately train three multi-layer perceptrons (MLPs) to recognize action units involving in the eyebrows, the eyes and the mouth regions. Then individual expression network was trained to recognize five basic facial expressions based on the outputs computed from the aforementioned three MLPs. Experiments were conducted to test the performance of the proposed facial expression recognition system.

Original languageEnglish
Pages (from-to)763-770
Number of pages8
JournalWSEAS Transactions on Computers
Issue number5
StatePublished - May 2007


  • Emotion
  • Expression recognition
  • Face detection
  • Facial action units
  • Facial expression analysis


Dive into the research topics of 'Facial expression recognition using optical flow without complex feature extraction'. Together they form a unique fingerprint.

Cite this