Facial expression change detection algorithm using optical flow technique

This study is aimed to investigate the use of optical flow techniques in detecting changes in facial expressions. A person face expression detection is very important as we can identify a person´s emotional and mental state. When communicating with people, human can identify someone´s expression accurately compared to computer. Although many approaches are tackled on this topic, there are still several drawbacks and limitations. In order to yield better results, we have applied optical flow technique to detect facial expression. In addition, we have the technique with Horn-Schunck method to optimize the results. Based on the experiment conducted, the average value represented by every facial expression can be identified, and the values are significant for future research that is focused on facial expression classification.