Optical flow for dynamic facial expression recognition.
Year: 2013
Type: dissertation
Abstract: Facial expressions are essential in human face-to-face communication because they reflect emotion and are a\nform of nonverbal communication. The face of a human has the most relevant visual characteristics of personality\nand emotion. We developed and analyzed a real-time fully automatic facial expression classification\nsystem that uses sequences of frames describing the dynamics of the expressions. This includes face detection,\nface registration using landmark points of the face, feature extraction using optical flow and finally classification\nbetween six basic expressions. Extensive experiments on the Cohn-Kanade database illustrate that this\napproach is effective for facial expression analysis. The contributions of this paper are twofold: (1) to have\na fully automated way to measure spontaneous facial expressions and (2) to incorporate optical flow to cope\nwith temporal information to enhance the overall recognition results. The results of the classification indicate\nthat the correct alignment has a significant effect on the accuracy of the system.
Author: Athanasios Psaltis
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W34508470
