Detecting Facial Expressions for Monitoring Patterns of Emotional Behavior

  • Authors:
  • Nikolaos Bourbakis

  • Affiliations:
  • Assistive Technologies Research Center ATRC, College of Engineering and Computer Science, Wright State University, Dayton, OH, USA

  • Venue:
  • International Journal of Monitoring and Surveillance Technologies Research
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Detecting faces and facial expressions has become a common task in human-computer interaction systems. A face-facial detection system must be able to detect faces under various conditions and extract their facial expressions. Many approaches for face detection have been proposed in the literature mainly dealing with the detection or recognition of faces in still conditions rather than the person's facial expressions and the reflecting emotional behavior. In this paper, the author describes a synergistic methodology for detecting frontal high-resolution color faces and for recognizing their facial expressions accurately in realistic conditions both indoor and outdoor, and with a variety of conditions shadows, high-lights, non-white lights. The methodology associates these facial expressions to emotional behavior. It extracts important facial features, such as eyes, eyebrows, nose, mouth lips and defines them as the primitive elements of an alphabet of a simple formal language in order to synthesize these facial features and generate emotional expressions. The main goal of this effort is to monitor emotional behavior and learn from it. Illustrative examples are also provided for proving the concept of the methodology.