29-32
Facial Expression Recognition Based on Computer-Vision Specific Methods
Authors: Delia Mitrea, Sergiu Nedevschi, Dorian Gorgan
Number of views: 405
The automatic, computerized recognition of the emotional states based on the facial expression represents an important step towards the elimination of the communication gaps that exist between the man and the machine. The corresponding methods have multiple practical applications. The human face is the most important element able to provide useful information concerning the emotional and affective state, besides the body position. The detection of the facial expression through computer vision based methods represents an efficient solution, in both concerning accuracy and cost. In this paper we will present the most relevant methods that exist in the corresponding domain, at national al international level, then we will describe our own solution, based on the computation of potentially useful imagistic features and on the application of some performant classification algorithms. The imagistic features refer to the shape and orientation of the facial elements (eyes, eyebrows, nose, mouth, chin, brow) in the context of a certain emotional state. We also establish the relevance of the determined imagistic features and the role that various facial regions play in the process of facial expression recognition