Software Based Affective Smile Estimation

Student thesis: Master Thesis and HD Thesis

  • Tomas Fuchs Bøttern
4. term, Medialogy, Master (Master Programme)
This thesis investigated if a computer could be programmed to interpret and reason the human smile with the same accuracy and understanding as that of humans. Research revealed that attempts at extracting meaning from facial features in Computer Vision had not been attempted from the point of view of the computer. Two testing phases were devised that provided an average smile rating based on answers given by test subjects. For test phase one the computer had a 50% success ratio of correctly rating the smile conveyed in pictures. In test phase two the computer rated the smile at the same level as the test subjects. The computer was able to understand and rate smiles that were conveyed with visual distinct features, whereas ubiquitous smiles could not be rated.
This thesis covered the following terms, Affective Computing, The Facial Action Coding System, Action Units and Emotional Intelligence. Understanding and rating a smile could only be conducted from visually distinct smiles, whereas when gaze was the predominant visual factor, the computer could not rate accordingly.
Publication date24 May 2012
Number of pages108


ID: 63305475