Computing and Evaluating the Body Laughter Index
- Cite this paper as:
- Mancini M., Varni G., Glowinski D., Volpe G. (2012) Computing and Evaluating the Body Laughter Index. In: Salah A.A., Ruiz-del-Solar J., Meriçli Ç., Oudeyer PY. (eds) Human Behavior Understanding. HBU 2012. Lecture Notes in Computer Science, vol 7559. Springer, Berlin, Heidelberg
The EU-ICT FET Project ILHAIRE is aimed at endowing machines with automated detection, analysis, and synthesis of laughter. This paper describes the Body Laughter Index (BLI) for automated detection of laughter starting from the analysis of body movement captured by a video source. The BLI algorithm is described, and the index is computed on a corpus of videos. The assessment of the algorithm by means of subject’s rating is also presented. Results show that BLI can successfully distinguish between different videos of laughter, even if improvements are needed with respect to perception of subjects, multimodal fusion, cultural aspects, and generalization to a broad range of social contexts.
Unable to display preview. Download preview PDF.