Fakultät Wirtschaftsinformatik und Angewandte Informatik

Angewandte Informatik / Kognitive Systeme

Kooperationsprojekt IIFOP Schmerz

Research Project "Automated Pain Detection from Video Monitoring of Facial Expressions"

July 15 2015 to May 14 2016
 
Joint project with:

  • Fraunhofer IIS, Intelligent Systems Group Electronic Imaging
    Department (Dr. Jens Garbas, Teena Hassan, Dominik Seuss)
  • Physiological Psychology (PP), Institute of Psychology University of
    Bamberg (Prof. Dr. Stefan Lautenbacher, PD Dr. Miriam Kunz)
  • Cognitive Systems Group (Prof. Dr. Ute Schmid, Michael Siebers)

 

Description

The SHORE system of Fraunhofer IIS is a highly performant system for detection of faces and analysis of facial expression with succesful applications in consumer research. In this pilot project, it will be investigated how SHORE can be applied to the identification of facial expressions of pain in a clinical context. The PP group will provide their expertise in psychological experimental research of determinants in decoding and encoding facial expressions of pain. The CogSys group will provide their expertise in standard machine learning as well as in high-level symbolical learning on structural data (e.g. ILP, grammar learning).

  • Workshop on Detection of Pain in Facial Expressions, Feb. 19 2016: Program(211.6 KB)

  

Publications

Hassan, Teena, Seuß, Dominik, Wollenberg, Johannes, Gargas, Jens, Schmid, Ute (2016). A Practical Approach to Fuse Shape and Appearance Information in a Gaussian Facial Action Estimation Framework. In: Kaminka, Gal A., Fox, Maria, Bouquet, Paolo, Hüllermeier, Eyke, Dignum, Virginia, Dignum, Frank, van Harmelen, Frank (Eds.).  22nd European Conference on Artificial Intelligence. Including Prestigious Applications of Artificial Intelligence. Proceedings. Amsterdam: IOS Press BV, p. 1812–1817.

Siebers, Michael, Schmid, Ute, Seuß, Dominik, Kunz, Miriam, Lautenbacher, Stefan (2016). Characterizing Facial Expressions By Grammars of Action Unit Sequences – A First Investigation Using ABL. Information Sciences 329, p. 866-875. DOI: 10.1016/j.ins.2015.10.007.