Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A practical approach to fuse shape and appearance information in a Gaussian facial action estimation framework

: Hassan, Teena; Seuss, Dominik; Wollenberg, Johannes; Garbas, Jens; Schmid, Ute


Kaminka, Gal A. ; European Association for Artificial Intelligence -EurAI-:
ECAI 2016, 22nd European Conference on Artificial Intelligence : 29 August-2 September 2016, The Hague, The Netherlands; Including Prestigious applications of intelligent systems (PAIS 2016); Proceedings
Amsterdam: IOS Press, 2016 (Frontiers in Artificial Intelligence and Applications 285)
ISBN: 978-1-61499-671-2 (Print)
ISBN: 978-1-61499-672-9 (Online)
European Conference on Artificial Intelligence (ECAI) <22, 2016, The Hague>
Conference on Prestigious Applications of Intelligent Systems (PAIS) <2016, The Hague>
Conference Paper
Fraunhofer IIS ()

In many domains of computer vision, such as medical imaging and facial image analysis, it is necessary to combine shape(geometric) and appearance (texture) information. In this paper, we describe a method for combining geometric and texture-based evidence for facial actions within a Kalman filter framework. The geometric evidence is provided by a face alignment method. The texturebased evidence is provided by a set of Support Vector Machines (SVM) for various Action Units (AU). The proposed method is a practical solution to the problem of fusing categorical probabilities within a Kalman filter based state estimation framework. A first performance evaluation on upper face AUs demonstrates the practical applicability of the proposed fusion method. The method is applicable to arbitrary imaging domains, apart from facial action estimation.