Sciweavers

Share
ICVS
2009
Springer

Increasing the Robustness of 2D Active Appearance Models for Real-World Applications

10 years 2 days ago
Increasing the Robustness of 2D Active Appearance Models for Real-World Applications
Abstract. This paper presents an approach to increase the robustness of Active Appearance Models (AAMs) within the scope of humanrobotinteraction. Due to unknown environments with changing illumination conditions and different users, which may perform unpredictable head movements, standard AAMs suffer from a lack of robustness. Therefore, this paper introduces several methods to increase the robustness of AAMs. In detail, we optimize the shape model to certain applications by using genetic algorithms. Furthermore, a modified retinex-filter to reduce the influence of illumination is presented. These approaches are finally combined with an adaptive parameter fitting approach, which can handle bad initializations. We obtain very promising results of experiments evaluating the IMM face database [1]. Key words: Active Appearance Model, Genetic Algorithm, Retinexfilter, Illumination, Optimization
Ronny Stricker, Christian Martin, Horst-Michael Gr
Added 26 May 2010
Updated 26 May 2010
Type Conference
Year 2009
Where ICVS
Authors Ronny Stricker, Christian Martin, Horst-Michael Gross
Comments (0)
books