Department of Computer Science Technische Universitaet Muenchen
Home People Teaching Research Publications Info Sitemap
About | Research

Research Interest: Image Processing and Computer Vision, Pattern Recognition, Human Robot Interactions, Model Based Analysis of Human Faces, Age and Gender Classification
Appearance Model: This technique describes an approach to face recognition as a two step process: 1) modelling an appearance model for the face image, 2) applying PCA to resulting normalized extracted face. The novelty lies not only in generation of appearance models which uses the explicit approach for shape and texture but also the combined use of the aforementioned techniques The result is an algorithm that is more robust against illumination and shape variances. Moreover it reduces the amount of texture up to 12% of the image texture instead of considering whole face image. Experiments have been performed on Cohn Kanade facial database using ten subjects for training and seven subjects for experimentation. This produced quite excellent results in experiments for images with and without facial expressions. Only two out of 28 images were falsely recognized in case of neutral expression. Face recognition using PCA is fast and efficient to use, while the extracted AAM could be further used for facial expressions recognition and tracking. This combination is simple to model and apply in real time.

Computer Science IX | Technische Universität München