This paper describes a comprehensive approach to extract a common feature set from the image sequences. We use simple features which are easily extracted from a 3D wireframe model ...
Zahid Riaz, Christoph Mayer, Michael Beetz, Bernd ...
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3...
Recognition of complex activities from surveillance video requires detection and temporal ordering of its constituent "atomic" events. It also requires the capacity to ro...
Abstract. Quality of segmentations obtained by 3D Active Appearance Models (AAMs) crucially depends on underlying training data. MRI heart data, however, often come noisy, incomple...
We address the issue of segmenting multiple textured objects in presence of a background texture. The proposed technique is based on Geodesic Active Contour (GAC) and can segment m...