In this paper we introduce a novel image descriptor enabling accurate object categorization even with linear models. Akin to the popular attribute descriptors, our feature vector ...
In this work we seek to move away from the traditional paradigm for 2D object recognition whereby objects are identified in the image as 2D bounding boxes. We focus instead on: i...
Person recognition using facial features, e.g., mug-shot images, has long been used in identity documents. However, due to the widespread use of web-cams and mobile devices embedde...
This paper presents a 3D approach to multi-view object class detection. Most existing approaches recognize object classes for a particular viewpoint or combine classifiers for a f...
Perfusion data are dynamic medical image data which characterize the regional blood flow in human tissue. These data bear a great potential in medical diagnosis, since diseases can...
Steffen Oeltze, Helmut Doleisch, Helwig Hauser, ...