The application of a technique for labelling connected components based on the classical recursive technique is studied. The recursive approach permits labelling, counting, and cha...
In this paper we present a new framework for image segmentation using probabilistic multinets. We apply this framework to integration of regionbased and contour-based segmentation ...
We propose an hybrid and probabilistic classification of image regions belonging to scenes primarily containing natural objects, e.g. sky, trees, etc. as a first step in solving ...
This paper demonstrates how to reduce the hand labeling effort considerably by 3D information in an object detection task. In particular, we demonstrate how an efficient car detec...
Stefan Kluckner, Georg Pacher, Helmut Grabner, Hor...
We present a hierarchical system for object recognition that models neural mechanisms of visual processing identified in the mammalian ventral stream. The system is composed of ne...