In this paper, we introduce a semi-automated segmentation method based on minimizing the Geodesic Active Contour energy incorporating a shape prior. We increase the robustness of t...
Manuel Werlberger, Thomas Pock, Markus Unger, Hors...
Tracking can be considered a two-class classification problem between the foreground object and its surrounding background. Feature selection to better discriminate object from ba...
Text extraction is an important phase in document recognition systems. In order to segment text from a page document it is necessary to detect all the possible manuscript text reg...
Rodolfo P. dos Santos, Gabriela S. Clemente, Ing R...
This paper presents a new approach to discriminative modeling for classi cation and labeling. Our method, called Boosting on Multilevel Aggregates (BMA), adds a new class of hiera...
Abstract. This paper presents an approach on high-level feature detection using a region thesaurus. MPEG-7 features are locally extracted from segmented regions and for a large set...