Saliency measures the low-level stimuli to human vision, and serves as an alternative to semantic image understanding. This paper presents a region enhanced scale-invariant salien...
We propose a methodology for improved segmentation of images in a Bayesian framework by fusion of color, texture and gradient information. The proposed algorithm is initialized by...
Abstract. In this paper, we introduce an adaptive model-based segmentation framework, in which edge and region information are integrated and used adaptively while a solid model de...
Junzhou Huang, Xiaolei Huang, Dimitris N. Metaxas,...
Abstract. For every segmentation task, prior knowledge about the object that shall be segmented has to be incorporated. This is typically performed either automatically by using la...
Margret Keuper, Robert Bensch, Karsten Voigt, Alex...
We propose a region-based foreground object segmentation method capable of dealing with image sequences containing noise, illumination variations and dynamic backgrounds (as often...