We use a set of photographs showing similar scenes as a model for a single photograph this scene. A distance measure for this model is defined by correlating the neigborhoods of p...
Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which...
When magnifying a bitmapped image, we want to increase the number of pixels it covers, allowing for finer details in the image, which are not visible in the original image. Simple...
— We present a topological navigation system that is able to visually recognize the different rooms of an apartment and guide a robot between them. Specifically tailored for sma...
Abstract. Shape classification using graphs and skeletons usually involves edition processes in order to reduce the influence of structural noise. However, edition distances can no...