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...
Images with large areas of low texture pose significant challenge to stereo algorithms. We propose a novel segmentation based stereo scheme tuned to handle such scenes. We combine ...
Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It...
Lubor Ladicky, Christopher Russell, Pushmeet Kohli...
A general method for text localization and recognition in real-world images is presented. The proposed method is novel, as it (i) departs from a strict feed-forward pipeline and re...
Given a set of images of scenes containing different object categories (e.g. grass, roads) our objective is to discover these objects in each image, and to use this object occurre...
Anna Bosch, Arnau Oliver, Robert Marti, Xavier Mu&...