Many approaches to learning classifiers for structured objects (e.g., shapes) use generative models in a Bayesian framework. However, state-of-the-art classifiers for vectorial d...
We propose a fast and robust skew estimation method for scanned documents that estimates skew angles based on piecewise covering of objects, such as textlines, figures, forms, or...
In this paper we present a framework for computing depth images at interactive rates. Our approach is based on combining time-of-flight (TOF) range data with stereo vision. We use ...
In this paper we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object a...
Ahmed M. Elgammal, Ramani Duraiswami, Larry S. Dav...
— The semantic robots of the immediate future are robots that will be able to find and recognize objects in any environment. They need the capability of segmenting objects in th...
Ajay K. Mishra, Yiannis Aloimonos, Cornelia Ferm&u...