This paper presents a novel hybrid method combining genetic programming and decision tree learning. The method starts by estimating a benchmark level of reasonable accuracy, based ...
Visual sensors provide exclusively uncertain and partial knowledge of a scene. In this article, we present a suitable scene knowledge representation that makes integration and fusi...
This paper describes a novel approach to automatically recover corresponding feature points and epipolar geometry over two wide baseline frames. Our contributions consist of sever...
Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we propose a novel, general recognition framework...
We present an algorithm for performing Lambertian photometric stereo in the presence of shadows. The algorithm has three novel features. First, a fast graph cuts based method is u...