Abstract. We propose a probabalistic model of single source multimodal generation and show how algorithms for maximizing mutual information can find the correspondences between com...
Illumination conditions cause problems for many computer vision algorithms. Inparticular, shadows in an image can cause segmentation, tracking, or recognition algorithms to fail. I...
Graham D. Finlayson, Steven D. Hordley, Mark S. Dr...
Abstract. Quadrature filters are a well known method of low-level computer vision for estimating certain properties of the signal, as there are local amplitude and local phase. How...
We present a novel method for inferring three-dimensional shape from a collection of defocused images. It is based on the observation that defocused images are the null-space of ce...
Abstract. This paper proposes a solution for the automatic detection and tracking of human motion in image sequences. Due to the complexity of the human body and its motion, automa...