Dichromatic Illumination Estimation via Hough Transforms in 3D

A new illumination-estimation method is proposed based on the dichromatic reflection model combined with Hough transform processing. Other researchers have shown that using the dichromatic reflection model under the assumption of neutral interface reflection, the color of the illuminating light can be estimated by intersecting the dichromatic planes created by two or more differently coloured regions. Our proposed method employs two Hough transforms in sequence in RGB space. The first Hough Transform creates a dichromatic plane histogram representing the number of pixels belonging to dichromatic planes created by differently coloured scene regions. The second Hough Transform creates an illumination axis histogram representing the total number of pixels satisfying the dichromatic model for each posited illumination axis. This method overcomes limitations of previous approaches that include requirements such as: that the number of distinct surfaces be known in advance, that the image be presegmented into regions of uniform colour, and that the image contain distinct specularities. Many of these methods rely on the assumption that there are sufficiently large, connected regions of a single, highly specular material in the scene. Comparing the performance of the proposed approach with previous non-training methods on a set of real images, the proposed method yields better results while requiring no prior knowledge of the image content.