Shades of gray and colour constancy

Colour constancy is a central problem for any visual system performing a task which requires stable perception of the colour world. To solve the colour constancy problem we estimate the colour of the prevailing light and then, at the second stage, remove it. Two of the most commonly used simple techniques for estimating the colour of the light are the Grey-World and Max-RGB algorithms. In this paper we begin by observing that this two colour constancy computations will respectively return the right answer if the average scene colour is grey or the maximum is white (and conversely, the degree of failure is proportional to the extent that these assumptions hold). We go on to ask the following question: "Would we perform better colour constancy by assuming the scene average is some shade of grey?". We give a mathematical answer to this question. Firstly, we show that Max-RGB and Grey-World are two instantiations of Minkowski norm. Secondly, that for a large calibrated dataset L(6) norm colour constancy works best overall (we have improved the performance achieved by a simple normalization based approach). Surprisingly we found performance to be similar to more elaborated algorithm.