Estimating varying illuminant colours in images

Lynch, Stuart Ellis (2014) Estimating varying illuminant colours in images. Doctoral thesis, University of East Anglia.

[thumbnail of 2014LynchSEPhD.pdf]
Download (3MB) | Preview


Colour Constancy is the ability to perceive colours independently of varying illumi-nation colour. A human could tell that a white t-shirt was indeed white, even under
the presence of blue or red illumination. These illuminant colours would actually make the reflectance colour of the t-shirt bluish or reddish. Humans can, to a good extent, see colours constantly. Getting a computer to achieve the same goal, with a high level of accuracy has proven problematic. Particularly if we wanted to use colour as a main cue in object recognition. If we trained a system on object colours under one illuminant and then tried to recognise the objects under another illuminant, the system would likely fail. Early colour constancy algorithms assumed that an image contains a single uniform illuminant. They would then attempt to estimate the colour
of the illuminant to apply a single correction to the entire image.
It’s not hard to imagine a scenario where a scene is lit by more than one illuminant. If we take the case of an outdoors scene on a typical summers day, we would see
objects brightly lit by sunlight and others that are in shadow. The ambient light in shadows is known to be a different colour to that of direct sunlight (bluish and
yellowish respectively). This means that there are at least two illuminant colours to be recovered in this scene. This thesis focuses on the harder case of recovering the
illuminant colours when more than one are present in a scene.
Early work on this subject made the empirical observation that illuminant colours are actually very predictable compared to surface colours. Real-world illuminants
tend not to be greens or purples, but rather blues, yellows and reds. We can think of an illuminant mapping as the function which takes a scene from some unknown
illuminant to a known illuminant. We model this mapping as a simple multiplication of the Red, Green and Blue channels of a pixel. It turns out that the set of realistic
mappings approximately lies on a line segment in chromaticity space. We propose an algorithm that uses this knowledge and only requires two pixels of the same surface
under two illuminants as input. We can then recover an estimate for the surface reflectance colour, and subsequently the two illuminants.
Additionally in this thesis, we propose a more robust algorithm that can use vary-ing surface reflectance data in a scene. One of the most successful colour constancy
algorithms, known Gamut Mappping, was developed by Forsyth (1990). He argued that the illuminant colour of a scene naturally constrains the surfaces colours that are possible to perceive. We couldn’t perceive a very chromatic red under a deep blue illuminant. We introduce our multiple illuminant constraint in a Gamut Mapping
context and are able to further improve it’s performance.
The final piece of work proposes a method for detecting shadow-edges, so that we can automatically recover estimates for the illuminant colours in and out of shadow.
We also formulate our illuminant estimation algorithm in a voting scheme, that probabilistically chooses an illuminant estimate on both sides of the shadow edge.
We test the performance of all our algorithms experimentally on well known datasets, as well as our new proposed shadow datasets.

Item Type: Thesis (Doctoral)
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Users 2593 not found.
Date Deposited: 23 Jun 2014 14:42
Last Modified: 23 Jun 2014 14:42


Downloads per month over past year

Actions (login required)

View Item View Item