The Experts below are selected from a list of 2052 Experts worldwide ranked by ideXlab platform
Graham D. Finlayson - One of the best experts on this subject based on the ideXlab platform.
-
Chromatic Illumination Discrimination Ability Reveals that Human Colour Constancy Is Optimised for Blue Daylight Illuminations
PloS one, 2014Co-Authors: Bradley Pearce, Graham D. Finlayson, Stuart Crichton, Michal Mackiewicz, Anya HurlbertAbstract:The phenomenon of Colour Constancy in human visual perception keeps surface Colours constant, despite changes in their reflected light due to changing illumination. Although Colour Constancy has evolved under a constrained subset of illuminations, it is unknown whether its underlying mechanisms, thought to involve multiple components from retina to cortex, are optimised for particular environmental variations. Here we demonstrate a new method for investigating Colour Constancy using illumination matching in real scenes which, unlike previous methods using surface matching and simulated scenes, allows testing of multiple, real illuminations. We use real scenes consisting of solid familiar or unfamiliar objects against uniform or variegated backgrounds and compare discrimination performance for typical illuminations from the daylight chromaticity locus (approximately blue-yellow) and atypical spectra from an orthogonal locus (approximately red-green, at correlated Colour temperature 6700 K), all produced in real time by a 10-channel LED illuminator. We find that discrimination of illumination changes is poorer along the daylight locus than the atypical locus, and is poorest particularly for bluer illumination changes, demonstrating conversely that surface Colour Constancy is best for blue daylight illuminations. Illumination discrimination is also enhanced, and therefore Colour Constancy diminished, for uniform backgrounds, irrespective of the object type. These results are not explained by statistical properties of the scene signal changes at the retinal level. We conclude that high-level mechanisms of Colour Constancy are biased for the blue daylight illuminations and variegated backgrounds to which the human visual system has typically been exposed.
-
general ࡁ p constrained approach for Colour Constancy
International Conference on Computer Vision, 2011Co-Authors: Graham D. Finlayson, Perla Troncoso A Rey, Elisabetta TrezziAbstract:In this work we seek to advance the state of art of Colour Constancy by fusing two approaches which have recently been presented in the literature and which we believe are complementary in nature. First, we review and then extend the Minkowski p-norm approach so that it incorporates, in a mathematically rigorous way, a constraint on illumination. Second, we incorporate the idea of image derivatives into the Constrained Minkowski norm problem formulation (since there is evidence that Colour Constancy on derivatives seems to work better than on the Colours themselves). Rather than laboriously tune our algorithm by choosing the kind of derivatives we use (order and scale) we instead propose a simple combination of first and second derivative information. Across five benchmark data sets and in comparison to competing algorithms our new simple algorithm offers generally good and often best-in-class performance.
-
a combined physical and statistical approach to Colour Constancy
Computer Vision and Pattern Recognition, 2005Co-Authors: Gerald Schaefer, S. D. Hordley, Graham D. FinlaysonAbstract:Computational Colour Constancy tries to recover the Colour of the scene illuminant of an image. Colour Constancy algorithms can, in general, be divided into two groups: statistics-based approaches that exploit statistical knowledge of common lights and surfaces, and physics-based algorithms which are based on an understanding of how physical processes such as highlights manifest themselves in images. A combined physical and statistical Colour Constancy algorithm that integrates the advantages of the statistics-based Colour by correlation method with those of a physics-based technique based on the dichromatic reflectance model is introduced. In contrast to other approaches not only a single illuminant estimate is provided but a set of likelihoods for a given illumination set. Experimental results on the benchmark Simon Fraser image database show the combined method to clearly outperform purely statistical and purely physical algorithms.
-
Chromagenic Colour Constancy
2005Co-Authors: Graham D. Finlayson, S. D. Hordley, Peter MorovicAbstract:A chromagenic camera takes two pictures of each scene. The first image is taken as normal and then the second is captured with a specially chosen chromagenic filter placed in front of the camera. In contradistinction to previous cameras that have more than 3 sensors, the aim of a chromagenic camera is not to measure more degrees of freedom in reflectance. Indeed, in a chromagenic camera the RGBs are, to a first approximation, linearly related to the filtered RGBs. However, the chromagenic filter is chosen so that this relationship depends on, and varies with illumination. The chromagenic camera is sensitive to the degrees of freedom in illumination. Chromagenic Colour Constancy proceeds in two stages. In pre-processing, for each light, the relation that takes filtered to unfiltered RGBs is computed. The input to Colour Constancy processing comprises the unfiltered and filtered RGBs captured for a given scene under unknown lighting conditions. To estimate the illuminant, the filtered responses are transformed by the pre-computed relations, and then these estimates are compared to the unfiltered counterparts. The transform that best predicts the data identifies the illuminant. Remarkably, this very simple approach works as well as, or better than, all other algorithms tested.
-
Combining physical and statistical evidence for computational Colour Constancy
2005Co-Authors: Gerald Schaefer, S. D. Hordley, Graham D. FinlaysonAbstract:Colour Constancy algorithms are typically divided into physics-based techniques which exploit the physical image formation process and statistics-based method that use statistical knowledge on surfaces and lights. In this paper we introduce a combined physical and statistical algorithm for computational Colour Constancy. Estimates obtained from the statistical Colour by Correlation algorithm are integrated with those of a physics based method based on the dichromatic reflectance model. The algorithm not only provides an illuminant estimate but a complete set of likelihoods for a given set of reference lights. Recovery performance is shown to exceed that of purely statistical and purely physical algorithms.
Gerald Schaefer - One of the best experts on this subject based on the ideXlab platform.
-
a combined physical and statistical approach to Colour Constancy
Computer Vision and Pattern Recognition, 2005Co-Authors: Gerald Schaefer, S. D. Hordley, Graham D. FinlaysonAbstract:Computational Colour Constancy tries to recover the Colour of the scene illuminant of an image. Colour Constancy algorithms can, in general, be divided into two groups: statistics-based approaches that exploit statistical knowledge of common lights and surfaces, and physics-based algorithms which are based on an understanding of how physical processes such as highlights manifest themselves in images. A combined physical and statistical Colour Constancy algorithm that integrates the advantages of the statistics-based Colour by correlation method with those of a physics-based technique based on the dichromatic reflectance model is introduced. In contrast to other approaches not only a single illuminant estimate is provided but a set of likelihoods for a given illumination set. Experimental results on the benchmark Simon Fraser image database show the combined method to clearly outperform purely statistical and purely physical algorithms.
-
Combining physical and statistical evidence for computational Colour Constancy
2005Co-Authors: Gerald Schaefer, S. D. Hordley, Graham D. FinlaysonAbstract:Colour Constancy algorithms are typically divided into physics-based techniques which exploit the physical image formation process and statistics-based method that use statistical knowledge on surfaces and lights. In this paper we introduce a combined physical and statistical algorithm for computational Colour Constancy. Estimates obtained from the statistical Colour by Correlation algorithm are integrated with those of a physics based method based on the dichromatic reflectance model. The algorithm not only provides an illuminant estimate but a complete set of likelihoods for a given set of reference lights. Recovery performance is shown to exceed that of purely statistical and purely physical algorithms.
-
robust dichromatic Colour Constancy
International Conference on Image Analysis and Recognition, 2004Co-Authors: Gerald SchaeferAbstract:A novel Colour Constancy algorithm that utilises both physical and statistical knowledge is introduced. A physics-based model of image formation is combined with a statistics-based constraint on the possible scene illumination. Based on the dichromatic reflection model, the intersection of two Colour signal planes from two objects will yield the scene illuminant. However, due to noise and insufficient segmentation this approach tends not to work outside the lab. By removing those intersections that are likely to produce unstable illuminant estimates and applying an illumination constraint in form of a set of feasible reference lights the Colour Constancy algorithm presented clearly outperforms the conventional approach and provides excellent results on a benchmark set of real images.
-
ICIAR (2) - Robust Dichromatic Colour Constancy
Lecture Notes in Computer Science, 2004Co-Authors: Gerald SchaeferAbstract:A novel Colour Constancy algorithm that utilises both physical and statistical knowledge is introduced. A physics-based model of image formation is combined with a statistics-based constraint on the possible scene illumination. Based on the dichromatic reflection model, the intersection of two Colour signal planes from two objects will yield the scene illuminant. However, due to noise and insufficient segmentation this approach tends not to work outside the lab. By removing those intersections that are likely to produce unstable illuminant estimates and applying an illumination constraint in form of a set of feasible reference lights the Colour Constancy algorithm presented clearly outperforms the conventional approach and provides excellent results on a benchmark set of real images.
-
Solving for Colour Constancy using a Constrained Dichromatic Reflection Model
International Journal of Computer Vision, 2001Co-Authors: Graham D. Finlayson, Gerald SchaeferAbstract:Statistics-based Colour Constancy algorithms work well as long as there are many Colours in a scene, they fail however when the encountering scenes comprise few surfaces. In contrast, physics-based algorithms, based on an understanding of physical processes such as highlights and interreflections, are theoretically able to solve for Colour Constancy even when there are as few as two surfaces in a scene. Unfortunately, physics-based theories rarely work outside the lab. In this paper we show that a combination of physical and statistical knowledge leads to a surprisingly simple and powerful Colour Constancy algorithm, one that also works well for images of natural scenes. From a physical standpoint we observe that given the dichromatic model of image formation the Colour signals coming from a single uniformly-Coloured surface are mapped to a line in chromaticity space. One component of the line is defined by the Colour of the illuminant (i.e. specular highlights) and the other is due to its matte, or Lambertian, reflectance. We then make the statistical observation that the chromaticities of common light sources all follow closely the Planckian locus of black-body radiators. It follows that by intersecting the dichromatic line with the Planckian locus we can estimate the chromaticity of the illumination. We can solve for Colour Constancy even when there is a single surface in the scene. When there are many surfaces in a scene the individual estimates from each surface are averaged together to improve accuracy. In a set of experiments on real images we show our approach delivers very good Colour Constancy. Moreover, performance is significantly better than previous dichromatic algorithms.
Sérgio M. C. Nascimento - One of the best experts on this subject based on the ideXlab platform.
-
Robust Colour Constancy in red-green dichromats
PloS one, 2017Co-Authors: Leticia Álvaro, João M. M. Linhares, Humberto Moreira, Julio Lillo, Sérgio M. C. NascimentoAbstract:Colour discrimination has been widely studied in red-green (R-G) dichromats but the extent to which their Colour Constancy is affected remains unclear. This work estimated the extent of Colour Constancy for four normal trichromatic observers and seven R-G dichromats when viewing natural scenes under simulated daylight illuminants. Hyperspectral imaging data from natural scenes were used to generate the stimuli on a calibrated CRT display. In experiment 1, observers viewed a reference scene illuminated by daylight with a correlated Colour temperature (CCT) of 6700K; observers then viewed sequentially two versions of the same scene, one illuminated by either a higher or lower CCT (condition 1, pure CCT change with constant luminance) or a higher or lower average luminance (condition 2, pure luminance change with a constant CCT). The observers’ task was to identify the version of the scene that looked different from the reference scene. Thresholds for detecting a pure CCT change or a pure luminance change were estimated, and it was found that those for R-G dichromats were marginally higher than for normal trichromats regarding CCT. In experiment 2, observers viewed sequentially a reference scene and a comparison scene with a CCT change or a luminance change above threshold for each observer. The observers’ task was to identify whether or not the change was an intensity change. No significant differences were found between the responses of normal trichromats and dichromats. These data suggest robust Colour Constancy mechanisms along daylight locus in R-G dichromacy.
-
Effect of Scene Complexity on Colour Constancy with Real Three-Dimensional Scenes and Objects:
Perception, 2005Co-Authors: Sérgio M. C. Nascimento, Vasco M. N. De Almeida, Paulo Torrão Fiadeiro, David H. FosterAbstract:The effect of scene complexity on Colour Constancy was tested with a novel technique in which a virtual image of a real 3-D test object was projected into a real 3-D scene. Observers made discriminations between illuminant and material changes in simple and complex scenes. The extent of Colour Constancy achieved varied little with either scene structure or test-object Colour, suggesting a dominant role of local cues in determining surface-Colour judgments.
-
How temporal cues can aid Colour Constancy
Color research and application, 2000Co-Authors: David H. Foster, Kinjiro Amano, Sérgio M. C. NascimentoAbstract:Colour Constancy assessed by asymmetric simultaneous Colour matching usually reveals limited levels of performance in the unadapted eye. Yet observers can readily discriminate illuminant changes on a scene from changes in the spectral reflectances of the surfaces making up the scene. This ability is probably based on judgements of relational Colour Constancy, in turn based on the physical stability of spatial ratios of cone excitations under illuminant changes. Evidence is presented suggesting that the ability to detect violations in relational Colour Constancy depends on temporal transient cues. Because Colour Constancy and relational Colour Constancy are closely connected, it should be possible to improve estimates of Colour Constancy by introducing similar transient cues into the matching task. To test this hypothesis, an experiment was performed in which observers made surface-Colour matches between patterns presented in the same position in an alternating sequence with period 2 s or, as a control, presented simultaneously, side-by-side. The degree of Constancy was significantly higher for sequential presentation, reaching 87% for matches averaged over 20 observers. Temporal cues may offer a useful source of information for making Colour-Constancy judgements.
-
Four issues concerning Colour Constancy and relational Colour Constancy
Vision research, 1997Co-Authors: David H. Foster, Sérgio M. C. Nascimento, B.j Craven, Karina J. Linnell, Frans W. Cornelissen, Eli BrennerAbstract:Four issues concerning Colour Constancy and relational Colour Constancy are briefly considered: (1) the equivalence of Colour Constancy and relational Colour Constancy; (2) the dependence of relational Colour Constancy on ratios of cone excitations due to light from different reflecting surfaces, and the association of such ratios with von Kries' coefficient rule; (3) the contribution of chromatic edges to Colour Constancy and relational Colour Constancy; and (4) the effects of instruction and observer training. It is suggested that cognitive factors affect Colour Constancy more than relational Colour Constancy, which may be an inherently more robust phenomenon.
-
Relational Colour Constancy from invariant cone-excitation ratios
Proceedings. Biological sciences, 1994Co-Authors: David H. Foster, Sérgio M. C. NascimentoAbstract:Quantitative measurements of perceptual Colour Constancy show that human observers have a limited and variable ability to match Coloured surfaces in scenes illuminated by different light sources. Observers can, however, make fast and reliable discriminations between changes in illuminant and changes in the reflecting properties of scenes, a discriminative ability that might be based on a visual coding of spatial Colour relations. This coding could be provided by the ratios of cone-photoreceptor excitations produced by light from different surfaces: for a large class of pigmented surfaces and for surfaces with random spectral reflectances, these ratios are statistically almost invariant under changes in illumination by light from the sun and sky or from a planckian radiator. Cone-excitation ratios offer a possible, although not necessarily unique, basis for perceptual Colour Constancy in so far as it concerns Colour relations.
David H. Foster - One of the best experts on this subject based on the ideXlab platform.
-
Immediate Colour Constancy.
Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians (Optometrists), 2007Co-Authors: David H. Foster, B.j Craven, Elizabeth R. H. SaleAbstract:Colour Constancy is traditionally interpreted as the stable appearance of the Colour of a surface despite changes in the spectral composition of the illumination. When Colour Constancy has been assessed quantitatively, however, by observers making matches between surfaces illuminated by different sources, its completeness has been found to be poor. An alternative operational approach to Colour Constancy may be taken which concentrates instead on detecting the underlying chromatic relationship between the parts of a surface under changes in the illuminant. Experimentally the observer's task was to determine whether a change in the appearance of a surface was due to a change in its reflecting properties or to a change in the incident light. Observers viewed computer simulations of a row of three Mondrian patterns of Munsell chips. The centre pattern was a reference pattern illuminated by a simulated, spatially uniform daylight; one of the outer patterns was identical but illuminated by a different daylight; and the other outer pattern was equivalent but not obtainable from the centre pattern by such a change in illuminant. Different patterns and different shifts in daylight were generated in each experimental trial. The task of the observer was to identify which of the outer patterns was the result of an illuminant change. Observers made reliable discriminations of the patterns with displays of durations from several seconds to less than 200 ms, and, for one observer, with displays of 1 ms. By these measures, human observers appear capable of Colour Constancy that is extremely rapid, and probably preattentive in origin.
-
Effect of Scene Complexity on Colour Constancy with Real Three-Dimensional Scenes and Objects:
Perception, 2005Co-Authors: Sérgio M. C. Nascimento, Vasco M. N. De Almeida, Paulo Torrão Fiadeiro, David H. FosterAbstract:The effect of scene complexity on Colour Constancy was tested with a novel technique in which a virtual image of a real 3-D test object was projected into a real 3-D scene. Observers made discriminations between illuminant and material changes in simple and complex scenes. The extent of Colour Constancy achieved varied little with either scene structure or test-object Colour, suggesting a dominant role of local cues in determining surface-Colour judgments.
-
Does Colour Constancy exist
Trends in cognitive sciences, 2003Co-Authors: David H. FosterAbstract:For a stable visual world, the Colours of objects should appear the same under different lights. This property of Colour Constancy has been assumed to be fundamental to vision, and many experimental attempts have been made to quantify it. I contend here, however, that the usual methods of measurement are either too coarse or concentrate not on Colour Constancy itself, but on other, complementary aspects of scene perception. Whether Colour Constancy exists other than in nominal terms remains unclear.
-
How temporal cues can aid Colour Constancy
Color research and application, 2000Co-Authors: David H. Foster, Kinjiro Amano, Sérgio M. C. NascimentoAbstract:Colour Constancy assessed by asymmetric simultaneous Colour matching usually reveals limited levels of performance in the unadapted eye. Yet observers can readily discriminate illuminant changes on a scene from changes in the spectral reflectances of the surfaces making up the scene. This ability is probably based on judgements of relational Colour Constancy, in turn based on the physical stability of spatial ratios of cone excitations under illuminant changes. Evidence is presented suggesting that the ability to detect violations in relational Colour Constancy depends on temporal transient cues. Because Colour Constancy and relational Colour Constancy are closely connected, it should be possible to improve estimates of Colour Constancy by introducing similar transient cues into the matching task. To test this hypothesis, an experiment was performed in which observers made surface-Colour matches between patterns presented in the same position in an alternating sequence with period 2 s or, as a control, presented simultaneously, side-by-side. The degree of Constancy was significantly higher for sequential presentation, reaching 87% for matches averaged over 20 observers. Temporal cues may offer a useful source of information for making Colour-Constancy judgements.
-
Four issues concerning Colour Constancy and relational Colour Constancy
Vision research, 1997Co-Authors: David H. Foster, Sérgio M. C. Nascimento, B.j Craven, Karina J. Linnell, Frans W. Cornelissen, Eli BrennerAbstract:Four issues concerning Colour Constancy and relational Colour Constancy are briefly considered: (1) the equivalence of Colour Constancy and relational Colour Constancy; (2) the dependence of relational Colour Constancy on ratios of cone excitations due to light from different reflecting surfaces, and the association of such ratios with von Kries' coefficient rule; (3) the contribution of chromatic edges to Colour Constancy and relational Colour Constancy; and (4) the effects of instruction and observer training. It is suggested that cognitive factors affect Colour Constancy more than relational Colour Constancy, which may be an inherently more robust phenomenon.
Mark S. Drew - One of the best experts on this subject based on the ideXlab platform.
-
Exemplar-Based Colour Constancy and Multiple Illumination
2016Co-Authors: Hamid Reza, Vaezi Joze, Mark S. DrewAbstract:Abstract—Exemplar-based learning or, equally, nearest neighbour methods have recently gained interest from researchers in a variety of computer science domains because of the prevalence of large amounts of accessible data and storage capacity. In computer vision, these types of technique have been successful in several problems such as scene recognition, shape matching, image parsing, character recognition and object detection. Applying the concept of exemplar-based learning to the problem of Colour Constancy seems odd at first glance since, in the first place, similar nearest neighbour images are not usually affected by precisely similar illuminants and, in the second place, gathering a dataset consisting of all possible real-world images, including indoor and outdoor scenes and for all possible illuminant Colours and intensities, is indeed impossible. In this paper we instead focus on surfaces in the image and address the Colour Constancy problem by unsupervised learning of an appropriate model for each training surface in training images. We find nearest neighbour models for each surface in a test image and estimate its illumination based on comparing the statistics of pixels belonging to nearest neighbour surfaces and the target surface. The final illumination estimation results from combining these estimated illuminants over surfaces to generate a unique estimate. We show that it performs very well, for standard datasets, compared to current Colour Constancy algorithms, including when learning based on one image dataset is applied to tests from a different dataset. The proposed method has the advantage of overcoming multi-illuminant situations, which is not possible for most current methods since they assume the Colour of the illuminant is constant all over the image. We show a technique to overcome the multiple illuminant situation using the proposed method and test our technique on images with two distinct sources of illumination using a multiple
-
white patch gamut mapping Colour Constancy
International Conference on Image Processing, 2012Co-Authors: Hamid Reza Vaezi Joze, Mark S. DrewAbstract:The White-Patch method, one of the first Colour Constancy methods, estimates the light source Colour from the maximum response of the different Colour channels. However, it has been eclipsed by the advent of more advanced physical or statistical methods, as well as complex learning based methods. Recently, a new independent line of work claims that the simple idea of using maximum pixel values is not as naive as it seems, but can also be made to perform very well via some manipulations. The bright areas of images can include highlights and specularity as well as white surfaces or light sources, and indeed all may be helpful in the illumination estimation process. In this paper, we define the White Patch Gamut as a new extension to the Gamut Mapping Colour Constancy method, comprising the bright pixels of the image. Adding new constraints based on the possible White Patch Gamut to the standard gamut mapping constraints, a new combined method outperforms gamut mapping methods as well as other wellknown Colour Constancy methods. The new constraints that are brought to bear are powerful, and indeed can be more discriminating than those in the original gamut mapping method itself.
-
ICIP - White Patch Gamut Mapping Colour Constancy
2012 19th IEEE International Conference on Image Processing, 2012Co-Authors: Hamid Reza Vaezi Joze, Mark S. DrewAbstract:The White-Patch method, one of the first Colour Constancy methods, estimates the light source Colour from the maximum response of the different Colour channels. However, it has been eclipsed by the advent of more advanced physical or statistical methods, as well as complex learning based methods. Recently, a new independent line of work claims that the simple idea of using maximum pixel values is not as naive as it seems, but can also be made to perform very well via some manipulations. The bright areas of images can include highlights and specularity as well as white surfaces or light sources, and indeed all may be helpful in the illumination estimation process. In this paper, we define the White Patch Gamut as a new extension to the Gamut Mapping Colour Constancy method, comprising the bright pixels of the image. Adding new constraints based on the possible White Patch Gamut to the standard gamut mapping constraints, a new combined method outperforms gamut mapping methods as well as other wellknown Colour Constancy methods. The new constraints that are brought to bear are powerful, and indeed can be more discriminating than those in the original gamut mapping method itself.
-
exemplar based Colour Constancy
British Machine Vision Conference, 2012Co-Authors: Hamid Reza Vaezi Joze, Mark S. DrewAbstract:Exemplar-based learning or, equally, nearest neighbour methods have recently gained interest from researchers in a variety of computer science domains because of the prevalence of large amounts of accessible data and storage capacity. In computer vision, these types of technique have been successful in several problems such as scene recognition, shape matching, image parsing, character recognition and object detection. Applying the concept of exemplar-based learning to the problem of Colour Constancy seems odd at first glance since, in the first place, similar nearest neighbour images are not usually affected by precisely similar illuminants and, in the second place, gathering a dataset consisting of all possible real-world images, including indoor and outdoor scenes and for all possible illuminant Colours and intensities, is indeed impossible. In this paper we instead focus on surfaces in the image and address the Colour Constancy problem by unsupervised learning of an appropriate model for each training surface in training images. We find nearest neighbour models for each surface in a test image and estimate its illumination based on comparing the statistics of pixels belonging to nearest neighbour surfaces and the target surface. The final illumination estimation results from combining these estimated illuminants over surfaces to generate a unique estimate. The proposed method has the advantage of overcoming multi-illuminant situations, which is not possible for most current methods. The concept proposed here is a completely new approach to the Colour Constancy problem. We show that it performs very well, for standard datasets, compared to current Colour Constancy algorithms.
-
BMVC - Exemplar-Based Colour Constancy
Procedings of the British Machine Vision Conference 2012, 2012Co-Authors: Hamid Reza Vaezi Joze, Mark S. DrewAbstract:Exemplar-based learning or, equally, nearest neighbour methods have recently gained interest from researchers in a variety of computer science domains because of the prevalence of large amounts of accessible data and storage capacity. In computer vision, these types of technique have been successful in several problems such as scene recognition, shape matching, image parsing, character recognition and object detection. Applying the concept of exemplar-based learning to the problem of Colour Constancy seems odd at first glance since, in the first place, similar nearest neighbour images are not usually affected by precisely similar illuminants and, in the second place, gathering a dataset consisting of all possible real-world images, including indoor and outdoor scenes and for all possible illuminant Colours and intensities, is indeed impossible. In this paper we instead focus on surfaces in the image and address the Colour Constancy problem by unsupervised learning of an appropriate model for each training surface in training images. We find nearest neighbour models for each surface in a test image and estimate its illumination based on comparing the statistics of pixels belonging to nearest neighbour surfaces and the target surface. The final illumination estimation results from combining these estimated illuminants over surfaces to generate a unique estimate. The proposed method has the advantage of overcoming multi-illuminant situations, which is not possible for most current methods. The concept proposed here is a completely new approach to the Colour Constancy problem. We show that it performs very well, for standard datasets, compared to current Colour Constancy algorithms.