Exemplar-Based Colour Constancy and Multiple Illumination
نویسندگان
چکیده
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 multipleilluminant colour constancy dataset. The concept proposed here is a completely new approach to the colour constancy problem and provides a simple learning-based framework.
منابع مشابه
Exemplar-Based Colour Constancy
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 recognit...
متن کاملThe asymmetries of colour constancy as determined through illumination discrimination using tuneable LED light sources
reveals " blue " bias for colour constancy in real and simulated scenes. On calculating metamer sets for spectrally tunable LED illuminators. Are colour constancy mechanisms biased for typical illuminations? AIC 2013. Abstract The light reflected from object surfaces changes with the spectral content of the illumination. Despite these changes, the human visual system tends to keep the colours o...
متن کاملColour constancy in diurnal and nocturnal hawkmoths.
Diurnal and nocturnal hawkmoths have been shown to use colour vision for flower discrimination. Here, we present evidence that the nocturnal hawkmoth Deilephila elpenor and the diurnal hawkmoth Macroglossum stellatarum also have colour constancy. Colour constancy was shown in D. elpenor in two multiple-choice experiments with five different bluish colour patches under white and blue illuminatio...
متن کاملChromatic Illumination Discrimination Ability Reveals that Human Colour Constancy Is Optimised for Blue Daylight Illuminations
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 environme...
متن کاملSpatial and temporal aspects of chromatic adaptation and their functional significance for colour constancy
Illumination in natural scenes changes at multiple temporal and spatial scales: slow changes in global illumination occur in the course of a day, and we encounter fast and localised illumination changes when visually exploring the non-uniform light field of three-dimensional scenes; in addition, very long-term chromatic variations may come from the environment, like for example seasonal changes...
متن کامل