Color constancy and non-uniform illumination: Can existing algorithms work?

Bleier, M.; Rieß, Christian; Beigpour, Shida; Eibenberger, Eva; Angelopoulou, Elli; Tröger, Tobias; Kaup, André

doi:10.1109/iccvw.2011.6130331

Cited by 44 publications

(26 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many previous methods of estimating the aromaticity of the scene illumination have been based in one way or another on statistics of the RGB colors arising in an image, independent of their spatial location or frequency of occurrence in the image [27]. Structured Support Vector Machine is a relatively new tool developed primarily for machine learning that can be applied in a similar way.…”

Section: Resultsmentioning

confidence: 99%

Estimating Illumination Chromaticity Based on Structured Support Vector Machine

Tang¹,

Liu²,

Yuan³

et al. 2017

dtcse

View full text Add to dashboard Cite

Abstract. Illumination estimation is crucial to the color constancy problem. Most existing color constancy algorithms assume uniform illumination. However, in real-world scenes, this is not often the case. Thus, we propose a novel framework for estimation the colors of multiple illuminants and their spatial distribution in the scene. We formulate this problem as an illuminant color estimate is obtained independently from distinct image main-regions. We think there is only one kind of light in each main-regions. From these main-regions a robust local illumination color is computed by consensus. So we can solve the problem of multiple illumination estimation using single illuminant color constancy method. The performance if our method is evaluated on multiple data sets. Experimental results show that we can reliably process mixed illuminant scenes.

show abstract

Section: Resultsmentioning

confidence: 99%

Estimating Illumination Chromaticity Based on Structured Support Vector Machine

Tang¹,

Liu²,

Yuan³

et al. 2017

dtcse

View full text Add to dashboard Cite

show abstract

“…As a result, we have opted for the following databases in which the acquired image irradiance is approximately linear with respect to the scene radiance. To assure the linearity property, we have relied on the fact that these datasets are either generated from spectral data including reflectance [36] and illumination spectra [39] or captured in the RAW data format [20], [4]. The first of these was synthetically generated from the reflectance images of eight rural and urban scenes captured by Foster et al [36].…”

Section: Methodsmentioning

confidence: 99%

“…Despite its importance, the recovery and identification of illuminant colours in a scene has proven to be difficult task in uncontrolled real world scenes. This is mainly due to the fact that the recovery of region-wise illumination from a single image is an under-constrained problem [4]. As a result, existing methods often assume a uniform illumination power spectrum throughout the scene [5], [6].…”

Section: Introductionmentioning

confidence: 99%

“…This method is one of the few that are able to handle uncontrolled illumination in real-world environments using only input from a single image. Unlike supervised methods, such as that in [4], it does not involve complicated setups for learning prior knowledge from training data. Moreover, the method is applicable to a wide variety of natural scenes.…”

Section: Introductionmentioning

confidence: 99%

“…To do this, they employed prior knowledge about plausible illuminants to characterise the image chromaticity changes caused by illumination variation. More recently, Bleier et al [4] fused the outputs of different colour constancy algorithms after performing them on super-pixels in an image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation and Estimation of Spatially Varying Illumination

Huynh

Robles-Kelly

2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we present an unsupervised method for segmenting the illuminant regions and estimating the illumination power spectrum from a single image of a scene lit by multiple light sources. Here, illuminant region segmentation is cast as a probabilistic clustering problem in the image spectral radiance space. We formulate the problem in an optimisation setting which aims to maximise the likelihood of the image radiance with respect to a mixture model while enforcing a spatial smoothness constraint on the illuminant spectrum. We initialise the sample pixel set under each illuminant via a projection of the image radiance spectra onto a low-dimensional subspace spanned by a randomly chosen subset of spectra. Subsequently, we optimise the objective function in a coordinateascent manner by updating the weights of the mixture components, the sample pixel set under each illuminant and the illuminant posterior probabilities. We then estimate the illuminant power spectrum per pixel making use of these posterior probabilities. We compare our method with a number of alternatives for the tasks of illumination region segmentation, illumination colour estimation and colour correction. Our experiments show the effectiveness of our method as applied to one hyperspectral and three trichromatic image datasets.

show abstract

Analysis of biases in automatic white balance datasets and methods

Buzzelli

Zini

Bianco

et al. 2022

Color Research & Application

View full text Add to dashboard Cite

Annotated datasets for automatic white balance (AWB) are used for the evaluation and, when necessary, the training, of AWB methods. Relying on such datasets requires awareness of the potential bias in their content and characteristics: some methods are designed to rely on the presence of particular elements, such as human skin, while other methods learn implicit relationships between image content and light properties from training data. The dependency on these relationships makes it fundamental to understand whether the available datasets are actually representative of common application scenarios, such as the presence of human subjects, the diversity of composition, or the illumination conditions. In this paper we overview the most common datasets for Automatic White Balance, including those for single as well as multiple illuminant estimation, providing a critical analysis on their characteristics. Furthermore, we identify a number of existing methods for single illuminant estimation, as a representative pool of approaches to the problem with various levels of complexity. We investigate how the performance of these correlate to the image content of common datasets.

show abstract

Color constancy and non-uniform illumination: Can existing algorithms work?

Cited by 44 publications

References 22 publications

Estimating Illumination Chromaticity Based on Structured Support Vector Machine

Estimating Illumination Chromaticity Based on Structured Support Vector Machine

Segmentation and Estimation of Spatially Varying Illumination

Analysis of biases in automatic white balance datasets and methods

Contact Info

Product

Resources

About