Dark channel prior-based white point estimation for automatic white balance

Im, Jaehyun; Kim, Dae–Hee; Jung, Junghoon; Kim, Tae-Chan; Paik, Joonki

doi:10.1109/icce.2014.6775936

Cited by 4 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the object's colours do not get saturated if the image is taken under canonical light. Therefore, to retrieve the true colour of an image, a uniform distribution of light spectrum is needed to remove that colour cast so that the image exhibits its true colour under a canonical illuminant [6,7]. A considerable number of colour constancy techniques have been proposed in the literature to attain the original colour of an image [8][9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

True colour retrieval from multiple illuminant scene's image

Hussain

Sheikh-Akbari

2017

IET 3rd International Conference on Intelligent Signal Processing (ISP 2017)

View full text Add to dashboard Cite

This paper presents an algorithm to retrieve the true colour of an image captured under multiple illuminant. The proposed method uses a histogram analysis and K-means ++ clustering technique to split the input image into a number of segments. It then determines normalised average absolute difference (NAAD) for each resulting segment's colour component. If the NAAD of the segment's component is greater than an empirically determined threshold. It assumes that the segment does not represent a uniform colour area, hence the segment's colour component is selected to be used for image colour constancy adjustment. The initial colour balancing factor for each chosen segment's component is calculated using the Minkowski norm based on the principal that the average values of image colour components are achromatic. It finally calculates colour constancy adjustment factors for each image pixel by fusing the initial colour constancy factors of the chosen segments weighted by the normalised Euclidian distances of the pixel from the centroids of the selected segments. Experimental results using benchmark single and multiple illuminant image datasets, show that the proposed method's images subjectively exhibit highest colour constancy in the presence of multiple illuminant and also when image contains uniform colour areas.

show abstract