TY  - JOUR
AU  - Noha Elfiky
AU  - Theo Gevers
AU  - Arjan Gijsenji
AU  - Jordi Gonzalez
PY  - 2014//
TI  - Color Constancy using 3D Scene Geometry derived from a Single Image
T2  - TIP
JO  - IEEE Transactions on Image Processing
SP  - 3855
EP  - 3868
VL  - 23
IS  - 9
N2  - The aim of color constancy is to remove the effect of the color of the light source. As color constancy is inherently an ill-posed problem, most of the existing color constancy algorithms are based on specific imaging assumptions (e.g. grey-world and white patch assumption).In this paper, 3D geometry models are used to determine which color constancy method to use for the different geometrical regions (depth/layer) foundin images. The aim is to classify images into stages (rough 3D geometry models). According to stage models; images are divided into stage regions using hard and soft segmentation. After that, the best color constancy methods is selected for each geometry depth. To this end, we propose a method to combine color constancy algorithms by investigating the relation between depth, local image statistics and color constancy. Image statistics are then exploited per depth to select the proper color constancy method. Our approach opens the possibility to estimate multiple illuminations by distinguishingnearby light source from distant illuminations. Experiments on state-of-the-art data sets show that the proposed algorithm outperforms state-of-the-artsingle color constancy algorithms with an improvement of almost 50% of median angular error. When using a perfect classifier (i.e, all of the test images are correctly classified into stages); the performance of the proposed method achieves an improvement of 52% of the median angular error compared to the best-performing single color constancy algorithm.
SN  - 1057-7149
L1  - http://refbase.cvc.uab.es/files/EGG2014.pdf
UR  - http://dx.doi.org/10.1109/TIP.2014.2336545
N1  - ISE; 600.078
ID  - Noha Elfiky2014
ER  -