Color Constancy Adjustment using Sub-blocks of the Image

Extreme presence of the source light in digital images decreases the performance of many image processing algorithms, such as video analytics, object tracking and image segmentation. This paper presents a color constancy adjustment technique, which lessens the impact of large unvarying color areas of the image on the performance of the existing statistical based color correction algorithms. The proposed algorithm splits the input image into several non-overlapping blocks. It uses the Average Absolute Difference (AAD) value of each block’s color component as a measure to determine if the block has adequate color information to contribute to the color adjustment of the whole image. It is shown through experiments that by excluding the unvarying color areas of the image, the performances of the existing statistical-based color constancy methods are significantly improved. The experimental results of four benchmark image datasets validate that the proposed framework using Gray World, Max-RGB and Shades of Gray statistics-based methods’ images have significantly higher subjective and competitive objective color constancy than those of the existing and the state-of-the-art methods’ images.