Direct binarization a quality-and-time efficient binarization strategy

Abstract

Most of the best known binarization algorithms have grayscale conversion as a pre-processing step, before applying the binarization strategy itself. Many algorithms produce equally good or even better quality images if fed with only one component of the image, instead of its gray-scale/luminance equivalent. The time-gain here is obtained in avoiding the several floating-point calculations in converting a RGB-color image into grayscale. More than 60 binarization algorithms were tested using "real-world" images.