Quantile Linear Algorithm for Robust Binarization of Digitalized Letters

We describe a threshold-based local algorithm for image binarization. The main idea is to compute a transition energy using pixel value differences taken from a neighborhood around the pixel of interest. By filtering the pixels with low positive and negative energy, we keep two subsets in the neighborhood, corresponding to higher positive and negative energy values. The binarization threshold is calculated using a statistical model of the high energy pixels. Experiments show that this new approach is faster and better than current state-of-the-art algorithms.