Assessing Binarization Techniques for Document Images

Abstract

Image binarization is a technique widely used for documents as monochromatic documents claim for far less space for storage and computer bandwidth for network transmission than their color or even grayscale equivalent. Paper color, texture, aging, translucidity, kind and color of ink used in handwritting, printing process, digitalization process, etc., are some of the factors that affect binarization. No algorithm is good enough to be a winner in the binarization of all kinds of documents. This paper presents a methodology to assess the performance of binarization algorithms for a wide variety of text documents, allowing a judicious quantitative choice of the best algorithms and their parameters.