A proposed method for document image binarization based on bit plane slicing

Abstract

Document image binarization has not been an easy task in the area of historical document restoration accounting to the difficulty in choosing a threshold value when the document has noises due to say, its degradation, ageing of the paper, other unwanted impurities, background images, bleed-through, and so on. Also, in case of handwritten documents there could be inconsistency in the darkness of the letters. Though many algorithms have been proposed for Document image binarization, there has not been an effective algorithm which can efficiently binarize all kinds of documents. In this paper we propose a method to perform document image binarization using bit-plane slicing. The proposed method is deployed based on the rule of divide-and-conquer. As per this technique, the 8 bit planes of the gray image are extracted and processed separately, at the end of which, the results are combined to give the final binarized output.