Document image binarization contributes significantly to the success of the document image analysis and recognition challenging tasks. Image quality can play an important role in addressing the issue of binarization effectiveness. In this paper, a comprehensive review of document database was presented. Review based on image from Document Image Binarization Contest (DIBCO) 2009 to 2012 consists handwritten and printed image. The best algorithm for each year is discussed and analysed. Implications of the review give the direction for future binarization approach developments.
