Adaptive document image binarization

A new method is presented for adaptive document image binarization, where t he page is considered as a collection of subcomponents such as text, backgr ound and picture. The problems caused by noise, illumination and many sourc e type-related degradations are addressed. Two new algorithms are applied t o determine a local threshold for each pixel. The performance evaluation of the algorithm utilizes test images with ground-truth, evaluation metrics f or binarization of textual and synthetic images, and a weight-based ranking procedure for the final result presentation. The proposed algorithms were tested with images including different types of document components and deg radations. The results were compared with a number of known techniques in t he literature. The benchmarking results show that the method adapts and per forms well in each case qualitatively and quantitatively. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved .