Decompose algorithm for thresholding degraded historical document images

Numerous techniques have previously been proposed for single-stage thresholding of document images to separate the written or printed information from the background. Although these global or local thresholding techniques have proven effective on particular subclasses of documents, none is able to produce consistently good results on the wide range of document image qualities that exist in general or the image qualities encountered in degraded historical documents. A new thresholding structure called the decompose algorithm is proposed and compared against some existing single-stage algorithms. The decompose algorithm uses local feature vectors to analyse and find the best approach to threshold a local area. Instead of employing a single thresholding algorithm, automatic selection of an appropriate algorithm for specific types of subregions of the document is performed. The original image is recursively broken down into subregions using quad-tree decomposition until a suitable thresholding method can be applied to each subregion. The algorithm has been trained using 300 historical images obtained from the Library of Congress and evaluated on 300 ‘difficult’ document images, also extracted from the Library of Congress, in which considerable background noise or variation in contrast and illumination exists. Quantitative analysis of the results by measuring text recall, and qualitative assessment of processed document image quality is reported. The decompose algorithm is demonstrated to be effective at resolving the problem in varying quality historical images.