Preprocessing of Low-Quality Handwritten Documents Using Markov Random Fields

Abstract

Abstract-This paper presents a statistical approach to the preprocessing of degraded handwritten forms including the steps of binarization and form line removal. The degraded image is modeled by a Markov Random Field (MRF) where the hidden-layer prior probability is learned from a training set of high-quality binarized images and the observation probability density is learned on-the-fly from the gray-level histogram of the input image. We have modified the MRF model to drop the preprinted ruling lines from the image. We use the patch-based topology of the MRF and Belief Propagation (BP) for efficiency in processing. To further improve the processing speed, we prune unlikely solutions from the search space while solving the MRF. Experimental results show higher accuracy on two data sets of degraded handwritten images than previously used methods.

A local linear level set method for the binarization of degraded historical document images

“…The method was developed based on the toggle mapping morphological operator toward text localization [14]. A few other successful approaches in binarization of document images are morphological operators [15], Markov Random Fields [16], local adaptive partitioning methods [17]. Despite huge diversity in the binarization methods, It is worth noting that the proposed method is the first level set-based approach in document binarization.…”

“…Effect of the area contraction force, using(16) with K = −1 in(4). From left to right initialization, t = 0.4, t = 1.4, and t = 2…”