Effective Process to Remove Broken Lines Effect from Degraded Document Images Using MATLAB Algorithm
Megha Paul · 2015
Most offline handwrit ing recognition approaches proceed by segmenting characters into s maller p ieces wh ich are recognized differently. The result of recognition is composition of the individually recognized parts. Inspired by results in cognitive researchers have begun to focus on holistic wo rd recognition approaches. Here we p resent an effective approach for degraded documents, which is motivated by the fact that for severely degraded documents a segmentation of words into characters will produce very poor results. The poor quality of origina l documents does not allow us to recognize them with h igh accuracy - our goal here is to p roduce transcriptions that will allow successful retrieval of images, which has been shown to be feasible even in such noisy environments. We believe that this is the first systematic approach to recognizing words in historical manuscripts with extensive experiments. Our experiment is to clear the degraded documents using filtering approach. We will use wiener filter for removing the broken lines from different images using wiener filter algorith m. We will also imp lement this design using GUI for selecting different images from self-created data-base.