PERFORMANCE EVALUATION OF QUANTITATIVE METRICS ON ANCIENT TEXT DOCUMENTS USING MIGT
N. V. Krishna Rao · 2015
In the present world scenario Optical Character Recognition (OCR) has wide variety of applications in the text document image analysis for recognizing individual characters of any language. Digitizing the old documents is a tough job for preserving the essence of the documents to the coming eras. In this paper we are summarizing different image quantitative metrics for estimating the loss of information from the image after cleaning the noisy image by using anyone of the local or non-local thresholding techniques. The quality evaluations are made on 40 Telugu and English text documents after cleaning the documents with Modifies Iterative Global Threshold (MIGT) approach.