期刊名称:Journal of Theoretical and Applied Information Technology
印刷版ISSN:1992-8645
电子版ISSN:1817-3195
出版年度:2015
卷号:82
期号:3
出版社:Journal of Theoretical and Applied
摘要: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.
关键词:Thresholding Techniques; Digitization; Evaluation; Optical Character Recognition; Document Image Analysis