期刊名称：International Journal of Engineering and Computer Science
印刷版ISSN：2319-7242
出版年度：2014
卷号：3
期号：3
页码：4062-4065
出版社：IJECS
摘要：Binarization is a process of separation of pixel values of an input image into two pixel values like white as background and black asforeground. It is an important part in image processing and the first step in many document analysis and OCR processes. Most of thebinarization techniques associate a certain intensity value called threshold. Each and every pixel of the concerned grayscale input image shouldbe compared with the threshold value and according to it, pixels are separated into two classes background and foreground. Thus thresholdplays a major role in binarization and choosing of an appropriate threshold value is an important one. It can be approached by two ways, first isthe global thresholding and second is the local thresholding techniques. The global thesholding are suitable for converting any grayscale imageinto a binary form but are inappropriate for complex documents, and degraded documents. If the illumination over the document is not uniform,it produces marginal noise along the page borders. To overcome these complexities, local thresholding techniques have been proposed fordocument binarization. These techniques estimate a different threshold for each pixel according to the grayscale information of the neighboringpixels. In this paper various local thresholding techniques are compared
