期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2016
卷号：4
期号：3
页码：3513
DOI：10.15680/IJIRCCE.2016.0403141
出版社：S&S Publications
摘要：Segmentation Document image binarization is a used pre-processing technique which is analysis segments text from degraded document image. In these studies we proposed a robust document image binarization techniques which is based on adaptive image contrast. Combination of local image and local image gradient is adaptive image contrast which is make liberal to text and by different type of document degradation background variation has been done. In our proposed technique text stroke edge pixel and binarized adaptive contrast map has been detected as using Canny's Algorithms. For detected text stroke edge pixel within local window the document text will be segmented by local threshold to detect high intensity. The above mentioned process has been rehashed by combining adaptive image contrast with Sobel's Edge detection technique andTotal Variation Edge Detection technique respectively. The comparison between these techniques are made on the basis of Mean square Error Values and Peak signal to noise ratio. These methods have been tested on images suffering from different types of degradations
