Abstract: To do segmentation from badly degraded document images is very tough and challenging tasks. It is due to the high inter/intravariation between the document background and the foreground text of different document images. we propose document image binarization technique that focuses on these issues by using adaptive image contrast. It Combine local image contrast and the local image gradient for construct adaptive contrast map that is tolerant to text and background variation caused by different types of document degradations. In the proposed technique, we first constructed adaptive contrast map for an input degraded document image. And then image segmentation algorithm is used to identify the text stroke edge pixels. The document text is further segmented by a local threshold that is estimated based on the intensities of detected text stroke edge pixels within a local window. The proposed method is simple, robust and involves minimum parameter tuning. This system was tested on three public datasets that were used in the recent. Those datasets are Document Image Binarization Contest (DIBCO) 2009 & 2011 and Handwritten Document Image Binarization Contest (H-DIBCO) 2010 and thus come up with an accuracies of 93.5%, 87.8% and 92.03%, respectively that are significantly higher than or close to that of the best-performing methods reported in the three contests.

Keywords: Adaptive Image Contrast, Document Analysis, Document Image Processing, Degraded Document Image Binarization, Pixel Classification.