To Detect The Text Stroke In Degraded Document Images Using Canny’s Map Binarization Technique

Nowadays a very difficult is Segmentation of text from degraded document images due to the high inter/intra variation between the document background and the foreground text of different document images. In this paper, we propose a novel canny’s map binarization technique that addresses these issues by using adaptive image contrast. In the proposed system using canny’s map detector to detect text stroke and background estimate using post processing procedure for degraded document images. The adaptive image contrast is a combination of the local image contrast and the local image gradient that is tolerant to text and background variation caused by different types of document degradations. In the proposed method, an contrast map is first constructed for an input degraded image. The contrast map is then binarized into 0’s and 1’s and combined with Canny’s edge map to detect the text stroke edge pixels. The document text is segmented by a local threshold value that is estimated based on the intensities of detected text stroke edge pixels within a local window using edge detection techniques. The proposed method is simple, robust, and involves many parameter . Experiments on the Bickley diary dataset that consists of several challenging bad quality document images also show the superior performance .