Abstract: Recovering of text from badly degraded document images is a very difficult task due to the very high inter/intra-variation between the document background and the foreground text of different document images. In this paper, we propose a robust document image binarization technique that addresses these issues by using inversion gray scale image contrast. The Inversion image contrast is a done by first converting the input image to invert image and then finding the contrast of the inverted image to differentiate text and background variation caused by different types of document degradations. In the proposed technique, an adaptive contrast map is first constructed for an input degraded document image. The contrast map is then converted to grayscale image so as to clearly identify the text stroke from background and foreground 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. Several challenging bad quality document images also showthe superior performance of our proposed method, compared with other techniques.