Segmentation of text from badly degraded document images is a very challenging task due to the high inter/Intra variation between the document background and the foreground text of different document images. Image processing and pattern recognition algorithms take more time for execution on a single-core processor. Graphics Processing Unit (GPU) is more popular now-a-days due to their speed, programmability, low cost and more inbuilt execution cores in it. The main goal of this research work is to make binarization faster for recognition of a large number of degraded document images on GPU. In this system, we provide a new image segmentation algorithm that each pixel in the image has its own threshold proposed. We are doing parallel work on a window of m*n size and extract object pixel of text stroke of that window. 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