Document Image Binarization Using Image Segmentation Algorithm in Parallel Environment
Department of Computer Engineering, GES’s R.H.Sapat College of Engineering, Nashik-422005, Maharashtra, India
International Journal of Computer Science and Mobile Computing, Vol.4, Issue.1, 360-366, 2015
@article{ekhande2015document,
title={Document Image Binarization Using Image Segmentation Algorithm in Parallel Environment},
author={Ekhande, Prakash N and Rumane, Sharad A and Ahire, Mayur A},
year={2015}
}
The Segmentation of text from poorly degraded document images is a very hard due to the high intravariation between the document background and the foreground text of different document images. The algorithms used for Image processing take more time for execution on a single core processor. Graphics Processing Unit (GPU) is becoming most popular due to their speed, programmability, less price and more integral 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 as well as on single core processor. In this system we provide 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.
February 23, 2015 by hgpu
