Ancient Degraded Document/Image Restoration using Hybrid Intelligent Water Droplets Algorithm and Sauvola Thresholding Technique
Kirandeep1, Harish Kundra2
1Kirandeep, Research Scholar, Department of Computer Science, Rayat Institute of Engineering and Information Technology, Ropar, India.
2Dr. Harish Kundra, Associate Professor and HOD, Department of Computer Science, Rayat Institute of Engineering and Information Technology, Ropar, India.
Manuscript received on December 25, 2017. | Revised Manuscript received on December 27, 2017. | Manuscript published on January 30, 2017. | PP: 16-21 | Volume-6 Issue-6, January 2017. | Retrieval Number: F2939016617/2017©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A historical document that have been affected by degradation and that are of poor image quality is difficult and continues to be a focus of research in the field of image processing. So, there is the need of image restoration techniques that can improve the visibility for the human eye to directly read these documents. Document image restoration aims to improve the document image quality by reducing the noise level, which not only enhance human perception, but also facilitate the subsequent automated image processing. In this research work, we are using hybrid approach of swarm intelligence based Intelligent Water Drops Algorithm (IWD) and Sauvola Binarisation method. IWD is a nature inspired optimization algorithm that work as per the moving water droplets with soil particle obstacles in their path. Sauvola’s algorithm is an improvement of Niblack’s method which is based on the local mean and standard deviation of the image. Sauvola’s approach computes the threshold value by using the dynamic range of gray-value standard deviation. The obtained results are compared with the Sauvola, Niblack, Wolf, M1-S, M2-N, M3-W algorithms. The results are also evaluated in parametric form with PSNR and F-Measure values.
Keywords: Intelligent Water Drops Algorithm, Niblack Method, Sauvola Method, Image Enhancement, Ancient Documents