Paper Details: Downloads: 781
Serial Number: P1121132693
Title: Comparison of Five Thinning Methods on the Arabic IFN/ENIT Database
Authors: Atallah AL-Shatnawi and Khairuddin Omar and Ahmed Zeki
Abstract: Thinning “Skeletonization” is a very crucial stage in the Arabic Character Recognition (ACR) system. It simplifies the text shape and reduces the amount of data that needs to be handled and it is usually used as a pre-processing stage for recognition and storage systems. The skeleton of Arabic text can be used for: baseline detection, character segmentation, and features extraction, and ultimately supporting the classification. In this paper, five of the state of the art thinning algorithms are selected and implemented. The five algorithms are: SPTA, Zhang-Suen parallel thinning algorithm, Voronoi- based thinning algorithm, thinning and skeletonization based morphological operation algorithms. The five selected algorithms are applied on the IFN/ENIT dataset. The results obtained by the five methods are discussed and analyzed against the IFN/ENIT dataset based on preserving shape and the text connectivity, preventing spurious tails, maintaining one pixel width skeleton and avoiding the necking problem as well as running time efficiently. In addition to that some performance measurement for checking text connectivity, spurious tails and calculating the stroke thickness are proposed and carried out.
Keywords: Thinning, Skeleton, Arabic Character Recognition, SPTA, Zhang-Suen, Voronoi-based, morphological, Text connectivity.
Journal/Conference: International Journal of Artificial Intelligence and Machine Learning
Volume: 14
Issue: 1
Submission Date: 8/10/2011 12:00:00 AM
Review Date: 6/10/2013 12:00:00 AM
Publishing Date: 2/4/2014 12:00:00 AM
Article Downloads: 781
Download:

Facebook