Arabic Characters Recognition by Edge Detection Using Connected Component Contour(CO3)

Abstract

  In the present paper, Arabic Character Recognition  Edge detection method based on contour and connected components  is proposed. First stage contour extraction feature is introduced to tackle the Arabic characters edge detection problem, where the aim is to extract the edge information presented in the Arabic characters, since it is crucial to understand the character content.         The second stage connected components appling for the same characters to find edge detection. The proposed approach exploits a number of connected components, which move on the character by character intensity values, to establish matrix, which represents the edge information at each pixel location .          The third stage the euclidean distance and vector angle are combined by using a saturation-based combination for edge detection using connected component Contour(CO3) for each character.  The system has been tested on MATLAB environment with satisfactory results. Given a better device the result should increase in accuracy significantly. Fonts show that the accuracy of the proposed method is 97.4% correct characters identification in average. The contour code technique seems to be very promising producing top results. The experimental results confirm the effectiveness of the proposed algorithm.