Title :
A system for Arabic character recognition
Author :
Hosseini, Habib Mir Mohamad ; Bouzerdoum, Abdesselam
Author_Institution :
Dept. of Electr. & Electron. Eng., Adelaide Univ., SA, Australia
fDate :
29 Nov-2 Dec 1994
Abstract :
In this paper, a method for automatic recognition of isolated characters is presented. In this system, the character matrix is circularly scanned, and the number of ON pixels around each circle is obtained and saved in a vector. A feedforward neural network is trained by backpropagation to recognize these vectors. In this method, even when the character is rotated around its centroid, or shifted within the matrix, it can still be recognized. The recognition rate with some noise and random rotations for isolated Arabic and Persian characters is about 91%
Keywords :
backpropagation; document image processing; feedforward neural nets; optical character recognition; Arabic character recognition; ON pixels; Persian characters; backpropagation; character matrix; character rotation; feedforward neural network; isolated character recognition; noise; random rotations; recognition rate; training; vector; Application software; Backpropagation; Character recognition; Feature extraction; Feedforward neural networks; Neural networks; Optical character recognition software; Optical computing; Optical noise; Writing;
Conference_Titel :
Intelligent Information Systems,1994. Proceedings of the 1994 Second Australian and New Zealand Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-7803-2404-8
DOI :
10.1109/ANZIIS.1994.396937
