This research aims to use geometrical features and neural networks to automatically recognize (read) off-line handwritten Arabic words. The nature of handwritten Arabic characters and hence the problems that could be faced when automatically (optically) recognizing them are discussed. This research concentrates on the feature extraction process, i.e. extraction of the main geometrical features of each of the extracted handwritten Arabic characters. A complete system able to recognize Arabic handwritten characters of only a single writer is proposed and discussed. A review of some of the previous trials in the field of off line handwritten Arabic character recognition is included. The system first attempts to remove some of the variations found in the images that do not affect the identity of the handwritten word (slant correction, slope correction, and baseline estimation). Next, the system codes the skeleton of tlie word so that feature information about the lines in the skeleton is extracted (segmentation and feature extraction). The features include locating endpoints, junctions, turning points, loops, generating frames (segmentation step), and detecting strokes. These features are then passed on to the recognition system for recognition. The character classification is achieved in this research using a feedforward error back propagation neural network. An 69.7 percent recognition rate has been achieved for the character frames of data.
Arabic characters, scaling, segmentation, handwritten characters, feature extraction, and back propagation neural networks.
All articles published by Studies in Informatics and Control (SIC) are published in accordance with the terms and conditions of the Creative Commons Attribution License (CC BY-NC-SA 4.0).