Multiclass Classification of Unconstrained Handwritten Arabic Words Using Machine Learning Approaches

In this paper, we propose and describe efficient multiclass classification and recognition of unconstrained handwritten Arabic words using machine learning approaches which include the K-nearest neighbor (K-NN) clustering, and the neural network (NN). The technical details are presented in terms of three stages, namely preprocessing, feature extraction and classification. Firstly, words are segmented from input scripts and also normalized in size. Secondly, from each of the segmented words various feature extraction methods are introduced. Finally, these features are utilized to train the K-NN and the NN classifiers for classification. In order to validate the proposed techniques, extensive experiments are conducted using the K-NN and the NN. The proposed algorithms are tested on the IFN/ENIT database which contains 32492 Arabic words; the proposed algorithms give good accuracy when compared with other methods.