Recognition of Handwritten Arabic Names using Probabilistic Neural Networks

Abstract: Emancipation of the computers from the limited in space data entry tools (such as keyboards) and its possession of the ability of hearing and reading, remains an area of active research in computer science for more than four decades. During this period, the researchers have provided a considerable number of methods and algorithms for the computerization of hearing and reading in what is known as Pattern Recognition in computer science. One of these methods is the Holistic Approach, which has proved its efficiency in the fast recognition. The usage of neural networks with the holistic method has special importance, as it helps to determine the transition to the analytical method very easy. This paper presents successful recognition experiments of probabilistic neural networks to recognize holistically the most common Arabic names. This network was succeeded in recognizing a high proportion of Arabic names very quickly because it does not segment the words.

Keywords: Holistic approach, Probabilistic Neural networks, Arabic names recognition