Prototyping structural description using an inductive learning program

Character recognition systems can contribute tremendously to the advancemen t of the automation process and can improve the interaction between man and machine in many applications, including office automation, cheque verifica tion and a large variety of banking, business and data entry applications. The main theme of this paper is the automatic recognition of hand-printed A rabic characters using machine learning. Conventional methods have relied o n hand-constructed dictionaries which are tedious to construct and difficul t to make tolerant to variation in writing styles. The advantages of machin e learning are that it can generalize over the large degree of variation be tween writing styles and recognition rules can be constructed by example. T he system was tested on a sample of handwritten characters from several ind ividuals whose writing ranged from acceptable to poor in quality and the co rrect average recognition rate obtained using cross-validation was 89.65%. (C) 2000 John Wiley & Sons, Inc.