摘要：This paper presents a novel new technique based on feature extraction and on dynamic cursor sizing for the recognition of Arabic Text. The most challenging area in Arabic OCR (AOCR) research is the segmentation of words into their sub-words and their individual characters. Several rules are defined that govern the size and movement of the cursor through each segment. The features obtained from each segment are termed strokes and each segment is defined by a number of strokes where each stroke is defined mainly in terms of a sequence of directions. The basic concept followed here is a logical, dynamically sized cursor that is used to "travel" through a text image of one word at a time while extracting features of strokes. The strokes obtained are then "pieced" back together to be classified into character classes based on a knowledge base and eventual recognition of characters is achieved. The results demonstrate that the technique is successful.
