A Tool to Develop Arabic Handwriting Recognition System Using Genetic Approach
853
Hanan Aljuaid*, Zulkifli Mohamad*, Muhammad Sarfraz **,
*Faculty of Computer science and Info System, UTM. Malaysia, Johor Bharu, Skudai 81310
**Department of Information Science, Kuwait University. Kuwait, Safat 13060
Abstract
This paper presents a complete system to recognize off-line Arabic handwriting image and Arabic handwriting and printed text database AHPD-UTM that used to implement and test the system. That system start from preprocessing and segmentation phases that deepened on thinning the image and found the V and H projection profile until recognition phase by genetic algorithm. The genetic algorithm stand on feature extraction algorithm that defines six feature for each segment beak.
This paper presents a complete system to recognize off-line Arabic handwriting image and Arabic handwriting and printed text database AHPD-UTM that used to implement and test the system. That system start from preprocessing and segmentation phases that deepened on thinning the image and found the V and H projection profile until recognition phase by genetic algorithm. The genetic algorithm stand on feature extraction algorithm that defines six feature for each segment beak.
Keywords: Arabic characters Recognition, Genetic algorithm, Feature extraction, Arabic characters pattern, OCR, AOCR, off-line characters recognition.