@Article{, title={A novel Arabic words recognition system using hyperplane classifier نظام جديد للتعرف على الكلمات العربية باستخدام المصنف الفائق}, author={Mahmoud Abdegadir Khalifa and Ammar Mohammed Ali and Saif Ali Abd Alradha Alsaidi and liying Zheng and Nahla Fadel Alwan and Gadiaa Saeed Mahdi}, journal={Wasit Journal of Computer and Mathematics Science مجلة واسط لعلوم الحاسوب والرياضيات}, volume={1}, number={2}, pages={12-20}, year={2022}, abstract={The topic of exhaustive study for about past decades has been carried out in machine imitation of human reading. a small number of investigations have been accepted on the detection of cursive font writing like Arabic texts for its individual challenges and difficulty. In this work, a novel technique for automatic Arabic font recognition is proposed to demonstrate a suitable recognition rate for multi-fonts styles and multi sizes of Arabic word images. The scheme can be classified into a number of steps. First, segmenting Arabic lines into words depending on the vertical projection and dynamic threshold then we implicated each Arabic word as a class by ignoring segmenting the word into characters. Second, normalizing step, the size of Arabic word images varies from each other. The system converts the images that contribute into a new size that is divisible by "N" without remainder, to decrease the difficulty of feature extraction and recognition of the system that may allow images from different resources, Third, the feature extraction step is based on applying the ratio of vertical sliding strips as a feature. Finally, multi-class support vector machine (one versus one technique)is used as a classifier. This method was estimated on offline printed fonts, five Arabic fonts, (Andalus, Arial, Simplified Arabic, Tahoma and Traditional Arabic) were used and the average recognition rate of all fonts was 95.744%.

} }