Isolated Arabic handwritten words recognition using EHD and HOG methods

<span>Handwriting recognition is a growing field of study in computer vision, artificial intelligence and pattern technology aimed to recognizing texts handwritings hefty amount produced official documents paper works by institutes or governments. Using distinguish make these accessible approachable the goal efforts. Moreover, text has accomplished practically major progress many domains such as security sector e-government structure more. A system for text’s handwriting was presented here relied on edge histogram descriptor (EHD), orientated gradients (HOG) features extraction support vector machine (SVM) classifier proposed this paper. HOG EHD give an optimal Arabic hand-written extracting directional properties text. Besides that, SVM most common learning that obtaining essential classification results within various kernel functions. The experimental evaluation carried out handwritten images from IESK-ArDB database using HOG, work provides 85% rate.</span>