Character Recognition of Arabic Handwritten Characters Using Deep Learning

Optical character recognition (OCR) is used to digitize texts in printed documents and camera images. The most basic step the OCR process recognition. Arabic language more complex than other alphabets, as cursive written characters have different spellings. Our research has improved a model for with 28 characters. Character was performed using Convolutional Neural Network models, which are accepted effective image processing Three CNN models been proposed. In study, training testing of were carried out Hijja data set. Among proposed Model C 99.3% accuracy rate obtained results that can compete studies literature.