Abstract: Recent research shows that in a wide variety of fields, such as computer vision, speech recognition and natural language processing, deep learning has produced noticeably promising results. Automatic recognition of handwriting is a significant component for many applications in different fields. It is a complex subject that has gained a great deal of attention in the past three decades. Research has focused on the recognition of Latin languages’ handwriting, fewer studies have been done for the Arabic language, a few problems still wait to be solved for Arabic handwritten characters. We presented a Convolutional Neural Network (CNN) model for the recognition of Arabic handwritten characters in this paper. The dataset is pre-processed before feeding it to the CNN model, it applied on database that contain 16800 of handwritten Arabic characters. The accuracy was raised to 96% as a test accuracy showing better results than other methods using the same database.

Keywords: Deep Learning, Convolutional Neural Network, Handwritten Characters, Pre-Processed.

PDF | DOI: 10.17148/IJARCCE.2020.91014

Open chat
Chat with IJARCCE