ARABIC HANDWRITING RECOGNITION USING NEURAL NETWORK CLASSIFIER
Azlina Abdullah, B. Agal, C. Alharthi, D. Alrashidi · Journal of Fundamental and Applied Sciences · 2018
Arabic language as the main language of more than millions of people all over the world has attracted researches in the handwriting script recognition field. Arabic scripts have many difficulties which make Arabic Handwriting recognition challenging. In this paper the model proposed aimed at recognizing Arabic words the IFN / ENIT dataset. The model is an OCR using Neural Network classifier preceded by a set of preprocessing techniques includes removing spaces between words, bolding the words, baseline estimation and correction and resizing the words images. The recognition rate of the proposed model is 70%. This result showed how much the proper selection of the preprocessing steps affects the recognition rate of handwritten words. The propo sed model differs from other suggested models in Arabic handwriting field, according, the unlike preprocessing steps applied on a model and a new approach in estimating and correcting words baseline.