https://jjcit.org/paper/133 10.5455/jjcit.71-1615204606 Ahmad T. Al-Taani*,Sadeem T. Ahmad Residual networks,Deep learning,Deep neural networks,Arabic handwritten characters,Characters recognition 17 7366 2091 8-Mar.-2021 8-May-2021 22-May-2021 This study proposes the use of Residual Neural Networks (ResNets) to recognize Arabic offline isolated handwritten characters including Arabic digits. ResNets is a deep learning approach which showed effectiveness in many applications more than conventional machine learning approaches. The proposed approach consists of three main phases: pre-processing phase, training the ResNet on the training set and testing the trained ResNet on the datasets. The evaluation of the proposed approach is performed on three available datasets: MADBase, AIA9K and AHCD. The proposed approach achieved accuracies of 99.8%, 99.05% and 99.55% on these datasets, respectively. It also achieved a validation accuracy of 98.9% on the constructed dataset based on the three datasets.