The Impact of Various Factors on the Convolutional Neural Networks Model on Arabic Handwritten Character Recognition

Abstract

Recognizing Arabic handwritten characters (AHCR) poses a significant challenge due to the intricate and variable nature of the Arabic script. However, recent advancements in machine learning, particularly through Convolutional Neural Networks (CNNs), have demonstrated promising outcomes in accurately identifying and categorizing these characters. While numerous studies have explored languages like English and Chinese, the Arabic language still requires further research to enhance its compatibility with computer systems. This study investigates the impact of various factors on the CNN model for AHCR, including batch size, filter size, the number of blocks, and the number of convolutional layers within each block. A series of experiments were conducted to determine the optimal model configuration for the AHCD dataset. The most effective model was identified with the following parameters: Batch Size (BS) = 64, Number of Blocks (NB) = 3, Number of Convolution Layers in Block (NC) = 3, and Filter Size (FS) = 64. This model achieved an impressive training accuracy of 98.29% and testing accuracy of 97.87%.