Enhancing arabic handwriting recognition through optimized deep learning frameworks

Abstract

Detecting Arabic handwriting is challenging due to letter shapes, intervening segments, and diacritical marks, despite recent advances in pattern recognition. Deep learning architectures ConvNeXt and NFNet-F5 and the meta-heuristic optimization algorithm Aquila Optimizer, inspired by eagle hunting, are used to overcome these challenges. We first review Arabic handwriting recognition literature to determine strengths, weaknesses, and future directions. Next, we describe Arabic handwriting, particularly its interconnectivity, diversity, and many diacritical symbols that make recognition difficult. The Aquila Optimizer is used to optimize CNN hyperparameters in this paper. The goal is to increase the recognition rate and reduce the computational workload. To prove the Aquila Optimizer's efficacy, the ConvNeXt and NFNet-F5 topologies are compared with and without it. The optimized ConvNeXt model has a recognition rate of 98.96%, significantly higher than comparable techniques. It also thoroughly assesses numerous meta-heuristic optimizers and highlights the Aquila Optimizer's potential to improve model performance. This work has enhanced Arabic handwriting recognition by building more precise and efficient models and provides a framework for future research on optimization and applying these models to other scripts like Persian and Urdu.