What does this research mean for the field?

A VGG-Like convolutional neural network achieves 99.61% accuracy in recognizing Arabic-derived handwritten letters, outperforming ResNet and LeNet architectures and demonstrating the superiority of modern deep architectures for this task. Novelty: ClaimNovelty.CONFIRMATORY. Consensus alignment: ConsensusAlignment.NEUTRAL.

March 29, 2026Open Access

Recognition of Arabic Derived Handwritten Letters using a VGG-like Convolutional Neural Network

Key Points

The aim is to evaluate and compare the effectiveness of different convolutional neural network architectures for recognizing Arabic-derived letters.
Utilized a new dataset of 55440 scanned images of Arabic-derived letters.
Implemented three CNN architectures: LeNet, simplified ResNet, and VGG-Like.
Applied data augmentation techniques to increase the dataset.
Trained models for up to 40 epochs with early stopping after 5 epochs without improvement.
VGG-Like model achieved the highest validation accuracy of 99.61%.
ResNet followed closely with a validation accuracy of 98.98%.
LeNet performed with a lower accuracy of 96.43%.
Modern and deep architectures offered better accuracy and robustness for character classification.

Abstract

Due to its complexity, the Arabic language and its extensions build a fertile field of research in the field of artificial intelligence in general and optical character recognition (OCR) specifically. There are several languages that use the Arabic alphabet in their manuscripts. These languages innovated new letters to pronounce sounds not found in the Arabic language. These letters are called 'Arabic-derived letters'. To enrich the Arabic language, we can use these letters to know the true pronunciation of intrusive words in the Arabic language. This article deals with the Arabic-derived letters (ADL) dataset. It is a new dataset that consists of 55440 scanned images of papers written by 30 participants of different ages, with a data augmentation technique to increase the number of images. This study aims to evaluate and compare the effectiveness of different convolutional neural network architectures for ADL recognition, focusing on accuracy, robustness, and generalization capability. Three architectures were implemented: LeNet, a simplified ResNet model with residual blocks, and a deep VGG-Like network. Training was limited to 40 epochs with early stopping after 5 epochs without improvement. Experimental results show that the VGG-Like model achieves the best performance with 99.61% accuracy in validation, closely followed by ResNet with an accuracy of 98.98%. In contrast, LeNet performs less efficiently by 96.43%. These results clearly demonstrate that modern and deep architectures provide better accuracy and robustness for the classification of handwritten characters.

Read Full Paperexternally

Demander à l'IA

Bookmark

View Full Paper

Cite This Study

Mouhssine El Atillah (Wed,) studied this question.

synapsesocial.com/papers/69c8c15ade0f0f753b39bbd7 https://doi.org/https://doi.org/10.21123/2411-7986.5254

Demander à l'IA

Bookmark

View Full Paper