Arabic Handwritten Text for Person Biometric Identification: A Deep Learning Approach

TL;DR

This paper evaluates deep learning models for Arabic handwritten text recognition in biometric identification, finding EfficientNetB7 achieves the highest accuracy across multiple datasets due to its advanced architectural features.

Contribution

It compares three deep learning architectures for Arabic handwritten text recognition and demonstrates the superior performance of EfficientNetB7 with novel scaling and convolution techniques.

Findings

EfficientNetB7 achieves over 99% accuracy on all datasets.

Deep learning models significantly improve biometric identification accuracy.

EfficientNetB7's features enhance feature extraction from handwritten text.

Abstract

This study thoroughly investigates how well deep learning models can recognize Arabic handwritten text for person biometric identification. It compares three advanced architectures -- ResNet50, MobileNetV2, and EfficientNetB7 -- using three widely recognized datasets: AHAWP, Khatt, and LAMIS-MSHD. Results show that EfficientNetB7 outperforms the others, achieving test accuracies of 98.57\%, 99.15\%, and 99.79\% on AHAWP, Khatt, and LAMIS-MSHD datasets, respectively. EfficientNetB7's exceptional performance is credited to its innovative techniques, including compound scaling, depth-wise separable convolutions, and squeeze-and-excitation blocks. These features allow the model to extract more abstract and distinctive features from handwritten text images. The study's findings hold significant implications for enhancing identity verification and authentication systems, highlighting the potential of deep learning in Arabic handwritten text recognition for person biometric identification.