Arabic Handwritten Text for Person Biometric Identification: A Deep Learning Approach
Mazen Balat, Youssef Mohamed, Ahmed Heakl, Ahmed Zaky
TL;DR
This work tackles biometric identification using Arabic handwritten text by leveraging transfer learning with CNNs (ResNet50, MobileNetV2, EfficientNetB7) and a robust preprocessing/augmentation pipeline evaluated on KHATT, AHAWP, and LAMIS-MSHD. The approach shows that EfficientNetB7 achieves the highest accuracy across all datasets, reaching near 99% test accuracy, aided by compound scaling, depthwise separable convolutions, and squeeze-and-excitation blocks. Key contributions include novel preprocessing and augmentation techniques, demonstrated transfer learning benefits, and an analysis of writer count versus accuracy. The results have practical implications for identity verification and forensic document analysis, and the method can be extended to other languages and handwriting styles.
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.