AUTHOR=Shahariar Parvez A. H. M. , Samiul Islam Md. , Al Farid Fahmid , Yeasmin Tashida , Islam Md. Monirul , Azam Md. Shafiul , Uddin Jia , Abdul Karim Hezerul 

TITLE=Enhancing Bangla handwritten character recognition using Vision Transformers, VGG-16, and ResNet-50: a performance analysis

JOURNAL=Frontiers in Big Data

VOLUME=Volume 8 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2025.1682984

DOI=10.3389/fdata.2025.1682984

ISSN=2624-909X

ABSTRACT=Bangla Handwritten Character Recognition (BHCR) remains challenging due to complex alphabets, and handwriting variations. In this study, we present a comparative evaluation of three deep learning architectures—Vision Transformer (ViT), VGG-16, and ResNet-50—on the CMATERdb 3.1.2 dataset comprising 24,000 images of 50 basic Bangla characters. Our work highlights the effectiveness of ViT in capturing global context and long-range dependencies, leading to improved generalization. Experimental results show that ViT achieves a state-of-the-art accuracy of 98.26%, outperforming VGG-16 (94.54%) and ResNet-50 (93.12%). We also analyze model behavior, discuss overfitting in CNNs, and provide insights into character-level misclassifications. This study demonstrates the potential of transformer-based architectures for robust BHCR and offers a benchmark for future research.