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

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 2...

Description complète

Détails bibliographiques

Auteurs principaux:	A. H. M. Shahariar Parvez, Md. Samiul Islam, Fahmid Al Farid, Tashida Yeasmin, Md. Monirul Islam, Md. Shafiul Azam, Jia Uddin, Hezerul Abdul Karim
Format:	Artigo
Langue:	Inglês
Publié:	Frontiers Media S.A. 2025-11-01
Collection:	Frontiers in Big Data
Sujets:	deep learning Bangla handwritten character recognition optical character recognition convolutional neural network Vision Transformer (ViT) VGG-16
Accès en ligne:	https://www.frontiersin.org/articles/10.3389/fdata.2025.1682984/full
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!