AKHCRNet: Bengali Handwritten Character Recognition Using Deep Learning

08/29/2020

∙

by   theroyakash, et al.

∙

0

∙

share

I propose a state of the art deep neural architectural solution for handwritten character recognition for Bengali alphabets, compound alphabets as well as numerical digits that achieves state-of-the-art accuracy 96.8 11 epochs. Similar work has been done before by Chatterjee, Dutta, et al. 2019 but they achieved 96.12 architecture used in that paper was fairly large considering the inclusion of the weights of the ResNet 50 model which is a 50-layer Residual Network. This proposed model achieves higher accuracy as compared to any previous work in a little number of epochs. ResNet50 is a good model trained on the ImageNet dataset, but I propose an HCR network that is trained from the scratch on Bengali characters without the "Ensemble Learning" that can outperform previous architectures.