Papers › AKHCRNet: Bengali Handwritten Character Recognition Using Deep Learning

AKHCRNet: Bengali Handwritten Character Recognition Using Deep Learning

29 Aug 2020arXiv:2008.12995archive 2025-07-28

Akash Roy

I propose a state of the art deep neural architectural solution for handwritten character recognition for Bengali alphabets, compound characters as well as numerical digits that achieves state-of-the-art accuracy 96.8% in just 11 epochs. Similar work has been done before by Chatterjee, Swagato, et al. but they achieved 96.12% accuracy in about 47 epochs. The deep neural 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.

Paper PDF Code

Code

theroyakash/AKHCRNet officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep Learning Ensemble Learning Handwriting Recognition Transfer Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Handwriting Recognition	BanglaLekha Isolated Dataset	AKHCRNet	Accuracy	96.8	#1 of 1	Archive leaderboard	report
Handwriting Recognition	BanglaLekha Isolated Dataset	AKHCRNet	Cross Entropy Loss	0.21612	#1 of 1	Archive leaderboard	report
Handwriting Recognition	BanglaLekha Isolated Dataset	AKHCRNet	Epochs	11	#1 of 1	Archive leaderboard	report
Transfer Learning	BanglaLekha Isolated Dataset	Chatterjee, Dutta et al.[1]	Accuracy	96.12	#1 of 1	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections