Skip to content

Bangla Handwritten Character Recognition System Using a Deep Convolutional Neural Network

License

Notifications You must be signed in to change notification settings

risal-shefin/Bangla-Handwritten-Character-Recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Bangla-Handwritten-Character-Classification

"train.ipynb" is for training the model. It uses "csv_loader.py" to load the dataset and "Model.py" to load the model. "draw_and_detect.py" takes mouse input and predicts the character using the trained model.

The model has obtained 97.82% validation accuracy and 97.3% testing accuracy on the CMATERdb dataset (231 character class) and 96.18% validation accuracy and 96.13% testing accuracy on the Ekush dataset (122 character class).

Paper Link

https://ieeexplore.ieee.org/document/9733479

Releases

No releases published

Packages

No packages published