https://github.com/dibyatanoy/Bengali-Handwritten-Character-Recognition-Using-Convolutional-Neural-Networks

Implementation of convolutional neural networks (CNNs) of increasing complexity for classification of handwritten Bengali characters. The deepest network achieves 94.2% accuracy on test data, compared to 85.96% reported on the latest paper using CNNs for Bengali OCR.
https://github.com/dibyatanoy/Bengali-Handwritten-Character-Recognition-Using-Convolutional-Neural-Networks

Last synced: 30 days ago
JSON representation

Implementation of convolutional neural networks (CNNs) of increasing complexity for classification of handwritten Bengali characters. The deepest network achieves 94.2% accuracy on test data, compared to 85.96% reported on the latest paper using CNNs for Bengali OCR.

• Host: GitHub
• URL: https://github.com/dibyatanoy/Bengali-Handwritten-Character-Recognition-Using-Convolutional-Neural-Networks
• Owner: dibyatanoy
• License: mit
• Created: 2016-05-29T09:35:03.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2017-08-19T15:14:55.000Z (almost 7 years ago)
• Last Synced: 2024-02-18T13:31:13.034Z (4 months ago)
• Language: Jupyter Notebook
• Size: 258 KB
• Stars: 72
• Watchers: 7
• Forks: 37
• Open Issues: 4

Lists

• awesome-bangla - Bengali Handwritten OCR with Convolutional NN