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.
Jupyter NotebookMIT
Stargazers
- acarafatUC Riverside
- aowalUMass Amherst
- arijitxHyderabad
- d1xlord@rubrikinc
- debanjanxyAccenture Operations | IIT Bombay
- DenisSergeevitch
- doxakisMontréal
- drupaltr
- faysalhaque@RedQ
- gangooteli
- git-vince
- go2chayanSpotify
- halumzCefalo
- hmcyrus
- ieee820Hua Data Technology Co.,Ltd
- md-k-sarker
- merin83Orbit
- minemerajRWTH Aachen University
- mirshahriar@klikit
- mrgoodboyUnited States
- neelflash07Arista Networks
- noprom
- PraggieNew Delhi
- qigaoBeijing China
- rahatm1@google
- sahashuvoEnosis Solutions Bangladesh Ltd.
- samuelcesc@learndHQ
- shakkhor@bKash
- srdg
- sudarshaanaJukto Digital
- tarexSaipan, CNMI, USA
- wk23415
- xxfeng2016beijing
- yeahia2508Senior Engineer at bKash
- Zahid2008
- ZoeyMiao