Skip to content

akshaybahadur21/Devanagiri-Recognizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

11 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

Devanagiri Recognition ๐Ÿ‡ฎ๐Ÿ‡ณ

This code helps you classify different alphabets of hindi language (Devanagiri) using Convnets

Code Requirements ๐Ÿฆ„

You can install Conda for python which resolves all the dependencies for machine learning.

Description ๐Ÿ•‰๏ธ

This code successfully recognizes hindi characters.

Technique โš™๏ธ

I have used convolutional neural networks. I am using Tensorflow as the framework and Keras API for providing a high level of abstraction.

Architecture ๐Ÿ—๏ธ

  1. CONV2D
  2. MAXPOOL
  3. CONV2D
  4. MAXPOOL
  5. FC
  6. Softmax
  7. Classification

Notes ๐Ÿ—’๏ธ

  1. You can go for additional conv layers.
  2. Add regularization to prevent overfitting.
  3. You can add additional images to the training set for increasing the accuracy.

Python Implementation ๐Ÿ‘จโ€๐Ÿ”ฌ

  1. Dataset- DHCD (Devnagari Character Dataset)
  2. Images of size 32 X 32
  3. Convolutional Network Support added.

Results ๐Ÿ“Š

Execution ๐Ÿ‰

To run the code, type python Dev-Rec.py

python Dev-Rec.py

About

A Hindi Alphabet classifier for humans ๐Ÿ‡ฎ๐Ÿ‡ณ

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages