HindiHnadWritingRecognizer

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

Description

This code successfully recognizes hindi characters when user make characters in front of camera.

Code Requirements

1. you can install Conda for python which resolves all the dependencies for machine learning.
2. install tensorflow , in conda -> $ conda install tensorflow
3. install keras , in conda -> $ conda install keras
4. install opencv , in conda -> $ conda install opencv
5. handWritingRecognition.py require data set data.csv for training and test
6. application.py require devanagari_model.h5 model for classify the characters.

Technique Used

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

Architecture

CONV2D --> MAXPOOL --> CONV2D --> MAXPOOL -->FC -->Softmax--> Classification

Python Implementation

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

Train Accuracy ~ 95%

train on 70000 with 8 Epochs

Test Accuracy ~ 92%

test on 2001

Execution of program

To train the dataset run file handWritingRecognition.py
To run code type: python3 handWritingRecognition.py

Execution for writing through webcam
type: python3 application.py