Giter Site home page Giter Site logo

hindi-character-recognition's Introduction

hindi-character-recognition

The folder should be downloaded as it is, and the model file must be downloaded from the models folder from this link - https://drive.google.com/drive/folders/1obh5CUAfGqmBcdlAepBP4uUrE-KqWtcJ?usp=sharing. Save the model .h5 file in the environment folder.

Dataset

File Description

Edit files and execute files in the following order and change paths where ever necessary

  • main.py - code of segmentation and character recognition
  • train.ipynb - trainer code of model
  • character.txt - contain characters which are segmented and recognised correctly

Important

  • Don't leave space between hindi words and it's above connecting line if a word contains more than 1 character
  • Some times predicted data can be shuffled i.e not in correct order
  • Most data is tested on words written on notepad, with different noises as hand written with pen or sketch pen can be very flawed but still the model performs pretty well on handwritten data too

Additional features

We have created as well as trained the model on a dataset containing VOWELS as well as CONSONANTS

  • Noise removal
  • Reading sparse as well as connected characters
  • Can deal on line noises/circular noises or noise of any category
  • Can Handle image of any size
  • Can detect characters from multiple lines
  • Dufferent types of cases our model can handle are given in sampleImages folder

Architecture

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

Python Implementation

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

Train Acuracy ~ 98%

Test Acuracy ~ 94%

hindi-character-recognition's People

Contributors

ajasra22 avatar amarkeshri28 avatar sudarshan4120 avatar

Stargazers

Atharva Hindukaje avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.