https://github.com/21amir21/handwritten-ocr

https://github.com/21amir21/handwritten-ocr

Last synced: 12 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/21amir21/handwritten-ocr
• Owner: 21amir21
• Created: 2024-04-30T14:37:26.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-05-06T00:03:05.000Z (7 months ago)
• Last Synced: 2024-05-31T18:15:30.720Z (6 months ago)
• Language: Jupyter Notebook
• Size: 392 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Handwritten OCR

## Introduction

Handwritten OCR is a Python-based optical character recognition (OCR) system designed to recognize handwritten text from images.

### In this project we used two approaches:-

1. using ANN (Artifical Neural Network)

2. using Random Forest

## Features

- Recognizes handwritten text from images.

- Supports various image formats such as JPEG, PNG, and BMP.

- Uses machine learning algorithms for accurate character recognition.

- [TODO] Provides easy-to-use APIs for integration into existing applications.

## Installation

1. Clone the repository:

   `git clone https://github.com/21amir21/handwritten-ocr.git`

2. Navigate to the project directory:

   `cd handwritten-ocr`

3. Install dependencies:

   `pip install -r requirements.txt`

## EMNIST Dataset

The EMNIST dataset is a collection of handwritten characters derived from the NIST Special Database 19 and converted to a more manageable format. It contains 814,255 characters divided into 814,255 training images and 81,224 testing images. You can download the dataset used for this project from [Kaggle](https://www.kaggle.com/crawford/emnist).

## Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.