Convolutional Neural Network for Digitizing Handwritten Notes

For more detailed insights, you can read our academic paper on the development of this technology. Access the paper here: CNN.pdf

Overview

This web application leverages a Convolutional Neural Network (CNN) to accurately convert images of handwritten text into digital text. The frontend is built using React, providing a responsive and interactive user interface, while the backend is powered by FastAPI for efficient handling of API requests and CNN model interactions.

Features

• Image Upload: Users can easily upload images of handwritten notes.
• Text Conversion: Utilizes a state-of-the-art CNN to convert handwriting in the image to editable text.
• Text Display and Edit: Converted text is displayed and can be edited within the web app.
• Academic Insights: View the academic research that underpins the CNN model used in this application.

Authors

• Patrick Lapid
• Colt Kondo
• Daniel Marzo
• Moojin Ahn

Getting Started

Prerequisites

• Node.js
• Python 3.11+
• pip

Clone the Repository

git clone https://github.com/Patrick-Lapid/IntroToML.git
cd IntroToML

Setup the Backend Server

Navigate to the backend directory and install the required Python dependencies:

cd server
pip install -r requirements.txt

Run the FastAPI server:

uvicorn main:app --reload

Setup the Frontend

Navigate to the client folder

cd ../client
npm install

Start the React development server:

npm start