README.md

FoodScan

Models

1. FoodModel

• Dataset: Food-101
• Accuracy: 78.18%
• Demo: Hugging Face Space

2. IndianFoodModel

• Dataset: Indian Food Images Dataset
• Accuracy: 75.26%

Features

• Food Detection: Identify food items from images
• Recipe Retrieval: Get recipes for identified food items
• Nutrient Comparison: Compare the nutritional values of food items

Backend

Backend is built using Flask API

Steps to Set Up

1. Create a virtual environment

   python -m venv env

2. Activate the virtual environment
   • On Windows:

     .\env\Scripts\activate

   • On macOS/Linux

     source env/bin/activate

3. Install dependencies

   pip install -r requirements.txt

4. Run the application

   python app.py

Frontend

Frontend is built using React

Steps to Set Up

1. Navigate to the frontend folder

   cd frontend

2. Install dependencies

   npm install

3. Start the development server

   npm start

Website

Visit the live application here: FoodScan

Screenshots

Homepage

Features

Food Detection

Recipe Retrieval

Nutrient Comparison

Diet Plan