Abstract

The "Food Calorie Prediction" project aims to assist individuals in maintaining a healthy lifestyle by providing a solution to estimate the caloric content of food items from images. This project uses deep learning to deliver accurate calorie predictions, enhancing users' dietary management. The frontend of the application is developed using React.js, ensuring a seamless and interactive user experience, while Firebase is utilized for backend operations, including secure user authentication and data storage.

Users can upload images of food items, and the system will analyze these images to predict their caloric content. This feature helps users make informed dietary choices by understanding the caloric intake of various food items. Additionally, users can view their previous predictions, allowing them to track and manage their total calorie consumption over time.

The project employs a dataset consisting of images from 101 different food items, and the ResNet-50 algorithm is used for training the model. ResNet-50, a powerful convolutional neural network, is well-suited for image recognition tasks and provides high accuracy in predicting food calories.

By integrating web technologies with advanced machine learning algorithms, the "Food Calorie Prediction" project offers a practical tool for users to monitor and manage their dietary habits effectively.

You can download abstract from here

Technologies Used

Modules

1. User

🧁 Login/Signup

🧁 Upload Food images

🧁 Classes - 101 Food Items

🧁 Voice recognition (user can say food name instead of image)

🧁 View History of previous predictions

🧁 Specify quantity and size of food Item

🧁 View nutritional value of detected food Item

🧁 Check if food is safe for users with allergies