Coming Soon
Project details are currently under development. Check back soon to see more information about this project!
Back to HomeMachine Learning Image Classifier
A web application that uses a trained convolutional neural network to classify images. Users can upload images and receive predictions with confidence scores.
Project Overview
This project demonstrates the practical application of machine learning for image classification. The core of the application is a convolutional neural network trained on a dataset of over 100,000 images across 10 categories. The web interface allows users to upload their own images or provide URLs to online images. The model then processes these images and returns predictions with confidence scores for the top 5 most likely categories. The machine learning model was built using TensorFlow and Keras, then converted to TensorFlow.js for client-side inference, allowing the application to work without sending user images to a server. This approach improves both privacy and performance.