This project is an AI-powered image classifier created by Zain Qamar as Task 2 for the Certura Internship.
This web application allows users to upload an image and receive an AI-based prediction of what the image contains. It features a welcome page that introduces the project and a classifier page where you can upload an image by either clicking to select a file or by dragging and dropping it.
The application is designed to identify 1,000 different categories of common objects, animals, and scenes.
The application's core is a Python program that runs on a Flask web server. When a user uploads an image, the server uses a pre-trained deep learning model called MobileNet (provided by TensorFlow/Keras) to analyze the image.
The process is as follows:
- The user uploads an image.
- The Flask backend receives and saves the image.
- The image is preprocessed: resized to 224x224 pixels and normalized for the model.
- The MobileNet model predicts the content, providing its top 3 most likely classifications with confidence scores.
- The results are displayed back to the user on the web page.
The user interface is built with standard HTML and CSS, and the welcome page is styled with Tailwind CSS for a modern look.