Abstract :

Content-Based Image Retrieval (CBIR) is an effective approach for searching and retrieving images based on their visual content rather than textual metadata. This project presents a Flask-powered CBIR system that allows users to upload an image and retrieve visually similar images from a database. The system extracts features such as color, texture, and shape using image processing and deep learning techniques. Flask acts as a lightweight backend framework to handle user requests and model inference. The similarity between images is computed using distance metrics. The proposed system improves retrieval accuracy and usability through a web-based interface. This solution is suitable for applications in medical imaging, surveillance, and digital libraries.