Efficient YOLOv9-Based Object Recognition System for Dynamic Scenarios

This project presents an object recognition system developed using the COCO dataset, which contains a wide variety of labeled images across multiple object categories. The system employs the YOLOv9 algorithm, known for its accuracy and efficiency in detecting and classifying numerous object classes within images. By leveraging this advanced deep learning model, the system is capable of identifying a diverse range of objects, including people, vehicles, animals, and everyday items, making it versatile for various applications.

The front-end interface is built using Streamlit, providing an intuitive platform for users to visualize and interact with detection results easily. This integration of a robust detection algorithm with an accessible web interface enhances the usability and effectiveness of the system. Overall, the project demonstrates the potential of combining large-scale datasets, modern object detection algorithms, and interactive technologies to improve automated object recognition in complex scenes.

Keywords: object recognition, COCO dataset, YOLOv9, multi-class detection, deep learning, Streamlit.