Cigarette Smoking Classification Using YOLO-based Computer Vision Models

Project Code :TCMAPY2134

Objective

The objective of this project is to develop an automated smoking detection system using deep learning models, specifically YOLOv8, for real-time image classification and prediction.

Abstract

This project aims to classify images as "smoking" or "not smoking" using advanced computer vision techniques. The dataset used for this project is the Cigarette Smoker Dataset. The classification is performed using the YOLOv5 and YOLOv8 algorithms, both of which are well-known for their accuracy and efficiency in object detection tasks. The system leverages a Flask-based backend and uses HTML, CSS, and JavaScript for the frontend. The MySQL database is used for storing user and prediction history. The objective is to build a robust model that can identify smoking behavior from images in a simple yet effective manner. This system offers easy accessibility for users through its well-structured modules, including prediction and history tracking features.

Keywords: cigarette smoke, YOLOv5, YOLOv8, image classification, Flask, MySQL, smoking detection, computer vision, dataset, prediction.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.