Region extraction based approach for cigarette usage classification using deep learning

TL;DR

This paper introduces a deep learning-based method for classifying smoking behavior by extracting relevant image regions and employing a Yolo-v3 based detection module, achieving high accuracy on a novel dataset.

Contribution

It presents a new region extraction approach combined with a Yolo-v3 based detection module for smoking classification, applied to a newly created dataset.

Findings

Achieved 96.74% classification accuracy.

First work on this specific dataset.

Effective in challenging environmental conditions.

Abstract

This paper has proposed a novel approach to classify the subjects' smoking behavior by extracting relevant regions from a given image using deep learning. After the classification, we have proposed a conditional detection module based on Yolo-v3, which improves model's performance and reduces its complexity. As per the best of our knowledge, we are the first to work on this dataset. This dataset contains a total of 2,400 images that include smokers and non-smokers equally in various environmental settings. We have evaluated the proposed approach's performance using quantitative and qualitative measures, which confirms its effectiveness in challenging situations. The proposed approach has achieved a classification accuracy of 96.74% on this dataset.