Related Experiment Video
Updated: Jul 8, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.2K
Face mask wearing image dataset: A comprehensive benchmark for image-based face mask detection models.
Yogesh Suryawanshi1, Vishal Meshram2, Vidula Meshram2
1Vishwakarma University, India.
Data in Brief
|December 11, 2023
Summary
This dataset provides 24,916 images for training AI to detect correct and incorrect face mask usage across various mask types and demographics. It aids research in public health and disease mitigation strategies.
Area of Science:
- Computer Science
- Public Health
Background:
- Accurate face mask detection is crucial for public health, especially during pandemics like COVID-19.
- Existing datasets may lack diversity in mask types, demographics, or usage correctness.
Purpose of the Study:
- To introduce a comprehensive image dataset for face mask detection and classification research.
- To support the development of machine learning models for evaluating proper face mask usage.
Main Methods:
- Collected and curated 24,916 images.
- Categorized images into 'Correct' and 'Incorrect' usage.
- Subdivided images by mask type (Bandana, Cotton, N95, Surgical) and demographics (Child, Male, Female).
Main Results:
- The dataset contains diverse images representing various face mask types, ages, and genders.
- It includes clear distinctions between correct and incorrect face mask application.
- Facilitates robust evaluation of AI models for real-world face mask detection scenarios.
Conclusions:
- This dataset enables the development and assessment of advanced face mask detection algorithms.
- It contributes to improving public health by promoting accurate mask-wearing behaviors.
- Supports research efforts in mitigating infectious disease spread through technology.
