Face Mask Detection Dataset with 300 Real Images

Ferdib-Al-Islam and colleagues from Northern University published this dataset in July 2021. It contains real images of people, with 150 images for the 'with mask' class and 150 images for the 'without mask' class. The dataset is hosted on Zenodo and is intended for computer vision research.

Use Cases

• Train a binary image classifier to detect the presence of a face mask based on real-world images.
• Benchmark model performance on a balanced dataset of masked and unmasked faces.
• Develop applications for automated mask compliance monitoring in public spaces using the provided image data.

Strengths

• Dataset contains 300 total images, providing a balanced set for binary classification.
• Images are described as 'real', suggesting they represent real-world conditions.

Limitations

• Row count and image resolution are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Zenodo, via paperswithcode.

Collection Method

Collection method is not described in the provided metadata.

Time Range

Dataset published in July 2021.

Freshness

Last updated date is unknown.

Geography

Spatial coverage is not specified.