# FaceMaskDetection Weightage — Data

来源：https://www.kaggle.com/competitions/facemaskdetection-weightage/data

采集时间：2026-10-19T09:35:37Z

Dataset
The data for this mini-project is collected from various sources including the masked images from internet and general frontal face images considered as without mask. This dataset consists of 5029 train images and 1059 test images with 3 classes with_mask, without_mask and partial_mask

Many people are not correctly wearing their masks due to bad practices, bad behaviors or vulnerability of individuals (e.g., children, old people). For these reasons, several mask wearing campaigns intend to sensitize people about this problem and good practices. In this sense, this work proposes three types of masked face detection dataset; namely, the Correctly Masked Face, the Incorrectly Masked Face and their combination for the global masked face detection. This dataset serves the objective of classifying faces that are:

Without Mask/ With Mask/ Partial Mask
Note that this dataset contains some annotated (artificially generated) masks to augment the 'masked' data category.