{
  "fetched_at": "2026-10-19T11:24:17Z",
  "source_url": "https://www.kaggle.com/competitions/face-mask-detection/data",
  "pages": [
    {
      "name": "data-description",
      "content": "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 660 images with 3 classes with_mask, without_mask and partial_mask in single directory. (220 images in each class)\n\nPeople 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:\n\nWithout Mask/ With Mask/ Partial Mask\nNote that this dataset contains some annotated (artificially generated) masks to augment the 'masked' data category.\n\nThe Dataset faceMask_Kaggle_test.zip contains all the images indexed from 1 to 660 in the .jpg format\n\nSample_Submission.csv is provided to help in making predictions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Problem Statement**\n\nTo build and implement a Convolutional Neural Network model to classify between masked/unmasked/partially masked faces.\n\nAt the end of this miniproject, you will be able to\n\n- load and extract features of images using ImageDataGenerator\n- build the convolutional neural networks\n- use the pre-trained models using keras applications\n\n**Introduction**\n\nThis project uses a Deep Neural Network, more specifically a Convolutional Neural Network, to differentiate between images of people, with masks, without masks and incorrectly placed masks. Manually built and pretrained networks will be used to perform this classification task.\n\n**Face-Mask-Detection-Using-CNN**\n\nOutbreak of the Coronavirus pandemic has created various changes in the lifestyle of everyone around the world.\nAmong these changes, wearing a mask has been very vital to every individual.\nDetection of people who are not wearing masks is a challenge due to the large populations.\nThis face mask detection project can be used in schools, hospitals, banks, airports etc as a digitalized scanning tool.\nThe technique of detecting people’s faces and segregating them into three classes namely the people with masks and people without masks and partial masks is done with the help of image processing and deep learning.\nWith the help of this project, a person who is monitoring the face mask status for a particular firm can be seated in a remote area and still monitor efficiently and give instructions accordingly.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "To evaluate the predictions, we use Weighted Categorization Accuracy Metric. In which we assign weight to each class and accuracy is calculated based on the weights attached.\n\nWeighted categorization accuracy can be generally defined as:\n\n![](https://cdn.iisc.talentsprint.com/CDS/Images/Kaggle_competition.gif)\n\nwhere  y are ground truths,  y_hat are the predicted results, and w  is the weight associated with the ith item in the dataset.\n\nIn our test set, we assign each testing item a weight according to its category. We set the weights in consideration of the imbalance of the data distribution to minimize the bias and to improve performance caused by the majority class.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}