{
  "fetched_at": "2026-10-19T10:51:37Z",
  "source_url": "https://www.kaggle.com/competitions/crack-identification-ce784a-2020-iitk/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>The dataset consists of 2 folders: 'train' and 'test'. The folder 'train' is a labelled dataset and consists of 2 sub-folders: 'cracked' and 'uncracked'. The sub-folder 'cracked' consists of a total of 7501 images containing cracks, while the 'uncracked' sub-folder contains 7467 images with no cracks.   All images are of the ‘.jpg’ format.</p>\n<p>The ‘test’ folder consists of the test dataset images. There are a total of 2000 images in this folder (all ‘.jpg’ files). These images are unlabelled i.e., the labels are not provided, whether they contain cracks or not. The objective of this challenge is to predict the class of each of these test images. The class can be either ‘cracked’ or ‘uncracked’. The filenames of these test images are given as 1.jpg, 2.jpg, 3.jpg, …, 2000.jpg.  </p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This assignment is on image classification problem using deep convolutional neural networks. The dataset consists of images obtained from concrete bridge decks, pavements, and walls. The images can contain either cracks or no cracks. Your objective in this challenge is to develop a binary image classification model that can classify from a given image if it contains any cracks or not. </p>\n\n\n<h2>Acknowledgements</h2>\n<p>This dataset is adapted from SDNET 2018 dataset.</p>\n<p>Dorafshan, S., Thomas, R. J., &amp; Maguire, M. (2018). SDNET2018: An annotated image dataset for non-contact concrete crack detection using deep convolutional neural networks. Data in Brief, 21, 1664–1668. https://doi.org/10.1016/j.dib.2018.11.015</p><p></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this challenge is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<p>50% of the test images will be used for public leaderboard performance calculation and the remaining 50% will be used for private leaderboard. Public scores will be shown on the public leaderboard, while only the private scores will be used for final evaluation. The private leaderboard score is not shown until the end of the competititon. You can hand-select any 2 of the eligible submissions for private leaderboard score, or will otherwise default to the best public scoring submissions.</p>\n\n\n<h2>Submission Format</h2>\n<p> Submission files should be in .csv format and contain two columns: filename and class. ‘filename’ should be in string format and will contain the image filename (1.jpg, 2. jpg, etc.). The ‘class’ will also be in string format and contain the corresponding class name. It can take two values: ‘cracked’ or ‘uncracked’. Since there are 2000 images in the test dataset, your submission should have 2000 rows (excluding the header), each with 2 columns. . A sample submission file is also provided in the dataset.  </p>\n<p>The file should contain a header and have the following format:</p>\n<pre>filename,class<br>1.jpg,cracked<br></pre>\n</strong>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}