{
  "id": 395330,
  "title": "📜3D X-ray scan layers animation",
  "url": "/competitions/vesuvius-challenge-ink-detection/discussion/395330",
  "author_name": "",
  "post_date": "2023-03-16T21:12:03.078879900Z",
  "votes": 36,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I made a <a href=\"https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook\" target=\"_blank\">notebook</a> in which I provide EDA for the competition's data and create animation for the train volume layers.</p>\n<p>Short description:</p>\n<ul>\n<li><p>The goal of this competition is to detect ink from 3D X-ray scans of ancient scrolls from a library buried by the eruption of Vesuvius nearly 2000 years ago. The scrolls were carbonized due to the heat of the volcano and are now impossible to open without breaking them.</p></li>\n<li><p>The ink used in the Herculaneum scrolls does not show up readily in X-ray scans, but machine learning models can detect it. The dataset contains 3D X-ray scans of four fragments at 4µm resolution, made using a particle accelerator, as well as infrared photographs of the surface of the fragments showing visible ink.</p></li>\n<li><p>Hand-labeled binary masks indicating the presence of ink in the photographs are also provided.</p></li>\n</ul>\n<hr>\n<p>Here is an animation example in <code>.gif</code> format (in the <a href=\"https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook\" target=\"_blank\">notebook</a> animations are in the <code>.mp4</code> format, so you can easily interact with it):</p>\n<p><img src=\"https://user-images.githubusercontent.com/45982614/225752518-5dee3104-d3b2-42bd-b2f5-856df0aad1e4.gif\" alt=\"\"></p>",
  "messages": [
    {
      "id": "2185164",
      "postDate": "03/16/2023 21:12:03",
      "content": "<p>I made a <a href=\"https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook\" target=\"_blank\">notebook</a> in which I provide EDA for the competition's data and create animation for the train volume layers.</p>\n<p>Short description:</p>\n<ul>\n<li><p>The goal of this competition is to detect ink from 3D X-ray scans of ancient scrolls from a library buried by the eruption of Vesuvius nearly 2000 years ago. The scrolls were carbonized due to the heat of the volcano and are now impossible to open without breaking them.</p></li>\n<li><p>The ink used in the Herculaneum scrolls does not show up readily in X-ray scans, but machine learning models can detect it. The dataset contains 3D X-ray scans of four fragments at 4µm resolution, made using a particle accelerator, as well as infrared photographs of the surface of the fragments showing visible ink.</p></li>\n<li><p>Hand-labeled binary masks indicating the presence of ink in the photographs are also provided.</p></li>\n</ul>\n<hr>\n<p>Here is an animation example in <code>.gif</code> format (in the <a href=\"https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook\" target=\"_blank\">notebook</a> animations are in the <code>.mp4</code> format, so you can easily interact with it):</p>\n<p><img src=\"https://user-images.githubusercontent.com/45982614/225752518-5dee3104-d3b2-42bd-b2f5-856df0aad1e4.gif\" alt=\"\"></p>",
      "rawMarkdown": "I made a [notebook](https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook) in which I provide EDA for the competition's data and create animation for the train volume layers.\n\nShort description:\n* The goal of this competition is to detect ink from 3D X-ray scans of ancient scrolls from a library buried by the eruption of Vesuvius nearly 2000 years ago. The scrolls were carbonized due to the heat of the volcano and are now impossible to open without breaking them.\n\n* The ink used in the Herculaneum scrolls does not show up readily in X-ray scans, but machine learning models can detect it. The dataset contains 3D X-ray scans of four fragments at 4µm resolution, made using a particle accelerator, as well as infrared photographs of the surface of the fragments showing visible ink.\n\n* Hand-labeled binary masks indicating the presence of ink in the photographs are also provided.\n\n***\n\nHere is an animation example in <code>.gif</code> format (in the [notebook](https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook) animations are in the <code>.mp4</code> format, so you can easily interact with it):\n\n![](https://user-images.githubusercontent.com/45982614/225752518-5dee3104-d3b2-42bd-b2f5-856df0aad1e4.gif)",
      "votes": null
    },
    {
      "id": "2185193",
      "postDate": "03/16/2023 21:38:23",
      "content": "<p>Nice, the animations are mesmerizing.</p>",
      "rawMarkdown": "Nice, the animations are mesmerizing.",
      "votes": null
    },
    {
      "id": "2185201",
      "postDate": "03/16/2023 21:50:33",
      "content": "<p>Thanks a lot for the comment 😊! <br>\nI'm very flattered that you like my work!</p>",
      "rawMarkdown": "Thanks a lot for the comment 😊! \nI'm very flattered that you like my work!",
      "votes": null
    },
    {
      "id": "2244113",
      "postDate": "05/03/2023 12:58:12",
      "content": "<p>Awesome work, thanks for sharing!</p>",
      "rawMarkdown": "Awesome work, thanks for sharing!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2185193,
      "author_name": "jpposma",
      "author_url": "",
      "post_date": "03/16/2023 21:38:23",
      "content": "<p>Nice, the animations are mesmerizing.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2185201,
          "author_name": "leonidkulyk",
          "author_url": "",
          "post_date": "03/16/2023 21:50:33",
          "content": "<p>Thanks a lot for the comment 😊! <br>\nI'm very flattered that you like my work!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 2244113,
      "author_name": "yassinealouini",
      "author_url": "",
      "post_date": "05/03/2023 12:58:12",
      "content": "<p>Awesome work, thanks for sharing!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2185164": "I made a [notebook](https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook) in which I provide EDA for the competition's data and create animation for the train volume layers.\n\nShort description:\n* The goal of this competition is to detect ink from 3D X-ray scans of ancient scrolls from a library buried by the eruption of Vesuvius nearly 2000 years ago. The scrolls were carbonized due to the heat of the volcano and are now impossible to open without breaking them.\n\n* The ink used in the Herculaneum scrolls does not show up readily in X-ray scans, but machine learning models can detect it. The dataset contains 3D X-ray scans of four fragments at 4µm resolution, made using a particle accelerator, as well as infrared photographs of the surface of the fragments showing visible ink.\n\n* Hand-labeled binary masks indicating the presence of ink in the photographs are also provided.\n\n***\n\nHere is an animation example in <code>.gif</code> format (in the [notebook](https://www.kaggle.com/code/leonidkulyk/eda-vc-id-volume-layers-animation/notebook) animations are in the <code>.mp4</code> format, so you can easily interact with it):\n\n![](https://user-images.githubusercontent.com/45982614/225752518-5dee3104-d3b2-42bd-b2f5-856df0aad1e4.gif)",
    "2185193": "Nice, the animations are mesmerizing.",
    "2185201": "Thanks a lot for the comment 😊! \nI'm very flattered that you like my work!",
    "2244113": "Awesome work, thanks for sharing!"
  },
  "source": "meta"
}