{
  "id": 176975,
  "title": "Effect of Colormaps",
  "url": "/competitions/osic-pulmonary-fibrosis-progression/discussion/176975",
  "author_name": "",
  "post_date": "2020-08-24T10:02:49.986156300Z",
  "votes": 10,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Quoting the content from Google AI blog : <br>\n<em>Colorizing images helps the human visual system pick out detail, estimate quantitative values, and notice patterns in data in a more intuitive fashion. However, the choice of color map can have a significant impact on a given task. For example, interpretation of “rainbow maps” have been linked to lower accuracy in mission critical applications, such as medical imaging. Still, in many applications, “rainbow maps” are preferred since they show more detail (at the expense of accuracy) and allow for quicker visual assessment</em>. </p>\n<p>I advise everyone to go through this before you are immersing yourself into image related competitions. This can help in your EDA process as it did for me(<strong>right now the notebook is private as it's still under development stage. Will make it public sometime next week</strong>).</p>\n<p><strong><a href=\"https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html\" target=\"_blank\">https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html</a></strong></p>\n<p>Some highlights :</p>\n<p>Inferno map<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F6130cac671008c621a683a179b966d92%2Finferno.png?generation=1598263141745590&amp;alt=media\" alt=\"\"></p>\n<p>Viridis map<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F3944c1d3d206be63217813f478499893%2Fvirdis.png?generation=1598263176639144&amp;alt=media\" alt=\"\"></p>\n<p>Google's Turbo Map : This will help u in inspection of medical images as openings and spaces are much easily visible<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F70df7ce9e6973dd7b08879a7f47df9c8%2Fturbo.png?generation=1598263241428669&amp;alt=media\" alt=\"\"></p>\n<p><strong>A faceoff - Inferno VS Turbo</strong></p>\n<p><strong>Inferno</strong><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F05a35084763b5b3247951fc3781d1944%2Finferno%20vs%20turbo%201.png?generation=1598263288720182&amp;alt=media\" alt=\"\"></p>\n<p><strong>Same stuff in Turbo - Look the difference in details visible</strong><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F7784433ca3a59b3f7260bb66887763d3%2Finferno%20vs%20turbon%202.png?generation=1598263332392705&amp;alt=media\" alt=\"\"></p>\n<p><strong>Do visit that blog more amazing details</strong>.</p>",
  "messages": [
    {
      "id": "983439",
      "postDate": "08/24/2020 10:02:49",
      "content": "<p>Quoting the content from Google AI blog : <br>\n<em>Colorizing images helps the human visual system pick out detail, estimate quantitative values, and notice patterns in data in a more intuitive fashion. However, the choice of color map can have a significant impact on a given task. For example, interpretation of “rainbow maps” have been linked to lower accuracy in mission critical applications, such as medical imaging. Still, in many applications, “rainbow maps” are preferred since they show more detail (at the expense of accuracy) and allow for quicker visual assessment</em>. </p>\n<p>I advise everyone to go through this before you are immersing yourself into image related competitions. This can help in your EDA process as it did for me(<strong>right now the notebook is private as it's still under development stage. Will make it public sometime next week</strong>).</p>\n<p><strong><a href=\"https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html\" target=\"_blank\">https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html</a></strong></p>\n<p>Some highlights :</p>\n<p>Inferno map<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F6130cac671008c621a683a179b966d92%2Finferno.png?generation=1598263141745590&amp;alt=media\" alt=\"\"></p>\n<p>Viridis map<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F3944c1d3d206be63217813f478499893%2Fvirdis.png?generation=1598263176639144&amp;alt=media\" alt=\"\"></p>\n<p>Google's Turbo Map : This will help u in inspection of medical images as openings and spaces are much easily visible<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F70df7ce9e6973dd7b08879a7f47df9c8%2Fturbo.png?generation=1598263241428669&amp;alt=media\" alt=\"\"></p>\n<p><strong>A faceoff - Inferno VS Turbo</strong></p>\n<p><strong>Inferno</strong><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F05a35084763b5b3247951fc3781d1944%2Finferno%20vs%20turbo%201.png?generation=1598263288720182&amp;alt=media\" alt=\"\"></p>\n<p><strong>Same stuff in Turbo - Look the difference in details visible</strong><br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F7784433ca3a59b3f7260bb66887763d3%2Finferno%20vs%20turbon%202.png?generation=1598263332392705&amp;alt=media\" alt=\"\"></p>\n<p><strong>Do visit that blog more amazing details</strong>.</p>",
      "rawMarkdown": "Quoting the content from Google AI blog : \n*Colorizing images helps the human visual system pick out detail, estimate quantitative values, and notice patterns in data in a more intuitive fashion. However, the choice of color map can have a significant impact on a given task. For example, interpretation of “rainbow maps” have been linked to lower accuracy in mission critical applications, such as medical imaging. Still, in many applications, “rainbow maps” are preferred since they show more detail (at the expense of accuracy) and allow for quicker visual assessment*. \n\nI advise everyone to go through this before you are immersing yourself into image related competitions. This can help in your EDA process as it did for me(**right now the notebook is private as it's still under development stage. Will make it public sometime next week**).\n\n**https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html**\n\nSome highlights :\n\nInferno map\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F6130cac671008c621a683a179b966d92%2Finferno.png?generation=1598263141745590&alt=media)\n\nViridis map\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F3944c1d3d206be63217813f478499893%2Fvirdis.png?generation=1598263176639144&alt=media)\n\nGoogle's Turbo Map : This will help u in inspection of medical images as openings and spaces are much easily visible\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F70df7ce9e6973dd7b08879a7f47df9c8%2Fturbo.png?generation=1598263241428669&alt=media)\n\n**A faceoff - Inferno VS Turbo**\n\n**Inferno**\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F05a35084763b5b3247951fc3781d1944%2Finferno%20vs%20turbo%201.png?generation=1598263288720182&alt=media)\n\n**Same stuff in Turbo - Look the difference in details visible**\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F7784433ca3a59b3f7260bb66887763d3%2Finferno%20vs%20turbon%202.png?generation=1598263332392705&alt=media)\n\n\n**Do visit that blog more amazing details**.",
      "votes": null
    },
    {
      "id": "983737",
      "postDate": "08/24/2020 14:47:31",
      "content": "<p>Awesome resource!  Thanks for taking the time to pull it together! </p>",
      "rawMarkdown": "Awesome resource!  Thanks for taking the time to pull it together!",
      "votes": null
    },
    {
      "id": "984657",
      "postDate": "08/25/2020 08:00:37",
      "content": "<p>No biggie!! Happy to help.<br>\nAll the best!</p>\n<p>~Aditya</p>",
      "rawMarkdown": "No biggie!! Happy to help.\nAll the best!\n\n~Aditya",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 983737,
      "author_name": "thaddeussegura",
      "author_url": "",
      "post_date": "08/24/2020 14:47:31",
      "content": "<p>Awesome resource!  Thanks for taking the time to pull it together! </p>",
      "votes": null,
      "replies": [
        {
          "id": 984657,
          "author_name": "fireheart7",
          "author_url": "",
          "post_date": "08/25/2020 08:00:37",
          "content": "<p>No biggie!! Happy to help.<br>\nAll the best!</p>\n<p>~Aditya</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "983439": "Quoting the content from Google AI blog : \n*Colorizing images helps the human visual system pick out detail, estimate quantitative values, and notice patterns in data in a more intuitive fashion. However, the choice of color map can have a significant impact on a given task. For example, interpretation of “rainbow maps” have been linked to lower accuracy in mission critical applications, such as medical imaging. Still, in many applications, “rainbow maps” are preferred since they show more detail (at the expense of accuracy) and allow for quicker visual assessment*. \n\nI advise everyone to go through this before you are immersing yourself into image related competitions. This can help in your EDA process as it did for me(**right now the notebook is private as it's still under development stage. Will make it public sometime next week**).\n\n**https://ai.googleblog.com/2019/08/turbo-improved-rainbow-colormap-for.html**\n\nSome highlights :\n\nInferno map\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F6130cac671008c621a683a179b966d92%2Finferno.png?generation=1598263141745590&alt=media)\n\nViridis map\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F3944c1d3d206be63217813f478499893%2Fvirdis.png?generation=1598263176639144&alt=media)\n\nGoogle's Turbo Map : This will help u in inspection of medical images as openings and spaces are much easily visible\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F70df7ce9e6973dd7b08879a7f47df9c8%2Fturbo.png?generation=1598263241428669&alt=media)\n\n**A faceoff - Inferno VS Turbo**\n\n**Inferno**\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F05a35084763b5b3247951fc3781d1944%2Finferno%20vs%20turbo%201.png?generation=1598263288720182&alt=media)\n\n**Same stuff in Turbo - Look the difference in details visible**\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F2599569%2F7784433ca3a59b3f7260bb66887763d3%2Finferno%20vs%20turbon%202.png?generation=1598263332392705&alt=media)\n\n\n**Do visit that blog more amazing details**.",
    "983737": "Awesome resource!  Thanks for taking the time to pull it together!",
    "984657": "No biggie!! Happy to help.\nAll the best!\n\n~Aditya"
  },
  "source": "meta"
}