{
  "id": 49419,
  "title": "image annotation with paper and markers",
  "url": "/competitions/data-science-bowl-2018/discussion/49419",
  "author_name": "Wei Dong",
  "post_date": "2018-02-10T23:20:18.821000",
  "votes": 1,
  "comment_count": 0,
  "views": 0,
  "content": "<p><a href=\"https://github.com/aaalgo/paperworks\">https://github.com/aaalgo/paperworks</a></p>\n\n<p>Drawing polygons by hand is rather tedious.  The project explores the idea of using paper and markers to annotate images.  The annotation on paper is transferred to image by image processing techniques.  The attached images shows sample scanned annotation, removal of gray-scale content and the final masks generated.  Multiple colors are used to separate touching objects.</p>\n\n<p>It's obvious that annotations generated by this process is incompatible with those used in this competition due to systematic bias.  This is just for fun.</p>\n\n<p>For those who are brave enough to try -- code is in a very rudimentary state.</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/280762/8542/scan.jpg\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/280762/8543/color.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/280762/8544/mask.gif\" alt=\"enter image description here\"></p>",
  "messages": [
    {
      "id": 280762,
      "postDate": "2018-02-10T23:20:18.820Z",
      "content": "<p><a href=\"https://github.com/aaalgo/paperworks\">https://github.com/aaalgo/paperworks</a></p>\n\n<p>Drawing polygons by hand is rather tedious.  The project explores the idea of using paper and markers to annotate images.  The annotation on paper is transferred to image by image processing techniques.  The attached images shows sample scanned annotation, removal of gray-scale content and the final masks generated.  Multiple colors are used to separate touching objects.</p>\n\n<p>It's obvious that annotations generated by this process is incompatible with those used in this competition due to systematic bias.  This is just for fun.</p>\n\n<p>For those who are brave enough to try -- code is in a very rudimentary state.</p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/280762/8542/scan.jpg\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/280762/8543/color.png\" alt=\"enter image description here\"></p>\n\n<p><img src=\"https://storage.googleapis.com/kaggle-forum-message-attachments/280762/8544/mask.gif\" alt=\"enter image description here\"></p>",
      "rawMarkdown": "[https://github.com/aaalgo/paperworks][1]\n\nDrawing polygons by hand is rather tedious.  The project explores the idea of using paper and markers to annotate images.  The annotation on paper is transferred to image by image processing techniques.  The attached images shows sample scanned annotation, removal of gray-scale content and the final masks generated.  Multiple colors are used to separate touching objects.\n\nIt's obvious that annotations generated by this process is incompatible with those used in this competition due to systematic bias.  This is just for fun.\n\nFor those who are brave enough to try -- code is in a very rudimentary state.\n\n![enter image description here](https://kaggle2.blob.core.windows.net/forum-message-attachments/280762/8542/scan.jpg)\n\n![enter image description here](https://kaggle2.blob.core.windows.net/forum-message-attachments/280762/8543/color.png)\n\n![enter image description here](https://kaggle2.blob.core.windows.net/forum-message-attachments/280762/8544/mask.gif)\n\n\n  [1]: https://github.com/aaalgo/paperworks\n  [2]: http://",
      "votes": 1
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "280762": "[https://github.com/aaalgo/paperworks][1]\n\nDrawing polygons by hand is rather tedious.  The project explores the idea of using paper and markers to annotate images.  The annotation on paper is transferred to image by image processing techniques.  The attached images shows sample scanned annotation, removal of gray-scale content and the final masks generated.  Multiple colors are used to separate touching objects.\n\nIt's obvious that annotations generated by this process is incompatible with those used in this competition due to systematic bias.  This is just for fun.\n\nFor those who are brave enough to try -- code is in a very rudimentary state.\n\n![enter image description here](https://kaggle2.blob.core.windows.net/forum-message-attachments/280762/8542/scan.jpg)\n\n![enter image description here](https://kaggle2.blob.core.windows.net/forum-message-attachments/280762/8543/color.png)\n\n![enter image description here](https://kaggle2.blob.core.windows.net/forum-message-attachments/280762/8544/mask.gif)\n\n\n  [1]: https://github.com/aaalgo/paperworks\n  [2]: http://"
  }
}