{
  "id": 30824,
  "title": "Question",
  "url": "/competitions/intel-mobileodt-cervical-cancer-screening/discussion/30824",
  "author_name": "EVasilev",
  "post_date": "2017-03-29T09:44:24.647000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hello for all! \nSorry for my English!\nI'm first time in Kaggle competition.</p>\n\n<p>Maybe my question is stupid, but it's normally for segmentation of cervix?(lower)</p>\n\n<p>1)To train the OpenCV's haar's cascade for detecting region of interest and croped others.</p>\n\n<p>2)Or it's better used gaussian mixture with clustering?</p>\n\n<p>I understand that, cascade can find region of interest , but it would crop image worse then second variant. \nAnd for using cascade I must crop n images handly ( for training)</p>\n\n<p>Thank in advance for answers and advices</p>",
  "messages": [
    {
      "id": 171286,
      "postDate": "2017-03-29T09:44:24.647Z",
      "content": "<p>Hello for all! \nSorry for my English!\nI'm first time in Kaggle competition.</p>\n\n<p>Maybe my question is stupid, but it's normally for segmentation of cervix?(lower)</p>\n\n<p>1)To train the OpenCV's haar's cascade for detecting region of interest and croped others.</p>\n\n<p>2)Or it's better used gaussian mixture with clustering?</p>\n\n<p>I understand that, cascade can find region of interest , but it would crop image worse then second variant. \nAnd for using cascade I must crop n images handly ( for training)</p>\n\n<p>Thank in advance for answers and advices</p>",
      "rawMarkdown": "Hello for all! \nSorry for my English!\nI'm first time in Kaggle competition.\n\nMaybe my question is stupid, but it's normally for segmentation of cervix?(lower)\n\n1)To train the OpenCV's haar's cascade for detecting region of interest and croped others.\n\n2)Or it's better used gaussian mixture with clustering?\n\nI understand that, cascade can find region of interest , but it would crop image worse then second variant. \nAnd for using cascade I must crop n images handly ( for training)\n\nThank in advance for answers and advices"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "171286": "Hello for all! \nSorry for my English!\nI'm first time in Kaggle competition.\n\nMaybe my question is stupid, but it's normally for segmentation of cervix?(lower)\n\n1)To train the OpenCV's haar's cascade for detecting region of interest and croped others.\n\n2)Or it's better used gaussian mixture with clustering?\n\nI understand that, cascade can find region of interest , but it would crop image worse then second variant. \nAnd for using cascade I must crop n images handly ( for training)\n\nThank in advance for answers and advices"
  }
}