{"id":55,"date":"2018-10-15T16:57:31","date_gmt":"2018-10-15T23:57:31","guid":{"rendered":"http:\/\/jasonfaas.net\/?p=55"},"modified":"2018-10-16T10:04:24","modified_gmt":"2018-10-16T17:04:24","slug":"kaggle-airbus-ship-detection-1st-attempt","status":"publish","type":"post","link":"https:\/\/jasonfaas.net\/?p=55","title":{"rendered":"Ships on Ocean Detection 1st Attempt"},"content":{"rendered":"

Kaggle was having an\u00a0Image Challenge<\/a>\u00a0and I decided to try my hand at it. The challenge is to identify ships on the ocean from satellite images.<\/p>\n

My first attempt involved blurring the training images. Attempting to filter large parts of the ocean. Then logging parts of the image for kNN usage. And noting if the image piece was contained a piece of the ship. To attempt to reduce training set size, the initial image piece was larger that what was reasonable for reporting back as true or false. My strategy was to take a smaller piece of the identified image and log that part as well.<\/p>\n

This first attempt turned out well, and I plan to make another attempt or 2. My code on GitHub<\/a>.<\/p>\n

Steps listed below<\/p>\n

    \n
  1. Original Image with Training Data
    \n    \"\"<\/a> \"\"<\/a><\/li>\n
  2. Blur and filter image
    \n    \"\"<\/a><\/li>\n
  3. Identify larger pieces (32×32 pixels) based on training data. (Thinner lines are False, thicker lines are True)
    \n    \"\"<\/a><\/li>\n
  4. Identify smaller pieces (4×4 pixels) based on training data. (Thinner lines are False, thicker lines are True)
    \n    \"\"<\/a><\/li>\n
  5. Apply data to knn<\/li>\n
  6. Review test image
    \n    \"\"<\/a><\/li>\n
  7. Get result of larger images
    \n    \"\"<\/a><\/li>\n
  8. Get result of smaller images
    \n    \"\"<\/a><\/li>\n
  9. Generate data to submit
    \n    \"\"<\/a><\/li>\n
  10. Comparison of Prediction and Test data
    \n    \"\"<\/a><\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"

    Kaggle was having an\u00a0Image Challenge\u00a0and I decided to try my hand at it. The challenge is to identify ships on the ocean from satellite images. My first attempt involved blurring …<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3,2],"tags":[],"class_list":["post-55","post","type-post","status-publish","format-standard","hentry","category-opencv","category-software-development"],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/jasonfaas.net\/index.php?rest_route=\/wp\/v2\/posts\/55","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jasonfaas.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jasonfaas.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jasonfaas.net\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jasonfaas.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=55"}],"version-history":[{"count":12,"href":"https:\/\/jasonfaas.net\/index.php?rest_route=\/wp\/v2\/posts\/55\/revisions"}],"predecessor-version":[{"id":87,"href":"https:\/\/jasonfaas.net\/index.php?rest_route=\/wp\/v2\/posts\/55\/revisions\/87"}],"wp:attachment":[{"href":"https:\/\/jasonfaas.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=55"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jasonfaas.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=55"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jasonfaas.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=55"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}