{"id":7200,"date":"2018-07-20T09:11:17","date_gmt":"2018-07-20T16:11:17","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=7200"},"modified":"2019-06-26T22:25:44","modified_gmt":"2019-06-27T05:25:44","slug":"body-rockin-drive-image-search-with-your-body-movements","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2018\/07\/20\/body-rockin-drive-image-search-with-your-body-movements\/","title":{"rendered":"Body Movin&#8217;: Drive image search with your body movements"},"content":{"rendered":"<p><em>Unleash the dank emotes!<\/em> My teammates George &amp; Tyler (see <a href=\"http:\/\/jnack.com\/blog\/2018\/05\/07\/demo-realtime-pose-estimation-in-a-browser\/\">previous<\/a>) are back at it running machine learning in your browser, this time to get you off the couch with the playful <a href=\"https:\/\/experiments.withgoogle.com\/collection\/ai\/move-mirror\/view\">Move Mirror<\/a>:<\/p>\n<p><iframe loading=\"lazy\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/JvzkFJW6LIU?feature=oembed\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen><\/iframe><\/p>\n<blockquote>\n<p>Move Mirror takes the input from your camera feed and maps it to a database of more than 80,000 images to find the best match. It\u2019s powered by Tensorflow.js\u2014a library that runs machine learning models on-device, in your browser\u2014which means the pose estimation happens directly in the browser, and your images are not being stored or sent to a server. For a deep dive into how we built this experiment, <a href=\"https:\/\/medium.com\/tensorflow\/move-mirror-an-ai-experiment-with-pose-estimation-in-the-browser-using-tensorflow-js-2f7b769f9b23\">check out this Medium post<\/a>.<\/p>\n<\/blockquote>\n<p>\u00a0Enjoy!<\/p>\n<p><a href=\"https:\/\/experiments.withgoogle.com\/collection\/ai\/move-mirror\/view\"><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2018\/07\/NewImage-19.png\" alt=\"NewImage\" width=\"598\" height=\"299\" border=\"0\" \/><\/a><\/p>\n<p><a href=\"http:\/\/jnack.com\/blog\/2018\/05\/07\/demo-realtime-pose-estimation-in-a-browser\/\"><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2018\/07\/NewImage-18.png\" alt=\"NewImage\" width=\"598\" height=\"423\" border=\"0\" \/><\/a><\/p>\n<p>[<a href=\"https:\/\/youtu.be\/JvzkFJW6LIU\">YouTube<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Unleash the dank emotes! My teammates George &amp; Tyler (see previous) are back at it running machine learning in your browser, this time to get you off the couch with the playful Move Mirror: Move Mirror takes the input from your camera feed and maps it to a database of more than 80,000 images to [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[17,8],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7200"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=7200"}],"version-history":[{"count":6,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7200\/revisions"}],"predecessor-version":[{"id":7207,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/7200\/revisions\/7207"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=7200"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=7200"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=7200"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}