{"id":388213,"date":"2017-08-23T03:47:00","date_gmt":"2017-08-22T19:47:00","guid":{"rendered":"https:\/\/www.engadget.com\/2017\/08\/22\/thanks-google-shutterstock-stop-automated-watermark-removal\/21|23157725"},"modified":"2017-08-23T03:47:00","modified_gmt":"2017-08-22T19:47:00","slug":"thanks-to-google-shutterstock-can-stop-automated-watermark-removal","status":"publish","type":"post","link":"https:\/\/people.utm.my\/asmawisham\/thanks-to-google-shutterstock-can-stop-automated-watermark-removal\/","title":{"rendered":"Thanks to Google, Shutterstock can stop automated watermark removal"},"content":{"rendered":"<p>The original removal process requires hundreds or thousands of photos with the same watermark. Google&#8217;s software can then detect the repeated image structure and then remove it completely without degrading image quality. Shutterstock&#8217;s software response adds minor inconsistencies to the watermark pattern itself, using machine learning to keep it random, thus confusing Google&#8217;s software. The changes are to the structure, or geometry, of the watermarks, not the opacity or location.<\/p>\n<p>&#8220;The result was a watermark randomizer that our engineering team developed so that no two watermarks are the same,&#8221; Shutterstock&#8217;s CTO Martin Brodbek told <a href=\"https:\/\/thenextweb.com\/google\/2017\/08\/21\/google-shutterstock-watermark-stock-photo\/#.tnw_fHVnXUfC\"><em>The Next Web<\/em><\/a>. &#8220;The shapes vary per image and include contributor names. By creating a completely different watermark for each image, it makes it hard to truly identify the shape.&#8221; The technique is already in use, too. You can see an example of one of the new watermarks on one of Shutterstock&#8217;s <a href=\"https:\/\/www.shutterstock.com\/image-photo\/3-years-old-boy-walking-on-382879477\">image pages<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The original removal process requires hundreds or thousands of photos with the same watermark. Google&#8217;s software can then detect the repeated image structure and then remove it completely without degrading image quality. Shutterstock&#8217;s software response adds minor inconsistencies to the watermark pattern itself, using machine learning to keep it random, thus confusing Google&#8217;s software. The [&hellip;]<\/p>\n","protected":false},"author":5817,"featured_media":388214,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[23],"tags":[27,59,26],"class_list":["post-388213","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-media","tag-engadget","tag-media","tag-technology"],"_links":{"self":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts\/388213","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/users\/5817"}],"replies":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/comments?post=388213"}],"version-history":[{"count":0,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/posts\/388213\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/media\/388214"}],"wp:attachment":[{"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/media?parent=388213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/categories?post=388213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/people.utm.my\/asmawisham\/wp-json\/wp\/v2\/tags?post=388213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}