Shutterstock’s Composition Aware AI Photo Search Uses Deep Learning

October 13, 2017 - photo frame

The batch print use Shutterstock has announced a new absolute print hunt apparatus called Composition Aware Search. It uses modernized low training record to let we hunt for photos containing certain objects in certain locations.

After typing in one or some-more hunt terms for a objects you’d like in a frame, we can mention where in a print you’d like those objects to appear. Everything is finished in a tiny “layout” box that has circles representing a objects you’re acid for. Move a circles around in a box, and a hunt automatically updates with new formula that improved compare your layout.

For example, if you’d like to find photos of booze in a top right dilemma of a frame, some cheese next it, and some dull space on a left, we can now simply do that.

Here’s a brief video display how a new Composition Aware hunt works:

“This patent-pending apparatus uses a multiple of appurtenance vision, healthy denunciation processing, and state of a art information retrieval techniques to find clever matches opposite formidable spatially wakeful hunt criteria,” Shutterstock says.

You can review a company’s white paper about this record here, and we can try it out for yourself here.

(via Shutterstock around Engadget)

small.wp_rp_excerpt { line-height:115%; font-style:normal; } .related_post_title { } ul.related_post { line-height:120%; } ul.related_post li { list-style-type:none; clear:both; margin:0 0 0 3px; } ul.related_post li a { font-weight: bold; display:block; margin:0 0 5px 0; } ul.related_post li a:hover { text-decoration:underline; } ul.related_post li A img { width:130px; height:auto; }

More frame ...

› tags: photo frame /