Shutterstock’s Composition Aware AI Photo Search Uses Deep Learning

The stock photo service Shutterstock has announced a new powerful photo search tool called Composition Aware Search. It uses advanced deep learning technology to let you search for photos containing certain objects in certain locations.

After typing in one or more search terms for the objects you’d like in the frame, you can specify where in the photo you’d like those objects to appear. Everything is done in a small “layout” box that has circles representing the objects you’re searching for. Move the circles around in the box, and the search automatically updates with new results that better match your layout.

For example, if you’d like to find photos of wine in the upper right corner of the frame, some cheese below it, and some empty space on the left, you can now easily do that.

Here’s a short video showing how the new Composition Aware search works:

“This patent-pending tool uses a combination of machine vision, natural language processing, and state of the art information retrieval techniques to find strong matches against complex spatially aware search criteria,” Shutterstock says.

You can read the company’s white paper about this technology here, and you can try it out for yourself here.

(via Shutterstock via Engadget)