We lift barriers between creativity and technology, and converge advanced development into outcome-driven solutions. Pushing boundaries in gaming, digital, and experiential since 2010



Posts: 407
Reposts: 0

Shutterstock uses Computer Vision to take image-search to the next level

There's a huge problem with stock imagery. Namely in the keyword system used to name and find it.

"Frustrated young handsome man looking exhausted while sitting at his working place and carrying his glasses in hand" just isn't a realistic way to search for what you're looking for anymore, as anyone who's spent hours searching for the perfect stock image will tell you.

Enter Shutterstock, who has stepped forward and brought us closer to eliminating awkward keywords than ever before. Using a Computer Vision system, they've released an experimental A.I. that will reverse search stock imagery for you based on a picture.

The days of awkward keywords seem to be numbered, but how will anyone find unintentionally hilarious stock imagery like this any more?

Computers still can’t read our minds. But stock image website Shutterstock has created a whole new way to categorize images. The company’s new tool, which launches today on their web site, is one of many innovations in a recent but rapidly growing field called computer vision. And Shutterstock is hoping that it can transform your frustrating process of matching the image in your head to the one on your screen into something that’s actually fun.

As a free user, you can follow Passle and like posts.

To repost this post to your own Passle blog, you will need to upgrade your account.

For plans and pricing, please contact our sales team at

Sorry, you don't have permission to repost or create posts.

Repost successful!

View the repost

Repost successful!

Your repost is currently a draft. Review your repost and request approval.

Something went wrong whilst reposting - please try again.

Sorry - this is not an option. This post already exists in the Passle you have selected.

Try reposting to another Passle.