Stock photography website Shutterstock has announced the launch of a feature that uses a 'custom-built neural network' to suggest keywords to users when uploading their images to their website.

The new feature aims to make the process of submitting images through their iOS app easier for users. Shutterstock requires contributors to add between seven and 50 keywords to their images when uploading them to the system, to help customers find appropriate images for their needs.

kw_suggest_1

The Shutterstock keyword suggstion tool

Their app uses artificial intelligence to review metadata and pixel data to suggest several keywords for the images contributors are uploading, that users can tap to select. It works by using computer vision technology to locate visually similar images to the uploaded image, and automatically suggest and previously successful keywords for the user to select.

The tool is being launched for mobile initially, to make the process of submitting images when using the smaller keyboard of a mobile phone easier.

Shutterstock claims to have over 100,000 contributors who may benefit from these advances in their technology.

Jon Oringer, Founder and CEO of Shutterstock, said: “We continue to invest in our Artificial Intelligence tools, which allow us to enhance the Shutterstock experience… In this instance, we are helping our artists and photographers focus on the job they enjoy most. Keyword suggestions and other innovative tools built on our custom computer vision technology are instrumental in bringing efficiency and accuracy to the contributor experience, helping them earn more faster.”

Autotagging

The autotagging tool in action

The keyword suggestion tool is available on the Shutterstock Contributor iPhone application in the app store from today.