Check out Shutterstock’s new feature!
Shutterstock has today introduced reverse image search, along with visually similar search capabilities. Reverse image search allows users to find images in Shutterstock’s collection, based on an image uploaded, rather than searching keywords. The algorithm will detect and then, in an instant, provide images similar in look and feel to the original, overcoming the limitations of keyword search.
Visually similar search capabilities for video are said to be just around the corner.”We’re continuing to build industry leading technology to improve our offering. With a collection as vast as Shutterstock’s, the importance of being able to surface exactly what a customer needs with advanced search and discovery tools is essential to our continued success,” said Shutterstock’s founder and CEO Jon Oringer. “Doing this in video is a breakthrough and as the technology continues to learn and recognize what’s inside an image or a clip, it promises more possibilities. We know we’ve only scratched the surface in how we use this deep machine learning to better understand and serve our customers.”
The feature was built by Shutterstock’s computer vision team, and has taken over a year to complete. Computer vision is the ability for a computer to break an image down into its primary characteristics, both visually and conceptually that can be represented numerically. The technology relies on pixel data within images – rather than metadata collected through keywords and tagging – to help identify and surface relevant content.
Is this a feature that will come in useful when you’re using stock images? Comment below and join the conversation!