Photo-sharing site Pinterest just announced a new feature intended to help users find items they discover in pins. Starting Monday, the company will launch a new search tool that can zoom into any part of an existing pinned image and bring up results for visually similar pins.
“Sometimes you spot something you really love on Pinterest, but you don’t know how to find it in real life, or what it’s even called,” Kevin Jing, an engineering manager at Pinterest, wrote in a blog post. “There’s that perfect lamp hiding in a Pin of someone’s living room, or maybe a random street style shot with the exact shoes you’re looking for.”
If you spot something in a pin that you’d like to know more about, all you need to do is press the search button in the corner of the image, place an adjustable box over the pin and crop it to fit over the desired item. Pinterest will then use its deep learning algorithm to scan the section and produce matching pins, with users able to add descriptive keywords to narrow down the search. It’s also possible to further filter the search results by topic.
Pinterest says the technology is a step toward a new type of visual search engine that it calls “a discovery engine.” Executives say it will help users find things they didn’t even know they liked.
The company said it collaborated with the Berkeley Vision and Learning Center to apply deep learning to analyze images across its “annotated dataset of billions of pins.” The two already have a pre-existing partnership; the center’s director, Professor Trevor Darrell, is an advisor to the company, and Pinterest has hired two of the center’s alumni, according to the Wall Street Journal.
The visual search tool – available across iOS, Android, and the website – will also offer new ways for Pinterest’s 100 million monthly active users to buy things. Once someone finds an item from a pin that they are interested in, the company’s new shopping tools will make it easy to purchase.