In an effort to make much needed upgrades to its visual search capabilities, Pinterest recently acquired two-man startup VisualGraph. Founder Kevin Jing previously worked on Google’s visual search features before partnering with David Liu and starting VisualGraph, now they are joining the engineering team at Pinterest.
In a response to the acquisition, Pinterest said:
The acquisition of VisualGraph will help us build technology to better understand what people are Pinning. By doing so, we hope to make it easier for people to find the things they love.
VisualGraph specializes in machine vision, image recognition, and visual search technologies. Their expertise will be used to improve Pinterest’s search capabilities with a deeper understanding of the content of an image without the assistance of text or tags. Pinterest will eventually be able to suggest other relevant pins with the help of image detection technology, similar to how Google’s “Search by Image” system works.
Pinterest’s search engine previously relied on signals like alt text, text in the image link, and image metadata to identify photos. Not only will the addition of image detection technology make the Pinterest search experience better for users, but also more difficult for spammers to take advantage of.
In a statement made on the VisualGraph home page, Kevin Jing had this to say:
On Pinterest, millions of people are curating and sharing billions of Pins everyday. And these Pins are more than just images — they link to contents that can inspire and enrich people’s lives. We are excited for the opportunity to combine machine vision with human vision and curation, and to build a visual discovery experience that is both aesthetically appealing and immensely useful for people everywhere.
As Pinterest continues to prove itself as a serious marketing platform, this is the exact kind of upgrade it needs in order to keep evolving. When Pinterest eventually rolls out its monetization strategy, image detection technology will no doubt play a key role in delivering relevant ads to targeted users.
