Keywords only get you so far when descriptors like “black dress shoes” apply to hundreds or even thousands of products. Advertising Continue reading below Enter visual search, which aims to change the way we find products online. Unlike image search (which returns images for a textual query) or reverse image search (which often relies on metadata to get matching results), visual search uses pixel-by-pixel comparisons to return results with similar brands, styles and colors. As Linda Bustos says in her GetElastic article, “Visual search 'reads' images to identify color, shape, size and proportions, even text to identify brand and product names. This offers an advantage over keyword research, in which the results are only as good as the searcher's ability to describe hair masking service them. " Visual search on Pinterest Visual search is not new. Google bought Like.com in 2010, and even before that the technology was used by Zappos. But a platform that quickly became a favorite haunt of e-commerce sites didn't embrace visual search technology until late 2015. Naturally, I'm talking about Pinterest. For many online retailers, Pinterest is a home away from home. With over 100 million monthly active users, an integrated “Buy Now” button, and its “promoted pins” advertising unit, Pinterest has expanded the reach of many brands and introduced them to a whole new audience. Advertising Continue reading below Now, Pinterest has also implemented a visual search feature: Sometimes you spot something you really like on Pinterest, but you don't know how to find it in real life, or what it's even called… Eh well, we now have a new tool that lets you find all those things you don't have the words to describe. » This new search method allows users to click the visual search icon at the top of their screen and then click any object in an image. Pinterest then automatically filters through similar pins, showing users where they can buy products related to the one that caught their eye.