Amazon's StyleSnap helps you copy favourite fashion from photos

  • Amazon is investing in a new app feature to help customers replicate a fashion look they have seen in magazines or on Instagram.

    The new artificial intelligence (AI) based feature is called StypeSnap. Customers can upload a photograph or screenshot of an outfit to it, and Amazon will then search its own site for similar items to suggest for the customer.

    The technology was launched at Amazon’s re:MARS 2019 conference, where worldwide consumer CEO Jeff Wilke said the “simplicity of the customer experience belies the complexity of the technology behind it,” according to The Verge.

    Related jobs

    The fashion giant Asos, homeware store Wayfair, and U.S. retailer Target all have similar tools in place but the technology is still in its early days.

    StyleSnap will use “computer vision” and “deep learning” to identify apparel pieces in a photo, Amazon said in a statement to the press. This technology is apparently inspired by the working of the human brain.

    Amazon said: “Neural networks are made up of millions of artificial neurons connected to each other, and can be ‘trained’ to detect images of outfits by feeding it a series of images. For example, if we feed a network thousands of images of maxi and accordion skirts, it will eventually be able to tell the difference between the two styles.”

    The company also stated that this means it will be able to detect different styles, shapes, and patterns like fit-and-flair dresses or flannel shirts.

    This isn’t the first time Amazon has tried to break into fashion technology. In 2017 the company introduced the Echo Look, an AI-powered camera that gave users fashion recommendations. However, it received some mixed reviews. It has also tried rolling out private-label brands and launching Prime Wardrobe, a try-before-you-buy service. Most recently, it launched The Drop, a new fashion shopping experience that offers on-demand products available for purchase for only 30 hours at a time.

    In a study on online shopping orientations, Seock and Bailey discovered that women visited more websites and contrasted different options more thoroughly than men. Put simply, women take longer when shopping, and prefer browsing. This would suggest that women tend to be more visual, hedonic shoppers, with young women in particularly being increasingly influenced by social media.

    StyleSnap thus seems geared towards Amazon's growing Influencer Program, which lets high-profile Instagram ‘influencers’and bloggers make money by recommending Amazon items. Business Insider reported that some influencers receive a commission as high as 10% for items they recommend from the company's private fashion line. However, Amazon has still struggled to get women to shop for clothes on its platform. The Amazon data platform JungleScout revealed that roughly 80% of the site’s private-label female clothing lines sell less than 100 units per month.

    StyleSnap is being referred to by some as the Shazam for fashion, but there has been no confirmation yet as to when the feature will become available.

    Read more here for Sync NI's view at how technology such as Amazon's is shaping the future of retail. 


    Source: Engadget

    About the author

    Niamh is a Sync NI writer with a previous background of working in FinTech and financial crime. She has a special interest in sports and emerging technologies. To connect with Niamh, feel free to send her an email or connect on Twitter.

    Got a news-related tip you’d like to see covered on Sync NI? Email the editorial team for our consideration.

Share this story