At Oracle OpenWorld, Enterprise Times talked with Jenny Griffiths MBE, Founder and CEO of Snap Tech. Snap Tech is a visual search engine that allows users to take an image of something they want and find it on the Internet. Amusingly, Griffiths describes it as finding dresses and guns. After all, who doesn’t want to make sure they can pack heat at the summer ball without it spoiling the line of their clothes.
You might think that taking a photo of a dress or a pair of shoes and then identifying it would be easy. As Griffiths points out, it is not. Distinguishing a dress from a group of people or a pair of shoes when looking at multiple sets of feet requires serious processing power and diversity of data. The latter is essential.
Snap Tech uses an AI to detect what is in a photo. This means access to a lot of images to build the visual engine. Just throwing images at the solution is not enough. While this is an approach that Snap Tech’s competitors use, Griffiths explains that it leads to poorly trained AI. Snap Tech prefers access to a retailers backend database so that it can pull all the data it needs. Getting them to agree this is not simple.
To hear what else Griffiths had to say, listen to the podcast.
Where can I get it?
obtain it, for Android devices from play.google.com/music/podcasts
use the Enterprise Times page on Stitcher
listen to the Enterprise Times channel on Soundcloud
listen to the podcast (below) or download the podcast to your local device and then listen the