Challenge

With user-generated content playing a large role in their app’s game mechanics, Pixide needed a solution that would provide a highly-scalable, quick-to-implement system for automatically categorizing user-generated images to enhance the user experience.

In the Pixide app, photographers are encouraged to share their pictures and rate others’ submissions. The goal of the app’s picture rating algorithm is to remove the “popularity contest” element that exists on other social networks (e.g. celebrities getting the most “likes” even though their photos may not be great). This is achieved by directly comparing a series of photos side-by-side to surface the best one. By creating a purely skill-based competition on who can take the best shot, Pixide is able to build a stronger, more engaged online community that recognizes photographers for their work.

Solution

In order to create a fair competition comparing apples to apples, Pixide used Clarifai’s computer vision technology to automatically categorize photos so they could be grouped by similar content and surfaced to app users for comparison and rating.

Using Clarifai’s computer vision product, Pixide was able to create a “sticky” gamified experience based on the ability for the user to directly compare photos of similar subject matter and choose the best one. Once a photographer uploads a photo to the platform, Clarifai’s API automatically recommends relevant and accurate categories and tags to the user.