How do you categorize large volumes of user-generated content?
Pixide is an online platform that allows photographers to share their pictures and compete with their peers in weekly photo contests.
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.
“Clarifai allowed us to validate our idea and build a market-ready product without the large technical overhead and time cost of building everything in-house.” – Stefano Giacone, CEO and Co-Founder of Pixide
Pixide used Clarifai to power its app’s game mechanics and create a more engaging 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.
In order to create a fair competition comparing apples to apples, Pixide used Clarifai’s visual recognition technology to automatically categorize photos so they could be grouped by similar content and surfaced to app users for comparison and rating.
Automatically “see” and understand images
Using Clarifai’s visual recognition 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.
“Clarifai allowed us to build a better user experience and smarter app using visual recognition and machine learning. The Clarifai API is a cornerstone of how our app works.”
Serve the right content to the right users
With all user-generated content automatically categorized through Clarifai’s API, Pixide is then able to pair images of similar subject matter and surface them to users to vote on through the slick contest interface. This ensures that the rating mechanics enable users to discovering the “best” photos of the community and keep them coming back for more.
“Clarifai allowed us to find new ways to explore the world of photography.”
Quick and easy implementation
Pixide’s CEO and Co-Founder, Stefano Giacone, tested visual recognition APIs like Imagga, Microsoft Computer Vision API, and Google Cloud Vision API before deciding that Clarifai offered the best possible solution for launching his mobile app. He selected Clarifai based on its superior accuracy, customer support, easy-to-follow documentation and starters, and multi-language support. With a product team of six people, Stefano was able to integrate Clarifai in just a couple of days and take Pixide from concept to production rollout in nine months.
“It was simple and straightforward to get started with Clarifai and use the API to power our mobile app. We’re excited about Clarifai’s upcoming mobile SDK, which will allow us to tag and categorize user-generated photos even faster and provide an even smoother user experience!”
DIY with Clarifai
Now that you’ve been inspired by Pixide’s mobile app, it’s time to build your own app. Clarifai’s core modelincludes tags for over 11,000 concepts you can apply to your business. Or, you can use Clarifai’s Custom Trainingsolution to teach our AI new concepts. All it takes is three simple lines of code – sign up for a developer API account to get started for free!