An iOS sticker-making app
StickerBox is a cross-messenger app that creates stickers based on your own face with the help of artificial intelligence.
Feb 2017 - Apr 2017
Cross-Messenger Sticker Maker
UI, UX, Desktop, Web, Strategy, User Research
The app will automatically recognize the face, cut out the background, and make a fancy sticker.
They help you to create a sticker that will make all your friends laugh and reflect the emotions perfectly.
Once saved, the stickers appear on a custom keyboard and can be shared regardless of any particular messenger.
StickerBox works s as easy as can be: the only thing you have to do is to take a picture, AI will do the rest.
Our team got inspired by Slack and its ability to create custom emojis. This activity became one of our favorite corporate pastimes. Also, seeing the reaction of our teammates when we showed them emojis made out of their photos was hilarious. In less than no time, we come to the conclusion: if we enjoy it so much, other people might too.
Chief Technology Officer
The app was designed to be as simple as possible for users to easily interact with the app, regardless of their device.
Here is the list of technologies and tools to bring our idea to life:
After the app recognizes the face with all its features, StickerBox’s artificial intelligence will cut out the background flawlessly to insert the face into a template.
The app contains an enormous amount of premade templates for you to create stickers and all of them drawn by our own team from scratch.
Sync with messengers
When stickers are complete, they are displayed on a custom-made keyboard, so you can share them literally in any messenger regardless of the mobile platform.
Challenges and Solutions
While creating StickerBox, we faced some development challenges that we were happy to resolve.
We needed technology that would find a face and hair in a photo, separate them from the rest of the body, and cut them out from the background for further use without redundant pixels.Solution:
We tried several mathematical algorithms like Canny Edge Detector and Graham scan, but they didn’t perform well enough, so finally we stopped at a self-learning neural network that completely met the requirements.
When we launched the app, we thought users would like to make custom stickers and change them the way they want. Soon after release, we found out they were much more amused with the sticker templates provided by the app since it was easier than manual editing.
We removed most of the customization features and released a version offering ready-made stickers with just one button click.
An iOS sticker maker that works with any messenger Available worldwide