We thought about a common problem with tourists, immigrants, and language barriers and those just wanting to learn another language. Shayna's actually been learning Mandarin and so having an app like this would be useful whether abroad or just hoping to get more practice.
The User takes a picture of an object with their phone's camera and it uses Google's object recognition API to figure out what is in the picture then processes it and passes the object's name into Googles translation API to translate that into a foreign language, so you can easily learn or ask about objects even when there is a language barrier.
We built the project using Android Studio and API's from Google Cloud. The language was entirely Java.
The biggest problem we faced was working with Android Studio and Google's API. We both had to learn how to use Android Studio while at Mhacks, and I personally had to learn Java. Another setback was a complete dud of a project as we hadn't fully looked into the capabilities of an API and thus found out it wouldn't be able to work for the project we had in mind. We also had a setback with Google's Translate API as it is a paid service, so we couldn't fully implement it.
We finished the project even with a ton of setbacks. We're just proud to have finished it by the deadline.
Google API--it's an invaluable tool to have, it has so much functionality to it, from image processing, to translation, to tracking.
For what's next, hopefully, get it fully functional even with the paid Translation API, tidy up the overall look of the GUI, and add in a language selection.
Log in or sign up for Devpost to join the conversation.