Words of the World

Inspiration

Our inspiration was accessibility of language learning around the globe. We wanted to create an app that would allow the user to scan an item into the app through the camera, allowing the user to learn about the objects right in front of them. We also planned on mapping routes for people to follow to learn a specific set of vocabulary, like foliage or shops. Our main goal was to make integrating with a language barrier into a community easier.

What it does

This app can take photos or use pictures from the camera roll on a phone and locate and label the objects depicted within the picture. The app would also be able to tell the user how to pronounce the word on the screen.

How we built it

We used tools from Microsoft's vision API to detect objects & indicate what they were to users.

Challenges we ran into

Turning python code into javascript was a challenge for our group, and implementing the API software in javascript was also a challenge. We tried multiple different API softwares for vision and text to speech and could not get most of them to work.

Accomplishments that we're proud of

We were able to implement the Microsoft vision API affectively after attempting to use multiple different devices. There were many challenges to overcome on a team of young hackers learning how to use API for the first time. We were absolutely thrilled when we got it to work, and could start making progress towards our goals.

What we learned

We learned how to work together to overcome challenges and to utilize the resources that we were given. We went to many workshops and reached out to mentors whenever we needed help.

What's next for Words of the World

We hope to implement a text to voice API to allow people to hear the words spoken to them in their target language. We also hope to eventually put the software into an app that will take pictures and access the camera roll.