Inspiration We were inspired by the machine learning capabilities and we wanted to utilize it and analyzing pictures.
What it does
It analyses pictures from Google storage and does various things: It detects landmarks, text, and facial emotion If there are facial emotions, it outputs the most frequent emotion in the pictures.
How we built it
We first used javascript using Google Vision API to teach ourselves how it works and after that we decided to use C# to create this program.
Challenges we ran into
Being unfamiliar with C# and javascript. Various test cases that broke the code.
Accomplishments that we're proud of
The whole program, learning how to use Vision API, and learning C# on our own.
What we learned
We learned how to use Google's Cloud Shell and it's various services that we could use like the Vision API.
What's next for Image Recognition
We are going to further improve the code and hopefully the final product would let a user snap various photos and the program will detect the overall mood of the entire gallery.
Log in or sign up for Devpost to join the conversation.