Inspiration
"Created by Anh Hoang, Abinai Pasunuri, Jason Yao, and Leeta Geltser \n\n At the start of this hackathon, we were told that at the end of every meal there would be a special bin to collect foodstuffs for composting. We were instructed to be very careful about what we threw into the bin, as any contaminants would ruin the composting job, resulting in simply more garbage. But the average person may not be aware of what items are compostable, what they should throw away, and what they should recycle. Thus, we have set out to develop an app which employs machine learning to help users classify rubbish so they a deposit it in the correct receptacle. We hope that our app will improve the efficiency of composting and recycling so that we throw away and pollute less.
What it does
The app allows a user to take a picture of an object and it will detect if an item is an electronic, compostable, or recyclable.
How we built it
This app was entirely built in Java and Android Studio Platform.
Challenges we ran into
The main challenges we ran into was getting the data from the Machine Learning platform and using this to detect the characterization of the object.
Accomplishments that we're proud of
We are proud that we were able to get a basic functioning app that is able to do some basic image detection given the dictionaries that were provided to the Machine Learning Model.
What we learned
We learned a lot about advanced Front End Development and a lot more about using APIs, Machine Learning and how Machine Learning models are trained and developed.
What's next for Recycle It!
The next step for Recycle It! is to be able to integrate deep learning within the platform. Currently, we were successfully able to use the Machine Learning API with large dictionaries of objects that are recycable. We want to integrate deep learning so the Machine Learning Model can be trained to automatically detect these images without the need to parse through the given data.
Log in or sign up for Devpost to join the conversation.