Inspiration
We wanted to create an app that contributes to a cleaner environment by reducing landfill waste. SmartScrapper empowers users to make a positive impact on the environment while promoting responsible waste management practices.
What it does
SmartScrapper simplifies sorting waster and promotes sustainability. Users can take a picture of their waste and the app's AI analyzes the image and categorizes it as trash, recycling, or compost. The app then displays the category with clear instructions on how to dispose of it.
How we built it
To create the model, we sourced a publicly available datasets on Kaggle, containing thousands of labeled images of various waste materials. We fed the dataset into Create ML, allowing it to learn the patterns and characteristics of different waste categories. We tested the model's performance using a separate set of images, evaluating its accuracy in categorizing waste. We iteratively refined the model, adjusting parameters and training techniques to improve its accuracy and efficiency. Then we integrated this model into our app using XCode and Swift.
Challenges we ran into
It was difficult and time-consuming to integrate our Custom Create ML model into our code on XCode. We also had to train and change our dataset multiple times for accurate results. It was difficult to get the notification to appear at a exact time and schedule the 2 minute timer.
Accomplishments that we're proud of
We're proud of having a successful ML Model that can categorize waste.
What we learned
We learned how to use CreateML to create a custom Machine Learning Model.
What's next for SmartScrapper
We plan on training our model even further so that it can recognize more types of waste.
Log in or sign up for Devpost to join the conversation.