SCANBAGE

Inspiration

What can single person do contribute to make our planet more sustainable? What small things things can we do which when everyone does them, make a big change to this planet? The treatment of personal household waste and recycling have a big impact on both CO2 emissions and well-being in public spaces We want to increase awareness for the impact of proper waste treatment and make recycling fun and easy.

What it does

A Web App to sort your waste via scanning the uploaded images
Classifies the waste material in the image into 6 categories :
1. Cardboard
2. Glass
3. Metal
4. Paper
5. Plastic
6. Trash
The results of tells if the item should be recycled, composted, put into the general trash or needs special treatment (hazardous materials)
Tells the information on how much CO2 emission they avoided

How was it built

Pre-Trained image detection model DenseNet-121
DenseNet-121 is pre-trained on ImageNet to distinguish 1000 classes of objects
Dataset is trained using VGG16 Transfer Learning Technique of CNN for the classification

Challenges we ran into

The main issue was the deployment. as the dependencies slug size was quite large and normal bugs and errors during the project.

Accomplishments that we're proud of

Our garbage material detection algorithm has an accuracy of ~80%! We worked very hard as a team, learning different skills to bring together the project right until the last minute. We were able to use our strength, individually, and share them with each other. And we feel happy that our project has the potential to help our ailing planet