📚 This was an ML project for USC CSCI 467: Introduction to Machine Learning. My co-authors are Russell Tan and Pablo Tayun-Mazariegos. The premise is as follows:

♻️ Recycling is a well known solution to saving landfill space, however, many people do not know how or often make mistakes in sorting trash. Sorting recyclables before reaching the recycling facility is crucial for effective recycling as it keeps costs down by preventing clogged machinery and the need of manual sorting in the facilities. If contaminants were to pass, the final product would be deemed unsatisfactory and thrown into the landfill rather than being reused. This experiment's purpose is to help improve models designed to classify six different forms of waste: glass, cardboard, metal, paper, plastic and trash.

📦 The classifier, which consists of different CNN models, will take an image input containing a single piece of waste on a white background (or any solid color background). The model should then classify the object into one of six possible waste categories mentioned prior.

If you're interested in learning about our research findings, please do take a look at the PDF in this repo. Thanks for checking in 👋