Background: Plastibot revolves around the development of a machine learning model designed to classify various types of plastic using photos captured by a hyperspectral camera. The project’s initial phase involves collecting data by cutting up plastic samples and subjecting them to the hyperspectral camera. The primary objective currently is to identify a ‘pivot,’ which could lead the project in one of two directions: refining machine learning methods to exclusively sort plastic or exploring alternatives, such as utilizing regular phone cameras and employing image processing techniques for plastic sorting.
Project Goal: The overarching goal of Plastibot is to advance plastic sorting technology through the application of machine learning. The project aims to develop a robust model that can accurately classify different plastic types based on hyperspectral camera data. Additionally, there is an exploratory aspect focused on researching the feasibility of using regular phone cameras and image processing for plastic classification. Through this, members involved in the project will gain foundational knowledge in machine learning and deep learning, with an emphasis on understanding how neural networks operate.
Focus Areas: Machine learning, hyperspectral imaging, image classification, data collection and analysis, algorithm development, image processing, neural network operation
Are you interested in joining the Plastibot team? Contact Joshmi or Yahav from the About page.