Implementation Of Automated Purity Grading System for Dry Coconuts Using Machine Learning

Dry coconut, also known as copra, is a raw material used in the coconut oil industry for food, cosmetics, and pharmaceuticals. The purity of copra determines the quality of coconut oil, so grading has to be accurate. Traditional manual sorting methods are labor- intensive, inconsistent, and prone to errors. To overcome these challenges, this study proposes an Automated Purity Grading System using Machine Learning. The system uses a CNN to classify images of dry coconuts and determine if they are pure or impure. It has a Raspberry Pi-based setup with an integrated camera and conveyor belt that does sorting in real time, reducing errors in classification. The CNN model used is trained and optimized with TensorFlow Lite for effective grading that is both consistent and costeffective. This helps decrease the reliance on humans while making coconut processing efficient. Larger datasets and sensor integration for improved classification are the future improvements.