Design and Development of a Coffee Bean Selector Using The Yolo Algorithm

Abstract

The enjoyment of brewed coffee is determined by many things, one of which is choosing quality coffee beans and coffee powder. Quality coffee beans are determined by shape and size (full, half full, or damaged). Checking the size and shape of coffee beans manually is subject to external influences such as fatigue, environment, light, etc. With the help of technologyimage processing, these factors can be overcome. Through this paper a tool is designed to detect coffee defects using the Yolo algorithm. The designed system consists of a camera that captures images of coffee beans which are then processed by the Raspberry Pi and the results are displayed on the laptop screen. Detection results using the YOLO algorithm for 10 trials using 100 coffee beans get an average percentage value of 76.54% for the perfect coffee bean category of 43 coffee beans, then the average percentage of imperfect coffee beans is 73.40% with lots of 48 3 coffee beans and coffee beans were not detected with an average percentage value of 1% and coffee beans included in the two categories were 6 coffee beans with an average percentage value of 19.8%. In this study the YOLO algorithm can maintain an accuracy rate of detection success of 75%.

Eggplant Disease Detection Using Yolo Algorithm Telegram Notified

“…The advantages of this Python program are that it is easy to learn, can run programs with many complex functions in it easily, uses less code, and is even able to change programs. with a high level of complexity becomes easy [23]. However, python also has drawbacks, namely, it is quite slow to run, lacks support for Android and IOS, has limitations in database access, and is also not suitable for doing multi-core / multi-processor work [24].…”