Classification of Immature and Mature Coffee Beans Using RGB Values and Machine Learning Algorithms

Abstract

© 2020, World Academy of Research in Science and Engineering. All rights reserved. The practice of coffee farmers to harvest all coffee cherries when 75 % of it are full red in a coffee tree gave rise to immature coffee beans. Immature coffee beans are green and yellow coffee cherries which were harvested earlier before they turn fully red, in order to reduce the operating cost of the coffee farmers. This practice greatly lowers the grade of coffee. Visually immature and mature coffee beans are different. Immature coffee beans are darker in color. When they are mixed, it will be very difficult to distinguish one from the other by visual inspection. This paper is about using image processing to extract RGB color features of the mature and immature coffee beans and used the extracted RGB values for classification using the 23 machine learning classifiers of Matlab’s Classification Learner App. The best in terms of accuracy and speed in training is the Quadratic Support Vector Machine which has a value of 94 % and 0.62 seconds respectively.