A Review for Palm Oil Fresh Fruit Bunch Ripeness Detection Methods Using Computer Vision
Savant Benedict1, Ricky Candra1, Suharjito1,2, Novita Hanafiah2

1School of Computer Science, BINUS Graduate Program - Master of Computer Science, Bina Nusantara University, Jakarta, Indonesia 11480
2Computer Science Department, BINUS Online Learning, Bina Nusantara University, Jakarta, Indonesia 11480

Abstract

One of the determining factors for the quality of palm oil is the level of maturity of the oil palm fruit at harvest. There have been many studies to be able to help the process of determining the maturity of oil palm fruit when harvested. The approach that is often used in determining the level of maturity is based on the color of the fruit using a computer vision approach. There are still many challenges faced with this approach such as lighting, shooting angles, and characteristics of the oil palm fruit. This study aims to review several methods that have been used to determine the maturity of oil palm fruit in order to find out which methods and stages are most optimal to implement efficiently. The method used for this study using a systematic literature review approach. the data used is based on articles published in the last five years (2015 - 2020) from well-known databases such as IEEE, Elsevier, and Google Scholar. The results of this study indicate that the development of an oil palm fruit maturity detection model using machine learning and deep learning approaches produces good performance and tends to have a lot of research leading to the use of this approach. However, in this perspective, there are still some obstacles such as the need for a large enough dataset and a highly capable machine so that further research is needed so that we can get a deep learning model that is lightweight and can be implemented in mobile applications.

Keywords: Palm Oil Fresh Fruit Bunch- Ripeness Detection- Methods- Computer Vision- deep learning

Topic: Computer Science