KLASIFIKASI KEMATANGAN BUAH SAWIT BERBASIS WEBSITE MENGGUNAKAN DEEP LEARNING

Abstract

Oil palm fruit is one of the main agricultural commodities in Indonesia. The maturity level of the fruit significantly influences both the quality and quantity of the oil produced. Manual determination of fruit maturity is still frequently carried out; however, this method is subjective and inefficient. This study aims to develop a web-based application for classifying the maturity level of oil palm fruit using artificial intelligence. The model employed is a Convolutional Neural Network (CNN) with the ResNet50V2 architecture, trained on a dataset of oil palm fruit images categorized into three maturity levels: unripe, ripe, and overripe. The model was then integrated into a web-based application using the Flask framework as the user interface. The test results show that the model is capable of performing classification with high accuracy and fast response time. The application enables users to upload images of oil palm fruit and automatically obtain classification results through a responsive web interface. The implementation of this technology can enhance accuracy, objectivity, and efficiency in the process of determining fruit maturity. The findings of this study indicate that artificial intelligence-based systems hold great potential for supporting the harvesting process in the palm oil industry.

Keywords: Image Classification, ResNet50V2, Convolutional Neural Network, Web Application