Open AccessResearch on Melon Fruit Selection Based on Rank with YOLOv4 Algorithm
Author(s) -
Nur Azizah Eka Budiarti,
Sri Wahjuni,
Willy Bayuardi Suwarno,
Wulandari Wulandari
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2123/1/012036
Subject(s) - convolutional neural network , melon , ranking (information retrieval) , deep learning , selection (genetic algorithm) , computer science , artificial intelligence , rank (graph theory) , artificial neural network , mathematics , machine learning , algorithm , horticulture , biology , combinatorics
Melon is one of the most popular fruits that is exceptionally favoured in Indonesia because it can be consumed directly as fresh fruit or processed as juice or salad. To meet the national market demand, several technologies are used to increase production, one of which is fruit selection. Plants need to be pruned based on fruit size so that fruit quality is maintained. One of the new approaches to detect plant fruits is using deep convolutional neural networks. The goal is to build a melon fruit detection system based on fruit size ranking for selection reliability. Recent work in deep neural networks has developed an excellent object detector, namely the one-stage You Only Look Once (YOLO) algorithm. We used the YOLOv4 model, the fourth generation of YOLO with speed acceleration and detection accuracy better than the previous versions. In addition, eight model schemes were tested with three different hyper-parameters: batch size, iterations, and learning rate. It was found that Scheme G using batch size 64, iterations 2000, and learning rate 0.001 obtained the highest score for both F1-score and mAP with values of 84.47% and 87.68%, respectively. It can be said that the F1-score value is directly proportional to the mAP value.