Please use this identifier to cite or link to this item:
Title: Investigating YOLO Models for Rice Seed Classification
Authors: Phan, Thi Thu Hong
Ho, Huu Tuong
Hoang, Thao Nhien
Keywords: Rice seed classification
Deep Learning
Issue Date: Jul-2023
Publisher: Springer Nature
Abstract: Rice is an important staple food over the world. The purity of rice seed is one of the main factors affecting rice quality and yield. Traditional methods of assessing the purity of rice varieties depend on the decision of human technicians/experts. This work requires a considerable amount of time and cost as well as can lead to unreliable results. To overcome these problems, this study investigates YOLO models for the automated classification of rice varieties. Experiments on an image dataset of six popular rice varieties in Vietnam demonstrate that the YOLOv5 model outperforms the other YOLO variants in both accuracy and time of training model.
Description: Lecture Notes in Networks and Systems (LNNS, volume 734); CITA: Conference on Information Technology and its Applications; pp: 181-192.
ISBN: 978-3-031-36886-8
Appears in Collections:CITA 2023 (International)

Files in This Item:

 Sign in to read

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.