Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal EDUMATIC: Jurnal Pendidikan Informatika
Chandra, Adrian
Unknown Affiliation
Computer Science & IT Education

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Soybean Seed Quality Classification using Magnitude-Enhanced Multiple Channel LBP and SVM Chandra, Adrian; Yohannes, Yohannes
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i1.33519

Abstract

Soybean is a major source of plant-based protein The quality of soybean seed affects resulting food. Therefore, image processing for classifying soybean seed quality is needed. Previous studies mainly used handcrafted or deep learning features and not evaluated local texture representations that using magnitude information for multi-class problems with high visual similarity. Traditional texture descriptors such as LBP or GLCM mainly using sign-based or global statistics and have limitations in representing colour-texture variations. This study aims to classify soybean seed quality using SVM with Multiple Channel Local Binary Pattern (MCLBP) and its enhanced variant with magnitude information (MCLBP+M) for feature extraction by utilizing correlations between colour channels through multi-radius approach. The dataset used is Soybean Seeds includes five classes: intact, spotted, immature, broken, and skin-damaged. This research conduct dataset splitting using 10-fold cross validation, data balancing (SMOTE), feature extraction, SVM model training and testing, and performance evaluation. The results show that MCLBP+M with Lab colour space and RBF kernel achieves accuracy of 86.30%, precision of 86.32%, recall of 85.99%, and F1-score of 86.07%. The results show that magnitude information in MCLBP+M consistently stable and improves classification performance across colour spaces and kernels, making it suitable for soybean seed quality classification.
Co-Authors Yohannes, Yohannes