Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal International Journal Education and Computer Studies
Y Lamasigi, Zulfrianto
Unknown Affiliation
Education Languange, Linguistic, Communication & Media Library & Information Science Mathematics Other

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

Found 1 Documents
Search

 1 
Classification of Skipjack Freshness Quality Based on Local Binary Pattern and Gray Level Co-Occurrence Matrix Using K-Nearest Neighbor Y Lamasigi, Zulfrianto; Efendi Lasulika, Mohamad; Mooduto, Sarlis
International Journal Education and Computer Studies (IJECS) Vol. 5 No. 3 (2025): NOVEMBER
Publisher : Lembaga KITA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijecs.v5i3.5791

Abstract

Katsuwonus pelamis or skipjack tuna is one of the results of fishing commodities from Gorontalo Province. The quality of fresh fish can be degraded easily if not handled and stored properly. Thus, in this study an automatic system for classifying the freshness level of skipjack tuna based on digital image processing techniques was introduced. It uses Local Binary Pattern (LBP) to extract local texture features and Gray Level Co-occurrence Matrix (GLCM) for statistical texture analysis with classification done by K-Nearest Neighbor (K-NN) algorithm using Euclidean distance as a measurement between features. There were 819 training images and 140 test images used in four categories: Fresh, Not Fresh, Worth Consuming, and Rotten. Tests on several values of k showed that the highest accuracy was at k = 1 with an accuracy rate of 86.42% while the lowest was at k = 9 with a rate of 49.28%. This indicates that the combination LBP-GLCM applied in K-NN has potentiality to capture texture difference effect from various levels fish freshness. This method is non-destructive and could be onboard application for fish quality monitoring as well as automatic system for freshness evaluation.
Co-Authors Efendi Lasulika, Mohamad Mooduto, Sarlis