Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal KLIK: Kajian Ilmiah Informatika dan Komputer
Teuku Muhammad Johan
Universitas Almuslim, Bireuen
Computer Science & IT

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

Found 1 Documents
Search

 1 
Klasifikasi Citra Ikan Menggunakan Algoritma Convolutional Neural Network dengan Arsitektur VGG-16 Imam Muslem R; Teuku Muhammad Johan; Luthfi
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 2 (2023): Oktober 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i2.1209

Abstract

The development of technology in the field of image processing has inspired this research which aims to overcome challenges in classifying fish images using a Convolutional Neural Network (CNN) based approach. In this research, we utilize the VGG-16 architecture, a CNN model that has been proven capable of retrieving important features from images with significant depth. The dataset consists of 1088 fish images divided into four classes: Bangus, Glass Perchlet, Gold Fish, and Gourami. The initial process involves feature extraction via image embedding using the VGG-16 architecture. Next, a classification model is built using the Orange Data Mining tool. The experimental results show that this approach is able to provide good classification performance with significant accuracy in recognizing different fish species. The use of VGG-16 enables powerful and complex feature extraction, and experimental results show that this approach achieves a training accuracy of 96.2%. Furthermore, when the classification process uses data testing, this method produces an accuracy of 99.5%. This finding shows the great potential of the Convolutional Neural Network in overcoming the challenge of classifying fish images with very satisfactory results, which can be applied in various fields including marine science and remote sensing.
Co-Authors Luthfi Muslem R, Imam