Article Per Year (5 Year)
p-Index From 2020 - 2025
0.702
P-Index
This Author published in this journals
All Journal Jurnal Media Infotama Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Journal of Practical Computer Science (JPCS) Jurnal Media Computer Science
Setyowati, Cindy
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Practical Computer Science (JPCS)

 1 
Perancangan Sistem Prediksi Penyakit pada Tanaman Padi Berbasis Image Processing Menggunakan Algoritma VGG-16 Transfer Learning dan K-Means Segmentation Hidayat, Jose Julian; Setyowati, Cindy; Werdana, Aditya Pratama
Journal of Practical Computer Science Vol. 5 No. 1 (2025): Mei 2025
Publisher : DPPM Universitas Pelita Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37366/jpcs.v5i1.5759

Abstract

Early diagnosis of foliar diseases is essential for improving crop yields as diseases in rice plants can significantly affect agricultural production. By using Transfer Learning techniques on an enhanced VGG-16 model along with K-Means segmentation, this study suggests a deep learning-based approach for rice leaf disease diagnosis. Due to its outstanding ability to extract features from digital photos, VGG-16 was chosen to capture important information about the leaf surface that may indicate the presence of disease. To separate contaminated regions from the background and enable more precise and effective identification, K-Means segmentation was used as a preprocessing step. The dataset used in this experiment contains a wide variety of photos of different categories of diseases on rice plants. According to the experimental data, this approach can identify the type of disease on the leaves very accurately the accuracy can exceed 90%. By concentrating on key regions of the image, K-Means improves the detection performance. When compared to conventional methods, these results show how this combination strategy can improve the accuracy of rice leaf disease diagnosis. The use of this system is expected to help agronomists and farmers to monitor plant health efficiently, thereby increasing agricultural yields. In this study, the VGG-16 method and K-Means segmentation were combined to create a rarely used image-based automatic diagnosis system simultaneously on rice plants. This method has been shown to have higher accuracy than previous methods.
Co-Authors Amin, Muhammad Dikaisa Ibnu Bimasakti, Khodir Hidayat, Jose Julian Julian Hidayat, Jose Pratama Werdana, Aditya Werdana, Aditya Pratama