Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal SKANIKA: Sistem Komputer dan Teknik Informatika
Beri Perima
IIB Darmajaya, Fakultas Teknik Komputer
Computer Science & IT Control & Systems Engineering Engineering

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

Found 1 Documents
Search

 1 
VISUALISASI DAN ANALISIS HISTOGRAM WARNA PADA CITRA PENYAKIT BSR UNTUK MENDUKUNG TAHAP PRA-PEMPROSESAN CITRA Beri Perima; Chairani Chairani
SKANIKA: Sistem Komputer dan Teknik Informatika Vol 9 No 2 (2026): Jurnal SKANIKA Juli 2026
Publisher : Universitas Budi Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36080/skanika.v9i2.3781

Abstract

Basal Stem Rot (BSR) is an important disease affecting oil palm plants that can reduce productivity. Image-based analysis can support disease detection, but color distribution characteristics need to be understood before the classification stage. This study aims to analyze the color distribution of oil palm leaf images from Healthy and BSR classes using histograms in the RGB and HSV color spaces and to evaluate the discriminative ability of color features. The dataset consisted of 2,438 images obtained from the open Roboflow repository. Each image was processed through 224×224-pixel resizing, Gaussian Blur, RGB-to-HSV conversion, and extraction of 12 statistical parameters consisting of mean and standard deviation. Differences between classes were tested using the Mann–Whitney U test, while the magnitude of differences was measured using Cohen’s d. The discriminative ability of G_Mean, S_Mean, and V_Mean was evaluated using the Receiver Operating Characteristic (ROC) and Area Under the Curve (AUC). The results showed significant differences among the three features (p-value = 0.0000) with large effect sizes. The AUC values for G_Mean, S_Mean, and V_Mean were 0.9794, 0.7362, and 0.9790, respectively. These findings indicate that color distribution analysis can identify discriminative features to support feature selection and BSR image preprocessing design.
Co-Authors Chairani Chairani