Year: 2024
Type: article
Abstract: Palm oil plantations play a significant role in the economy of Indonesia, supporting 16.2 million people. However, plant diseases pose a major threat to the productivity and health of palm oil crops. Early detection of these diseases is essential to prevent yield losses and mitigate damage. This study proposes the application of the Complete Kernel Fisher Discriminant (CKFD) method combined with Color Difference Histogram to classify diseases affecting oil palm fronds and leaves. The CKFD method uses a non-linear kernel transformation to improve the performance of Fisher Linear Discriminant Analysis (FLDA), while the Color Difference Histogram enhances sensitivity to color variations in different lighting conditions. Experimental results demonstrate that the CKFD method achieves superior accuracy in disease detection compared to traditional Convolutional Neural Networks (CNN) and Support Vector Machines (SVM). The proposed approach showed an average accuracy of 94.5% for detecting diseases like Curvularia sp and Cochliobolus carbonus. The combination of CKFD with Color Difference Histogram significantly reduces the impact of lighting variations on the classification results, making it a robust solution for practical deployment in palm oil plantations. This research provides an effective tool for early disease detection and management in the palm oil industry.
Source: SinkrOn
Authors: Johanes Terang Kita Perangin Angin, Herman Herman, Joni Joni
Institution: STMIK TIME
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: gold
Estimated APC paid: $32
OpenAlex ID: W4404372885