DETEKSI PENYAKIT TANAMAN CABAI BERBASIS DEEP LEARNING MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK SECARA REAL TIME

Mulyana Prayoga, Yogi
Wahyuni, Deasy
Elisawati

Jurnal UNITEK
Vol. 18 No. 2 (2025): Juli-Desember 2025

Chili peppers are a high-value horticultural commodity in Indonesia but are vulnerable to various plant diseases such as curly leaves, gemini virus, anthracnose, wilt, whitefly infestation, and armyworms. Early detection of these diseases is essential to prevent significant yield losses. This study aims to develop a chili disease detection system using a deep learning approach with a Convolutional Neural Network (CNN) architecture, specifically employing the MobileNet model, which is known for its efficiency in image classification tasks. The system is designed to operate in real-time using a device camera. Development follows the Waterfall model of the Software Development Life Cycle (SDLC), encompassing planning, analysis, design, implementation, and testing phases. Testing results indicate that the system achieves high accuracy in distinguishing between healthy and diseased chili leaves. This system is expected to assist farmers in early detection and prompt preventive actions, ultimately supporting increased productivity in chili cultivation.