PENERAPAN CONVOLUTIONAL NEURAL NETWORK UNTUK KLASIFIKASI CITRA PENYAKIT DAUN KOPI

Indonesia’s coffee industry plays a crucial role as a significant export, significantly contributing to the country’s economy by generating foreign exchange. The quality and quantity of coffee production depend on humidity, rain, and fungus that can cause rust diseases on coffee leaves. This disease can spread quickly and affect other coffee plants’ quality, decreasing production. To address this issue, utilized the CNN method with the VGG-19 architecture model to identify coffee plant diseases using image data and the Python programming language, which used MATLAB as their platform in previous studies. In addition, VGG-19, with contouring data for the pre-processing step, has a more profound learning feature than the method used in previous studies, AlexNet, which makes the structure of VGG-19 more detailed. The dataset used in this paper is Robusta Coffee Leaf Images Dataset, which has three classes: health, red spider mite, and rust. The VGG-19 model attained an F1-Score level of 90% when evaluated using the testing data with a ratio 80:20, of which 80% is training data and 20% is validation as testing data. This paper employed a 0.0001 learning rate, batch size 15, momentum 0.9, 12 training iterations, and RMSprop optimizer.