Klasifikasi penyakit citra daun anggur menggunakan model CNN transfer learning VGG16

This study aims to classify the disease image on grape leaves using image processing. The segmentation uses the k-means clustering algorithm, the feature extraction process uses the VGG16 transfer learning technique, and classification uses CNN. The results of this study obtained the accuracy of the CNN model training of 99.50%. Testing using test data yields an accuracy of 97.25 % while using test image data outside the dataset obtained an accuracy of 95%. The designed image processing method is expected to be applied in designing a system to identify and classify disease images on grape leaves.