Identification of Grape Plant Diseases Based on the Leaves using Naïve Bayes

One way to see the signs of disease in grapevines is a change in leaf color. Ordinary people detect diseases in grapevines only based on subjective vision. On this basis, we need a system that can help the layman to be able to detect diseases in grapevines based on the color of the leaves using the Naïve Bayes algorithm classification method. This algorithm uses simple calculations, so the process is carried out faster. In this study, testing was carried out using the Naive Bayes classification model with 800 training data and 160 validation data. The accuracy results obtained are 90% using the color historgram scenario on channel RGB interval 16 and GLCM with features of dissimilarity, correlation, homogeneity, contrast pixel spacing 5. 90% accuracy is also obtained in the color histogram scenario on channel HSV with interval 16 and GLCM with features of dissimilarity, correlation, homogeneity at pixel spacing of 5. Thus, it can be concluded that the Naive Bayes classification model can gain application in identifying diseases in grapevines through leaf color analysis.