Identification of Madura Tobacco Leaf Disease Using Gray- Level Co-Occurrence Matrix, Color Moments and Naïve Bayes

Abstract

Abstract Indonesia is one of the world’s biggest tobacco crop producers. By tobacco farmer, this plant is often even dubbed “green gold”. Madura Island is one of the best tobacco-producing areas in Indonesia. Tobacco is a significant trading crop in the eastern part of Madura Island, specifically in Pamekasan and Sumenep. The decline in tobacco yields is usually caused by pests and diseases that attack tobacco plants. Experts can easily detect conditions in plants (including tobacco) with their eyes, but this is very suitable and requires expensive operational costs when the size of the planting area is vast, and the distance of the planting area is far from the location of the expert. So that digital image processing techniques need to be applied to detect tobacco plant diseases earlier. By using data in the form of photographs of tobacco plant leaves, the condition will be identified. The method used in this research is GLCM (Gray Level Co-Occurrence Matrix) texture feature extraction, while CM (Color Moment) colour feature extraction and Naïve Bayes method are used for classification. The results of testing tobacco identification obtained the best accuracy of 82.2% for Pamekasan tobacco and 84.4% for Sumenep tobacco. The best results are obtained by using the colour feature extraction.