Texture features extraction technology using grey level co-occurrence matrix for the k-nearest neighbor classification of citrus disease: an agro-economic analysis

The citrus disease is a problem affecting the decrease of agricultural commodity yields. One way to determine in through leaves. Leaves, as place for photosynthesis, with will cause stunted plant growth. This study revolves around an Agro-economic Analysis classify diseases based on leaf images by applying Gray Level Co-occurrence Matrix (GLCM) extraction technology using K-Nearest Neighbor (KNN). To meet that aim, Otsu Thresholding segmentation carried out separate disease’s image from healthy experiment was Yogyakarta, Indonesia over year 2020, and 345 leaves were collected divided into three classes: canker, greening, healthy. Citrus classification has four main stages, namely pre-processing, segmentation, feature extraction, classification. Comparisons are made normalization dataset KNN distance used. Given results, without gets best results Hassanat (k = 29) accuracy 91.86%. A receives at Euclidean 7) 98.84%. These affirm efficiency this method distinguishing diseases. As result, can contribute improving quality crops reducing unnecessary expenses pesticides, finally could play role economics development.