Classification Of Rice Plant Diseases Using K-Nearest Neighbor Algorithm Based On Hue Saturation Value Color Extraction And Gray Level Co-Occurrence Matrix Features

This research aims to classify diseases in rice plants using the K-Nearest Neighbor (K-NN) algorithm based on Hue Saturation Value (HSV) color feature extraction and Gray Level Co-Occurrence Matrix (GLCM) texture. The main problem faced is how to identify the type of disease in rice plants automatically using digital images. Diseases such as Blight, Tungro, and Crackle often attack rice plants and require an accurate early detection system. Lack of understanding in recognizing disease symptoms manually often leads to errors in handling. For this reason, this research develops an image processing-based classification system that can detect diseases such as Blight, Tungro, and Crackle. The method used in this research is image processing which includes RGB to HSV color space conversion, texture feature extraction using GLCM, and classification using K-NN algorithm. The dataset consists of 240 images, divided into training data and testing data, namely 192 training data and 48 testing data. Tests were conducted by calculating accuracy at various values of the K parameter, namely K = 1, K = 3, and K = 5, to determine the effectiveness of the model in classifying plant diseases. The purpose of this study was to evaluate the accuracy of the system in identifying rice diseases and test the combination of HSV and GLCM features in improving classification performance. The results showed that using HSV and GLCM features together resulted in the highest accuracy at K=3 with an accuracy value of 75%. The system is expected to assist farmers in detecting plant diseases quickly and effectively, thus minimizing production losses and supporting agricultural sustainability