A novel framework for semi-automated system for grape leaf disease detection

Plants play a significant role in our lives. They are the primary source of food. But when these are diagnosed with diseases, productivity reduces. Grape is an important fruit, which is rich in potassium and hence is advantageous in balancing fluids in our body. Manually recognizing disease symptoms in plants is difficult due to several factors, involving time consumption and cost. A semi-automated system is proposed for grape lead disease detection. In existing systems, less accuracy has been observed and optimization of the segmentation process, hybridized feature extraction and ensemble classification has been ignored for detecting the leaf diseases. So, we have stressed on hybridization of different feature extraction algorithms and machine learning classifiers for the accurate prediction of diseases. Hence, a very novel approach is proposed that focuses on all the important stages in computerized leaf disease detection - segmentation, feature extraction and classification. To segment the diseased regions in mages, we have utilized K means clustering which is optimized using Grey Wolf Optimization (GWO). For the extraction of features, a hybrid of different algorithms has been utilized. Here, we have utilized Law's mask, which involves a convolution process for extracting features and is an acknowledged feature extraction algorithm in machine learning. Grey Level Co-occurrence Matrix, Local Binary Pattern and Gabor features have been conjunct to create a hybrid approach for robust results. Later, a newly introduced powerful ensemble classifier is applied to classify the correct diseases. A total of four categories of grape diseases have been used for the research from the "PlantVillage" dataset - Leaf Blight, Black measles, Black rot and healthy. We have compared our approach to existing approaches for detecting diseases in grape leaves. Our approach has proved to be robust as compared to existing approaches and has revealed an accuracy of 95.69%.