Vegetation indices based segmentation for automatic classification of brown spot and blast diseases of rice

Automatic identification of plant diseases is the new challenging area for the researchers. One of the most important steps in automatic identification of plant diseases is to extract the infected region from the normal portion of the plant. Studding the infected leaves it has been observed that the greenness of the infected portion of the leaves changes significantly with respect to the normal leaves. Vegetation indices (VI) [] are some metric used for the remote sensing images to measure the greenness. Thus VIs are computed from the acquired images of the infected plant. These VI are then used to extract the infected portion from the acquired visual images. Among the available VI Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Enhanced Vegetation Indices (EVI), and Soil Adjusted Vegetation Index (SAVI) are used in the proposed work. Images of the rice leave infected by leaf blast (caused by pathogen Magnaporthe grisea) and brown spot (caused by pathogen Bipolaris oryzae) diseases are acquired using the digital cameras. Then above mentioned vegetative indices are computed to get efficient segmentation. Otsu's method has been applied on the VI images to extract the infected portions. Then five different texture features namely Homogeneity, Correlation, Contrast, Energy and Entropy of the infected regions are computed. These feature values are then used for classifying the diseases using 15 different classifiers (such as: naïve Bayes, SVM, Part, J48 classifiers, etc.) available in WEKA tool. Among these VI, EVI gives the best average result. Not only that, to measures the efficiency of the VIs, features are also extracted from the infected region without converting it to the VI, which shows the efficiency of the proposed method.