ABSTRACT
Nowadays, disease damage engenders maximal drawbacks in the farming sector, especially in rice crops, since it moderately decreases the yield plus minimizes health conditions of the paddy plant. During the period of intensive cultivation, the earliest and most accurate diagnosis of the rice plant diseases would help to limit damage, eventually resulting in environmental protection and an improved yield. Crop infections can be nematodes, fervid, fungal, or bacterial, which will deface the crop drastically. In this chapter, we present the plan of rice crop infection identification with the aid of leaf photographs. In this chapter, we propose a prototype for the image classification and detection of diseased rice plant leaves. This work is presented after an all-inclusive experimental investigation of multiple techniques that are used in image processing. The proposed work considers rice crop infection, explicitly brown spot, leaf blast, and bacterial leaf blight. The proposed work uses the traditional classification techniques, namely Decision Tree, Random Forest, Support Vector Machine, and Naive Bayes. Hence, to advance the accurateness of the classifier, various learning techniques are proposed to classify the rice plant diseases. It is easy to draw out knowledge from a smaller dataset, as the data size upsurge analysis of the data becomes demanding.
