Abstract:
Plant leaf disease detection and classification is one of
the interesting research areas in the agriculture sector. An
approach based on image processing and machine learning
techniques is proposed in this paper to detect and classify paddy
leaf diseases. Leaf Blast, Brown Spot and Bacterial Leaf Blight
diseases are considered to calculate the performance of this
proposed methodology. Colour thresholding is applied to
identify the disease area in the paddy leaf. Hence, various
feature categories such as colour, texture, and shape features
are extracted from the affected area of the diseased image.
Support Vector Machine (SVM) and k-nearest neighbors (k-
NN) algorithms are used as classifiers and the performances of
the proposed methodology are evaluated using these classifiers.
The experimental results are compared with state-of-the-art
work approaches. Our proposed approach achieves 89.19%,
82.86%, and 89.19% of accuracy for detecting the rice plant
diseases such as leaf blight, brown spot and leaf blast
respectively.
