Dissertation on detection of plant leaf diseases by utilizing multiclass support vector machine

Abstract

Agriculture is an essential component of our economy and food security, but it is threatened by various factors, including plant diseases. Leaf diseases are a common problem in agriculture, and they can have a significant impact on crop yields and quality. Leaf disease detection and management are crucial for sustainable agriculture, and there are various methods to achieve this. One of the most promising methods is leaf disease detection using image processing. This technique involves capturing digital images of plant leaves and analysing them to identify disease symptoms. Plant leaf disease detection is an important task in agriculture to prevent the spread of diseases and increase crop yield. With the advancement of machine learning techniques, automated systems have been developed to detect and diagnose plant leaf diseases. Leaf disease detection using image processing and machine learning algorithms to identify the symptoms of diseases on the leaves of plants. The technique involves acquiring an image of a plant leaf, processing the image to extract features, and classifying the image based on the features. The input images are pre-processed, and the features are extracted using various techniques such as convolutional neural networks (CNN), support vector machines (SVM), and decision trees. The extracted features are then used to train the machine learning model, which can classify new images as healthy or diseased. The accuracy of these models varies depending on the quality of the input images and the size of the dataset. Additionally, the technique can help farmers make informed decisions about when and how to treat their crops, leading to improved yields and reduced costs.