Feature selection from crop image for disease detection

Abstract

The foundsation of human sustenance in this world is agriculture. In order to meet demand in today's world of expanding population, agriculture must greatly boost its output. A serious threat to the safety of the world's food supply is plant disease. Each year, plant diseases cause 10 to 16 percent of the world's crop production to be lost. In 2050, the Food and Agriculture Organization (FAO) predicts that there will be 9.1 billion people on the planet. To meet the full food needs of a population that is steadily rising, agricultural productivity must be boosted by up to 70%. However, the overuse of pesticides like fungicides, bactericides, and nematicides to treat plant diseases has had negative impacts on the agro-ecosystem. Effective early disease detection methods are currently needed to control plant diseases for food security and the sustainability of the agro-ecosystem. Feature extraction is a particular kind of dimensionality reduction used in pattern recognition and image processing. Feature extraction is the process of turning a set of features from the input data. A feature for an image is the area that piques the viewer's interest. These characteristics are crucial to categorisation. Color, shape, and texture features are frequently used as image features in image processing. In order to distinguish one class of objects from another, the features are required. The approach must be utilised to describe the items in a way that draws attention to important characteristics. The description focuses on identifying features in an image. So, features like texture, area, and colour are retrieved to accurately identify diseases and manage their control.