Chapter 7 - Utility system for premature plant disease detection using machine learning

Abstract

The lives of humans are ever changing due to the evolution in tools, techniques, and technologies all over the world, which is thereby aiding and contributing to the growth and well-being of societies globally. Agriculture is the backbone of most countries not only in terms of feeding the population, but also accounting for a large part of the gross domestic product (GDP). In a developing nation like India, where 17% of the GDP is derived from agriculture, technologies assist a long way in achieving this. A prominent concern in agriculture is diseases of plants that impact food production and the health of humans and animals. There are no efficient methods to detect these diseases from their outset. The task of detection of different kinds of diseases in plants is still carried out with the naked eye. This is a tedious process that consumes more time without great accuracy, and so automation of this process is required. On that note, using image processing is a better technique and solution for plant disease detection. It takes into consideration features which may not be detected by sight. With the application of these techniques, such as enhancing the image and extracting features, the type and severity of disease in a plant can be identified. There exists a plethora of works related to automatic disease detection in plants, specifically with respect to the use of techniques like image processing and modeling techniques including neural networks with the help of drone technology. Some of these have been described briefly. Also, a new system capable of detecting any disease, irrespective of the plant species, is implemented that employs support vector machine and image processing techniques.