Foliar Disease Detection Using ML and Deep Learning

Preview this chapter:

Foliar Disease Detection Using ML and Deep Learning, Page 1 of 1

< Previous page | Next page > /docserver/preview/fulltext/9789815324099/chapter-43-1.gif

This research surveys the classification approaches that can be utilized to categorize plant leaf diseases. Contemporary farming practices have the potential to provide sustenance for the 7.6 billion individuals on the Earth. Despite the availability of sufficient food, some persist in experiencing malnutrition. Plant diseases have a negative impact on both the yield and the quality of the entire crop. Several obstacles need to be addressed during the development of an image-processing model for prediction or classification purposes. Identifying indicators of sickness visually might pose a challenge for farmers. Computerized image processing technology is employed to safeguard crops in large-scale settings by utilizing color information from leaves to identify damaged foliage. Several classification methods exist, such as support vector machine (SVM), probabilistic neural network, k-nearest neighbor classifier, genetic algorithm, and principal component analysis. Due to the potential for various input data to yield varying quality outcomes, the selection of a classification approach is consistently a tough task. Plant leaf diseases are commonly classified in several industries, such as agriculture, biotechnology, and scientific research.