Machine Learning Techniques for Leaf Analysis in Plant Disease Detection

Abstract

A country's productive innovation is tied to its agriculture sector. Agriculture, the "mother" of all human
societies, is the source of food and building materials. We rely heavily on it as a food source, thus its importance
cannot be overstated. As a result, plant diseases pose a serious challenge to society. Pests and diseases affecting
plants might occur at any moment. It's possible for this to occur between planting and harvesting. The market's
economic worth has dropped significantly as a result. Consequently, the ability to identify leaf diseases is crucial
in the agricultural industry. Thus, conventional approaches were utilized for illness detection. However,
conventional leaf disease diagnosis relies only on the trained eyes of agriculturalists and plant pathologists.
Using this approach for disease detection in plant leaves was labor intensive, time consuming, expensive, and
needed a deep understanding of plant pathogens. Software solutions that have been evaluated experimentally can
now automatically identify and categorize plant leaf diseases. The process of new evolution is aided by machine
learning. Plant diseases are being detected using machine learning. Machine learning is a branch of AI used to
train computers to carry out certain tasks without human intervention. Machine learning's primary objective is to
decipher and incorporate the training data into models that will be of service to humans. Therefore, plant illness
may be identified using machine learning.