Deep Learning and Machine Learning Based Efficient Framework for Image Based Plant Disease Classification and Detection

Abstract

Without agriculture, human existence would be inconceivable. A large percentage of the world's population relies on agriculture for their daily needs. In addition, it creates a big number of jobs in the area. Using traditional agricultural practices results in lower yields, which is the fault of farmers. Agriculture and allied sectors will continue to be critical to the economy's long-term growth and prosperity. Farming has a slew of challenges, including disease detection and control and crop monitoring and tracking. Farming with intelligence is a realistic option in many situations. Smart agriculture is now possible because to the internet of things and machine learning approaches. Computer vision, image processing, and machine learning techniques are used in the automated leaf disease diagnostic system to analyze photographs of diseased leaves. A farmer can make an educated choice regarding a plant illness thanks to automated disease detection equipment that speeds up the diagnostic process. A farmer had to first send the contaminated leaf to a pathology lab for confirmation of the illness, which was a tedious process. It is the purpose of this paper to propose a framework for the real-time classification of agricultural images. Crop disease pictures categorization and illness prediction are made easier using this system.