Abstract:

Agriculture plays a crucial role in India due to the quick population growth and increased request for food. Therefore, it is crucial to implement strategies and techniques that can effectively enhance crop production and ensure higher harvest yields. Plant disease caused by microorganisms, infections, and organisms poses a significant threat to agriculture and can result in low crop yield. The field of agriculture relies heavily on plant disease investigation as a crucial task in the cultivation process. Using manual methods to monitor and detect plant diseases is a complex and challenging task that can be alleviated through the utilization of plant disease detection techniques. It requires a significant amount of manual labor and extensive planning time, which makes the task of monitoring and identifying plant diseases extremely challenging. The utilization of image processing techniques in the detection of plant diseases offers a viable solution to the labor-intensive and time-consuming nature of manual monitoring and care-taking. The process of plant disease classification with machine learning algorithms involves several key phases, including dataset construction, where a collection of images representing healthy and diseased plant leaves is assembled. The mentioned steps: dataset creation, loading pictures, preprocessing, segmentation, feature extraction, training classifier, and classification are essential components of the machine learning algorithm. In this study, the primary aim is to develop a prototypical that can effectively differentiate among healthy and diseased crop plants and provide predictions for various plant diseases. The authors of this study have developed and implemented a prototypical to effectively classify and identify specific crop species as well as detect and diagnose 26 different types of diseases from public datasets of healthy and diseases plant leaves. This paper focuses on the utilization of the ResNets algorithm in the context of plant disease classification and detection

Description:

Machine Learning, ResNet, Plant Disease, Pre-processing, Feature Extraction, Detection, Classification