Ml Based Farming System – Casava Leaf Disease Detection

Ml Based Farming System – Casava Leaf Disease Detection

Authors -AAssistant Professor J. Sunanthini, J. J. Charles Lifrin Packiyam

Abstract- – The ML-based farming system for cassava leaf dis- ease detection proposes a solution to automate the identification and diagnosis of diseases affecting cassava plants. This system leverages machine learning (ML) techniques to analyse images of cassava leaves and accurately classify them into healthy or diseased categories. The proposed system employs convolutional neural networks (CNNs), a type of deep learning architecture, for robust and efficient leaf disease detection. A dataset of la- belled cassava leaf images, comprising both healthy and diseased samples, is collected and used for model training. The CNN model is trained on this dataset to learn the visual patterns and features associated with different cassava leaf diseases. During the inference phase, new images of cassava leaves are fed into the trained CNN model, which predicts the presence or absence of diseases. The ML-based system provides a quick and reliable assessment of the leaf health status, allowing farmers to take proactive measures such as targeted treatments or removal of diseased plants to prevent further spread. The proposed system offers several advantages over traditional manual diagnosis methods. It eliminates the need for human experts, reducing the time and expertise required for disease identification. Additionally, the ML model can handle large volumes of data, making it scalable for real-time monitoring of large- scale cassava farms. The ML-based farming system for cassava leaf disease detection has the potential to significantly improve the efficiency and productivity of cassava farming. By enabling early disease detection and intervention, farmers can implement appropriate disease management strategies, minimize yield losses, and optimize crop health. Overall, the ML-based farming system offers a reliable and cost-effective solution for cassava leaf disease detection, empowering farmers with timely and accurate information to make informed decisions and safeguard their crop health.

DOI: /10.61463/ijset.vol.11.issue2.391