Nowadays, technologies deliver to humankind the ability to produce enough food for billions of people over the world. Even though the world is producing a huge amount of crops to ensure food security of the people, there are a lot of factors that are threats in the process of ensuring food security. The threats that occur on crops can be with climate changes, pollinators, and plant diseases. Plant diseases are not only threats to global food security, but they also have devastating consequences on smallholding families in Ethiopia, who are responsible for supporting many, in one family. Crop reduction is the major problem the world is facing currently, and solving this with artificial intelligence detection methods has been the major challenge of experts on the efficiency of the algorithms, because of the nature of the of the diseases to be identified on the crops. Convolutional neural network is showing a promising result, especially in computer vision. This paper elaborates on implementation of deep learning (convolutional neural networks) using the RGB value of the color of the disease found on the crop, which increases the efficiency of the model.
CITATION STYLE
Olana, M. D., Rajesh Sharma, R., Sungheetha, A., & Chung, Y. K. (2021). Applying Deep Learning Approach for Wheat Rust Disease Detection Using MosNet Classification Technique. In Lecture Notes in Networks and Systems (Vol. 173 LNNS, pp. 551–565). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-33-4305-4_41
Mendeley helps you to discover research relevant for your work.