Rifat Islam
Research Details
Thesis Name
Sugarcane Leaf Disease Prediction and Recognition Using Meta Deep-LearningThesis Abstract
This research aims to develop an intelligent vision solution for early detection and prediction of sugarcane leaf diseases, crucial for enhancing crop yield and reducing production costs in Australia. Utilizing Meta Deep Learn model and leaf image data, the study focuses on accurately classifying healthy and diseased leaves. Comparison with CNN, VGG-16, and VGG-19 Transfer Learning models will be conducted. The outcome will include a web application for public access
Why My Research is Important/Impacts
This research is crucial as it addresses the pressing need for early detection and prediction of sugarcane leaf diseases, which can significantly impact crop yield and production costs. By employing an intelligent vision solution utilizing the Meta Deep Learn model, farmers can efficiently monitor large production areas, enabling timely intervention and management decisions. Anticipated impacts include enhanced disease management, reduced production costs, and improved yield stability. Moreover, the development of a web app for public use will democratize access to this technology, benefiting farmers and agricultural stakeholders nationwide.
Funding/Scholarship
International Excellence Award by CQUniversityPartners
CodersBucket Ltd.
