Camellia sinensis disease Detection using GAN

Camellia sinensis disease Detection using GAN

 

 

Prof.Bhagath I

Computer Science and engg

KLS VDIT Haliyal

 

 

Anusha Nadiger

Compter Science and engg

KLS VDIT Haliyal

 

 

Prof.Nirmala G

Computer Science and engg

KLS VDIT Haliyal

 

 

 

Ayesha Mulla

Computer Science and engg

KLS VDIT Haliyal

 

 

Ankita Navalgund

Computer Science and engg

KLS VDIT Haliyal

 

 

Namita Rajputh

Computer Science and engg

KLS VDIT Haliyal

 

 

 

 

Abstract— this project focuses on developing an AI-driven solution for detecting diseases in tea leaves. By using Generative Adversarial Networks (GANs), we were able to create engineered pictures of unhealthy tea takes off, which made a difference  make strides the dataset and improve the execution of our illness discovery show. The Convolutional Neural Network(CNN) classifier precisely identified both healthy and diseased leaves. Additionally, we created a fertilizer recommendation system based on soil health factors like pH, nitrogen levels, and organic carbon, providing farmers with customized suggestions to improve soil quality and boost tea production. This combination of machine learning and agricultural insights offers a promising tool for early disease detection and better farming practices. Moving forward, we plan to refine the image generation process and integrate real-time soil data for even more accurate recommendations.

Keywords—camellia sinensis, GAN, image processing