Arecanut Disease Detection Using Deep Learning
Ghanshyam Puneeth Kumar1, Ajey2, Preethesh3, Spoorthi4
1Master of Computer Applications & Shree Devi Institute of Technology, Kenjar, Mangalore
2 Master of Computer Applications & Shree Devi Institute of Technology, Kenjar, Mangalore
3 Master of Computer Applications & Shree Devi Institute of Technology, Kenjar, Mangalore
4 Master of Computer Applications & Shree Devi Institute of Technology, Kenjar, Mangalore
Abstract - Arecanut cultivation is central to the agricultural economy in South India. Farmers find significant challenges due to unhealthy crop that cause crop outputs and cause losses to agri culture. Disease detection using current practices is done by manual inspection carried out by agricultural experts or farmers. Traditional practices are plagued by a number of limitations, including late identification, a chance occurrence of human error, and a shortage of experts in farming areas. This work shows an automatic way of finding diseases that utilize machine learning tech nology. Wecreated a framework effective of dealing with digital photographs of arecanut plants for commondiseases. It employs imageprocess methods andaneuralnetworktoautonomously detect patterns indicative of disease. The present study engaged in the acquisition of images from regional agricultural opera tions and the subsequent training of a computational model designed to differentiate between healthy and diseased plant specimens. We evaluated the system’s performance concerning three predominant arecanut diseases: fruit rot, bud rot, and yellow leaf disease. The findings indicate that our developed system achieves disease detection accuracy exceeding 90 percent across all identified disease categories. The operational benefits include accelerated identification of diseases, reduced specializa tion dependency, and cost-effective monitoring for agricultural producers. It can be imple mented on handheld devices, making it available to producers who operate in isolated commu nities. Its future development will include a focus on creating user-friendly mobile applications and extending the system to cover other categories of diseases.
Key Words: Arecanut Cultivation, Crop Disease Detection, Machine Learning (ML), Convo lutional Neural Network (CNN), Image Processing, Fruit Rot, Bud Rot, Yellow Leaf Disease, Precision Agriculture, Mobile Application
