Revolutionizing Hops Plant Disease Classification: Harnessing the Power of Transfer Learning
Sheshang Degadwala, Dhairya Vyas, Sonia Panesar, D. Ebenezer, Darshanaben Dipakkumar Pandya, Vandita Dipak Shah
Abstract
This research work introduces an innovative approach for the classification of hops plant diseases through the utilization of transfer learning with state-of-the-art Convolutional Neural Networks (CNNs). By leveraging pretrained models on extensive image datasets, this study has developed a customized CNN architecture, which is specifically designed to address the unique challenges posed by hop plant diseases. Their method demonstrates remarkable accuracy in classifying multiple hop plant diseases, offering significant potential for early disease detection and precise management strategies. The paper also provides an insightful comparison of the effectiveness of each CNN architecture within the context of hops plant disease classification. This research has the potential to automate and enhance hops plant disease management, ensuring the sustainability and quality of hop crops for the brewing industry while providing a valuable framework for addressing similar agricultural challenges.