Plant Leaf Disease Classification and Prediction Using a Customized Deep Transfer Learning Model

Main Article Content

Chandrika Bhargavi Achanta, Kavuru Devi Keerthi, Sujatha Kamepalli

Abstract

There is a significant productivity, financial damage due to plant diseases, and diminished overall quality of farm products. Detecting plant diseases has become more important in the surveillance of vast fields of crops in the modern-day. When it comes to disease management, farmers have difficulty transitioning from one strategy to another. The conventional method for detecting and identifying plant diseases is professional naked-eye inspection. This research examines the necessity for a simple technique for detecting plant leaf disease that would aid agricultural innovations. Early knowledge of crop health and disease detection may facilitate effective monitoring tactics. Crop yields will rise as a result of this method. In addition, the advantages and drawbacks of each of these prospective approaches are discussed in this study. Image capture, image analysis, extraction of features, and categorization based on neural networks are all part of the process. We get the best result to help the farmers through the processed methodology by implementing this model. The resulted accuracy of the implemented model is 81.09492659568787%. The proposed work enhances the farming culture to predict certain diseases and get a good yield of crops.

Article Details

Section
Articles