Optimizing Okra Plant Disease Management with Image Analysis and Deep Learning

Abstract

Indian agriculture is a significant contributor to the nation's economy. The identification of agricultural diseases is a critical field of research nowadays. One of the issues that leads to a decline in crop quality and productivity is this one. To treat Okra plant disease as effectively as possible, this study explores the use of image analysis and deep learning approaches. Okra is a crucial crop for food security, but it is frequently afflicted by several diseases that can drastically lower crop output and quality. To treat Okra plant disease as effectively as possible, this paper discusses image analysis and deep learning approaches. The inspection in conventional disease control techniques can be time-consuming and prone to human mistakes. This article suggests a unique method for automatically identifying and diagnosing diseases in okra plants using deep learning algorithms and image analysis. A convolutional neural network (CNN), ResNet152v3, and Inceptionv3. Cropped photos of leaves are used in this instance, and after processing them, it will determine whether or not the crop is affected by the disease. If a condition is found, the sort of disease it is and possible treatments, such as chemicals or pesticides, are provided. The productivity and economic process will both rise.