Use of RESNET-50 Neural Network in Diagnosing Diseases Mango Leaves

Abstract

Using a state-of-the-art convolutional neural network, specifically RESNET-50, for disease diagnosis on mango leaves is the focus of this research. The end goal is to develop a trustworthy method of mango plant disease detection using leaf image analysis. The approach used comprised gathering a sizable dataset encompassing a range of mango leaf diseases. Afterward, a classification system was developed by training the RESNET-50 model on image data. The system is able to learn extraordinarily intricate and profound visual patterns in pictures of mango leaves thanks to RESNET-50's deep and complicated architecture, which improves feature extraction. With a Test Accuracy of 99.16% and a Test Loss of only 0.4332, the results demonstrate a very reliable system. This impressive level of precision verifies that the system is capable of correctly distinguishing and categorizing mango leaf diseases. Consequently, this case demonstrates promising agricultural applications of the RESNET-50 model and offers a dependable and effective means of disease detection in mango plants. This study adds to the growing body of knowledge that can aid agricultural professionals and farmers in the early detection of disease symptoms on mango leaves, allowing for the prompt implementation of preventative measures. These findings also have broader implications, such as the potential for better agricultural productivity and management brought about by the use of comparable technologies for disease analysis in different crops.