Plant diseases are one of the major factors affecting crop yield. Early identification of these diseases can improve productivity and save money and time for the farmer. This paper presents a novel technique to diagnose plant diseases using a mobile application. A Convolutional Neural Network (CNN) model was built and trained using MobileNetV2 architecture with the help of image processing techniques and transfer learning. A dataset comprising 87,000 images that contain 38 classes of diseases belonging to 14 different crops was used to train the model. The model achieved an accuracy of 98.69% and a loss of 0.5373. A mobile application was built in Android Studio with the help of a trained model. The mobile application built works without a need for a remote server. The application can identify the disease, gives information regarding the identified disease and also suggests necessary remedies to tackle the disease.
Agriculture is one of the primary occupations in many countries. Tomatoes are grown by many farmers in countries where the water resource is available in abundance. Improper methods of cultivation and failure to identify the diseases when it is in the nascent stage results in the reduction of crop yield thus affecting the outcome of cultivation. This paper proposes a novel method of early identification of diseases in tomato plants by making use of convolutional neural networks (CNN) and image processing. Dataset from an open repository was considered for training and testing and the algorithm was capable of identifying nine different varieties of diseases that affect the tomato plant at its early stages. The images of tomato leaves were fed for identification through processing and classification. An optimum model was developed by analyzing various architectures of CNN including the VGG, ResNet, Inception, Xception, MobileNet and DenseNet. The performance of each of these architectures was compared and various metrics like the accuracy, loss, precision, recall and area under the curve (AUC) were analyzed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.