Deep Convolutional Neural Network for Diseases Diagnosis on Plants

Abstract

Using a deep convolutional neural network helps users to diagnose diseases on plants quickly and accurately. This also helps the process of disease treatment and care become better, reduces the time, cost, and contributes to improving the quality of agricultural products. This paper proposes a new model base on Convolutional Neural Network (CNN) and transfer learning for identifying and diagnosing diseases on plants. The proposed model also has been compared with the models VGG19, ResNet50 and DenseNet12. The highest accuracy of 95% was achieved from the proposed model. The measurement of F1-Score also gives the same result.