Plant leaf disease detection and classification using convolution neural networks model: a review

Abstract

Plants play a vital role in providing food on a global scale. Several environmental factors contribute to the occurrence of plant leaf diseases, leading to substantial reductions in crop yields. Nevertheless, the process of manually detecting plant leaf diseases is both time-consuming and prone to errors. Adopting deep learning technologies can address these challenges, and the efficacy of deep learning techniques in precision agriculture has been explored over the past decades. However, despite these applications, several gaps in plant leaf disease research still need to be addressed for efficient disease control. This paper, therefore, provides an in-depth review of the trends in using convolutional neural networks for leaf disease detection and classification. In addition, we also present the existing plant leaf disease datasets. It was found that convolutional neural network models, such as VGG, EfficientNet, GoogleNet, and ResNet, provide the highest accuracy in classifying plant leaf disease images. This review will provide valuable information for scholars who are seeking effective deep learning-based classifiers for plant leaf disease detection and classification.