Social and Environmental Impact of a Plant Disease Analysis Method Based on Object Extraction

Abstract

Plant leaf infections are a common threat to global production in both the long and short terms, affecting not only many farmers but also consumers around the world. Early detection and treatment of plant leaf diseases are essential to promote healthy plant growth in agriculture and ensure sufficient supply and health security for the world’s geometric (population) growth. Detection of plant leaf diseases using computer-aided technologies is widespread today. In the first part of this thesis, we describe an artificial intelligence (AI) model that enables image analysis to facilitate disease detection and then present its contribution at the societal level. We used images of maize leaves and images of apples in fields from the standard PlantVillage repository for object localization. An efficient deep learning (DL) modified mask region convolutional neural network (Mask R-CNN) is proposed for autonomous segmentation and detection of the object to be analyzed in this research. The proposed work exploited the features learned by the Mask R-CNN model at various processing hierarchies. We achieved improved code generation of singular images of the detected objects and an overall accuracy of 98.89% on the validation sets. In the rest of our research, we wanted to show the impact of our solution at a social level while highlighting the important aspects that characterize good development. The specificity of this approach is to present the different AI solutions used for the analysis of agricultural crops, with the aim of highlighting their benefits and their impact on human activities.