Shweta V. Bondre, Kotadi Chinnaiah, Vipin D. Bondre
{"title":"Application of M-RCNN for prompt segmentation between infected tomato leaves and healthy tomato leaves","authors":"Shweta V. Bondre, Kotadi Chinnaiah, Vipin D. Bondre","doi":"10.1111/jph.13363","DOIUrl":null,"url":null,"abstract":"<p>Plant diseases have become a problem, as both the quality and quantity of agricultural products can be significantly reduced. The goal of the research is to detect the infection in the plant leaf so that it can be cured before spreading of disease to other plants. The aim of the research is to find out the severity of the leaf disease so that it can be cured based on the level of severity. Also, crop loss can be predicted by using the severity loss. For object localization, we utilize 10,640 tomato leaf images of various classes from the PlantVillage standard repository. As a baseline for future work, we propose a model based on the Mask R-CNN architecture with ResNet-50 as the backbone that effectively performs instance segmentation for these six diseases. The dataset is annotated by using the VGG annotator tool and this annotated dataset would have been used to train the ‘Mask R-CNN model’ and the ResNet50 backbone, fine-tuning the network's weights to accurately detect and segment diseased regions on leaves. The outcomes of the suggested model achieved an average accuracy of 91.3% by using multiple performance indicators like accuracy, precision and F1 score and Recall. Based on the outcome, the severity of the disease is being identified on a scale of 0, 1, 2 and 3.</p>","PeriodicalId":16843,"journal":{"name":"Journal of Phytopathology","volume":"172 4","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Phytopathology","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jph.13363","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PLANT SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Plant diseases have become a problem, as both the quality and quantity of agricultural products can be significantly reduced. The goal of the research is to detect the infection in the plant leaf so that it can be cured before spreading of disease to other plants. The aim of the research is to find out the severity of the leaf disease so that it can be cured based on the level of severity. Also, crop loss can be predicted by using the severity loss. For object localization, we utilize 10,640 tomato leaf images of various classes from the PlantVillage standard repository. As a baseline for future work, we propose a model based on the Mask R-CNN architecture with ResNet-50 as the backbone that effectively performs instance segmentation for these six diseases. The dataset is annotated by using the VGG annotator tool and this annotated dataset would have been used to train the ‘Mask R-CNN model’ and the ResNet50 backbone, fine-tuning the network's weights to accurately detect and segment diseased regions on leaves. The outcomes of the suggested model achieved an average accuracy of 91.3% by using multiple performance indicators like accuracy, precision and F1 score and Recall. Based on the outcome, the severity of the disease is being identified on a scale of 0, 1, 2 and 3.
期刊介绍:
Journal of Phytopathology publishes original and review articles on all scientific aspects of applied phytopathology in agricultural and horticultural crops. Preference is given to contributions improving our understanding of the biotic and abiotic determinants of plant diseases, including epidemics and damage potential, as a basis for innovative disease management, modelling and forecasting. This includes practical aspects and the development of methods for disease diagnosis as well as infection bioassays.
Studies at the population, organism, physiological, biochemical and molecular genetic level are welcome. The journal scope comprises the pathology and epidemiology of plant diseases caused by microbial pathogens, viruses and nematodes.
Accepted papers should advance our conceptual knowledge of plant diseases, rather than presenting descriptive or screening data unrelated to phytopathological mechanisms or functions. Results from unrepeated experimental conditions or data with no or inappropriate statistical processing will not be considered. Authors are encouraged to look at past issues to ensure adherence to the standards of the journal.