Archives of Phytopathology and Plant Protection · 2021 · 93 citations · 40 references
AgricultureComputer SciencePlant PathologyComputer VisionMachine LearningPlant Disease DiagnosisBlight DiseasesDeep LearningDisease AssessmentDisease DetectionDisease DiagnosisTransfer LearningCrop Disease ClassificationDeep Learning-based DetectionDeep Learning-based DiagnosisEarly DiagnosisMachine Learning Diagnostics
There is an incredible progress in machine learning applications in the field of agricultural research. Detection of various diseases, deficiencies, and factors impacting crops’ productivity is one of the major ongoing research in this field. This paper considers various machine learning and deep learning techniques (transfer learning) for rice disease detection. In this study three different rice diseases viz. bacterial blight, rice blast, and brown spot are considered. A detailed comparative analysis of the results indicates the superiority of transfer learning techniques over conventional machine learning techniques. It is observed that InceptionResNetV2 achieves the best result followed by XceptionNet. This work can be incorporated in assisting the farmers for early diagnosis of rice disease so that future course of action may be taken on time. For future studies, efforts should be directed to work with bigger datasets so as to generalize the findings of the experiment.
40
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
null · Philosophy study · 2016 · 28.3K citations · Full text
Xception: Deep Learning with Depthwise Separable Convolutions
François Chollet · 2017 · 19K citations
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard, Menglong Zhu, Bo Chen et al. · arXiv (Cornell University) · 2017 · 9.9K citations · Full text