dCrop: A Deep-Learning Based Framework for Accurate Prediction of Diseases of Crops in Smart Agriculture

Pallagani, Vishal; Khandelwal, Vishal; Chandra, B Subhash; Udutalapally, Venkanna; Das, Debanjan; Mohanty, Saraju P.

doi:10.1109/ises47678.2019.00020

Cited by 44 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The possibility of using the technology of identification of crops by pathogens in the field is one of the necessary properties of the system for operational monitoring of diseases. In this direction, methods are being actively developed that integrate the results of prediction by the method of deep learning and the implementation of access to them via smartphones and tablets [ 48 , 49 , 61 , 62 ]. This, however, requires additional effort to build and maintain mobile applications.…”

Section: Discussionmentioning

confidence: 99%

“…This increases the efficiency of disease monitoring and, consequently, the chances of successful plant treatment by fungicides. One of the approaches is using mobile devices for this, both for semi-automatic determination of the degree of plant damage [ 58 ] and fully automatic analysis, including computer vision methods [ 59 , 60 ] and deep learning networks [ 48 , 49 , 61 , 62 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image-Based Wheat Fungi Diseases Identification by Deep Learning

Genaev

Сколотнева

Gultyaeva

et al. 2021

Plants

View full text Add to dashboard Cite

Diseases of cereals caused by pathogenic fungi can significantly reduce crop yields. Many cultures are exposed to them. The disease is difficult to control on a large scale; thus, one of the relevant approaches is the crop field monitoring, which helps to identify the disease at an early stage and take measures to prevent its spread. One of the effective control methods is disease identification based on the analysis of digital images, with the possibility of obtaining them in field conditions, using mobile devices. In this work, we propose a method for the recognition of five fungal diseases of wheat shoots (leaf rust, stem rust, yellow rust, powdery mildew, and septoria), both separately and in case of multiple diseases, with the possibility of identifying the stage of plant development. A set of 2414 images of wheat fungi diseases (WFD2020) was generated, for which expert labeling was performed by the type of disease. More than 80% of the images in the dataset correspond to single disease labels (including seedlings), more than 12% are represented by healthy plants, and 6% of the images labeled are represented by multiple diseases. In the process of creating this set, a method was applied to reduce the degeneracy of the training data based on the image hashing algorithm. The disease-recognition algorithm is based on the convolutional neural network with the EfficientNet architecture. The best accuracy (0.942) was shown by a network with a training strategy based on augmentation and transfer of image styles. The recognition method was implemented as a bot on the Telegram platform, which allows users to assess plants by lesions in the field conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Image-Based Wheat Fungi Diseases Identification by Deep Learning

Genaev

Сколотнева

Gultyaeva

et al. 2021

Plants

View full text Add to dashboard Cite

show abstract

“…For example, in the work [50], using a PlantVillage dataset and the authors' data, a two-stage network architecture was developed which showed an average accuracy of disease recognition of 0.936. In the work [40], the problem of simultaneous identification of 14 crop species and 26 diseases was also solved on the basis of the PlantVillage dataset. The network of the ResNet50 architecture was used, which achieved an accuracy of 99.24%.…”

Section: Discussionmentioning

confidence: 99%

“…The possibility of using the technology of identification of crops by pathogens in the field is one of the necessary properties of the system for operational monitoring of diseases. In this direction, methods are being actively developed that integrate the results of prediction by the method of deep learning and the implementation of access to them via smartphones and tablets [29,28,39,40]. This, however, requires additional effort to build and maintain mobile applications.…”

Section: Discussionmentioning

confidence: 99%

“…This increases the efficiency of disease monitoring and, consequently, the chances of successful plant treatment by fungicides. One of the approaches is using mobile devices for this, both for semi-automatic determination of the degree of plant damage [36] and fully automatic analysis, including computer vision methods [37,38] and deep learning networks [29,28,39,40].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image-Based Wheat Fungi Diseases Identification by Deep Learning

Genaev

Сколотнева²,

Gultyaeva

et al. 2021

Preprint

View full text Add to dashboard Cite

Diseases of cereals caused by pathogenic fungi can significantly reduce crop yields. Many cultures are exposed to them. The disease is difficult to control on a large scale, thus one of the relevant approaches is the crop field monitoring, which helps to identify the disease at an early stage and take measures to prevent its spread. One of the effective control methods is disease identification based on the analysis of digital images with the possibility of obtaining them in field conditions using mobile devices. In this work, we propose a method for the recognition of five fungal diseases of wheat shoots (leaf rust, stem rust, yellow rust, powdery mildew, and septoria), both separately and in combination, with the possibility of identifying the stage of plant development. A set of 2414 images of wheat fungi diseases (WFD2020) was generated, for which expert labeling was performed by the type of disease. WFD2020 data are available freely at http://wfd.sysbio.ru/. In the process of creating this set, a method was applied to reduce the degeneracy of the training data based on the image hashing algorithm. The disease recognition algorithm is based on the convolutional neural network with the EfficientNet architecture. The best accuracy (0.942) was shown by a network with a training strategy based on augmentation and transfer of image styles. The recognition method was implemented by the authors as a bot on the Telegram platform, which allows assessing plants by lesions in the field conditions.

show abstract