2021
DOI: 10.1016/j.matpr.2020.11.993
|View full text |Cite|
|
Sign up to set email alerts
|

WITHDRAWN: A comparative analysis on plant pathology classification using deep learning architecture – Resnet and VGG19

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
10
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(10 citation statements)
references
References 12 publications
0
10
0
Order By: Relevance
“…The plant sciences have also steadily incorporated DL methods, with experimentation using DL algorithms providing superior performance relative to conventional ML algorithms in classifying plants and in detecting various plant diseases [26] , [27] , [28] . Convolutional Neural Networks (CNNs) have successfully classified plants [29] , [30] , [31] , [32] , [33] and identified diseased plants [34] , [35] , [36] . For example, a CNN-based approach DenseNet-77 gave better accuracy than SVM and K-Nearest Neighbors (KNN) in detecting diseased plants [35] .…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…The plant sciences have also steadily incorporated DL methods, with experimentation using DL algorithms providing superior performance relative to conventional ML algorithms in classifying plants and in detecting various plant diseases [26] , [27] , [28] . Convolutional Neural Networks (CNNs) have successfully classified plants [29] , [30] , [31] , [32] , [33] and identified diseased plants [34] , [35] , [36] . For example, a CNN-based approach DenseNet-77 gave better accuracy than SVM and K-Nearest Neighbors (KNN) in detecting diseased plants [35] .…”
Section: Introductionmentioning
confidence: 99%
“…For example, a CNN-based approach DenseNet-77 gave better accuracy than SVM and K-Nearest Neighbors (KNN) in detecting diseased plants [35] . CNN techniques have also been proven capable of differentiating plants according to species [27] , [31] , [32] , [33] , [37] . Recurrent Neural Networks (RNN) have also been successful in analyzing spatiotemporal data when paired with CNNs [38] , [39] , [40] .…”
Section: Introductionmentioning
confidence: 99%
“…11 In the field of image recognition, convolution neural networks have been proposed. A large number of scholars have worked in this field and built excellent neural networks, such as GoogLeNet, 12 ResNet, 13 and EfficientNet. 13 In particular, the ResNet-18 network structure, because of its simplicity and good performance, has been widely used and can achieve excellent results in weed classification and recognition tasks.…”
Section: Introductionmentioning
confidence: 99%
“…A large number of scholars have worked in this field and built excellent neural networks, such as GoogLeNet, 12 ResNet, 13 and EfficientNet. 13 In particular, the ResNet-18 network structure, because of its simplicity and good performance, has been widely used and can achieve excellent results in weed classification and recognition tasks. In the field of target detection, we need to use a large number of weed data to train the model.…”
Section: Introductionmentioning
confidence: 99%
“…As discussed by Guo et al (2016), there are many variations of the CNN methods, where the difference is basically in terms of the total number of convolutional layers. The CNN classifiers have demonstrated exceptional accuracy and precision in many agriculture applications (Khanramaki et al, 2021;Alhnaity et al, 2020;Ayan et al, 2020;Chouhan et al, 2019;Ferentinos, 2018;Habiba et al, 2019), including in the field of plant phenotyping (Fuentes et al, 2019;Wang et al, 2019;Subetha et al, 2021).…”
Section: Introductionmentioning
confidence: 99%