2020
DOI: 10.1007/s00500-020-04946-0
|View full text |Cite
|
Sign up to set email alerts
|

Automatic method for classification of groundnut diseases using deep convolutional neural network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
17
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 33 publications
(17 citation statements)
references
References 30 publications
0
17
0
Order By: Relevance
“…The initial image samples is presented in L*a*b after the samples get segmented with Kmeans clustering. [86], [87] The textural attributes gain with the help of Local Binary Patterns (LBP), local features extracted using Bag of Words (BoVW) algorithm and Speeded up Robust features (SURF), color features extracted using color moment technique. The final step is classification that is performed through supervised leaning classifier Support Vector Machine (SVM) that obtained the accuracy of 75.8% [89].…”
Section: Legumesmentioning
confidence: 99%
See 3 more Smart Citations
“…The initial image samples is presented in L*a*b after the samples get segmented with Kmeans clustering. [86], [87] The textural attributes gain with the help of Local Binary Patterns (LBP), local features extracted using Bag of Words (BoVW) algorithm and Speeded up Robust features (SURF), color features extracted using color moment technique. The final step is classification that is performed through supervised leaning classifier Support Vector Machine (SVM) that obtained the accuracy of 75.8% [89].…”
Section: Legumesmentioning
confidence: 99%
“…The features extraction and classification done using CNN Firstly the background is subtracting to gain only leaf area of these images. Then these images were train on CNN model SoyNet architecture, as compared to existing models the proposed model provide higher F1 score (97), precision (97), recall (97) and accuracy of 98.14% in soybean diseases recognition [92]. Soybean leaf disease present the a verity of characteristics that are local outbreaks and large impact, large variety thus an automate system is required to discover these diseases, to conduct the experiment the 1470 sample images were collected from a farm but these samples were not sufficient and led the model to overfitting.…”
Section: Legumesmentioning
confidence: 99%
See 2 more Smart Citations
“…Another CNN-based architecture was proposed to classify disease in the PlantVillage dataset, and it performed better than the well-known DL models including AlexNet, VGG-16, Inception-v3, and ResNet [19]. A recent article proposed a CNN-based model for the classification of groundnut disease [20]. Similarly, few studies focused on the advanced training techniques; for example, [21] evaluated the performance of AlexNet and GoogLeNet trained from scratch and transfer learning approaches.…”
Section: Introductionmentioning
confidence: 99%