Electronics: Identification of Plant-Leaf Diseases Using CNN and Transfer-Learning Approach
Electronics: Identification of Plant-Leaf Diseases Using CNN and Transfer-Learning Approach
Article
Identification of Plant-Leaf Diseases Using CNN and
Transfer-Learning Approach
Sk Mahmudul Hassan 1 , Arnab Kumar Maji 1, *, Michał Jasiński 2, * , Zbigniew Leonowicz 2
and Elżbieta Jasińska 3
1 Department of Information Technology, North Eastern Hill University, Shillong, Meghalaya 793022, India;
[email protected]
2 Department of Electrical Engineering Fundamentals, Wroclaw University of Science and Technology,
50-370 Wroclaw, Poland; [email protected]
3 Faculty of Law, Administration and Economics, University of Wroclaw, 50-145 Wroclaw, Poland;
[email protected]
* Correspondence: [email protected] (A.K.M.); [email protected] (M.J.)
Abstract: The timely identification and early prevention of crop diseases are essential for improving
production. In this paper, deep convolutional-neural-network (CNN) models are implemented to
identify and diagnose diseases in plants from their leaves, since CNNs have achieved impressive
results in the field of machine vision. Standard CNN models require a large number of parameters
and higher computation cost. In this paper, we replaced standard convolution with depth=separable
convolution, which reduces the parameter number and computation cost. The implemented models
were trained with an open dataset consisting of 14 different plant species, and 38 different categorical
disease classes and healthy plant leaves. To evaluate the performance of the models, different
parameters such as batch size, dropout, and different numbers of epochs were incorporated. The
Citation: Hassan, S.M.; Maji, A.K.;
implemented models achieved a disease-classification accuracy rates of 98.42%, 99.11%, 97.02%, and
Jasiński, M.; Leonowicz, Z.; Jasińska,
E. Identification of Plant-Leaf
99.56% using InceptionV3, InceptionResNetV2, MobileNetV2, and EfficientNetB0, respectively, which
Diseases Using CNN and were greater than that of traditional handcrafted-feature-based approaches. In comparison with other
Transfer-Learning Approach. deep-learning models, the implemented model achieved better performance in terms of accuracy
Electronics 2021, 10, 1388. and it required less training time. Moreover, the MobileNetV2 architecture is compatible with mobile
https://doi.org/10.3390/ devices using the optimized parameter. The accuracy results in the identification of diseases showed
electronics10121388 that the deep CNN model is promising and can greatly impact the efficient identification of the
diseases, and may have potential in the detection of diseases in real-time agricultural systems.
Academic Editor: Juan M. Corchado
Keywords: artificial intelligence; convolutional neural network; deep learning; machine learning;
Received: 24 May 2021
transfer learning
Accepted: 8 June 2021
Published: 9 June 2021
2. Related Work
The implementation of proper techniques to identify healthy and diseased leaves
helps in controlling crop loss and increasing productivity. This section comprises different
existing machine-learning techniques for the identification of plant diseases.
and analyzed performance. The authors reported better accuracy than that of a traditional
machine-learning-based approach.
Pretrained AlexNet and GoogleNet were used in [36] to detect 3 different soybean
diseases from healthy-leaf images with modified hyperparameters such as minibatch size,
max epoch, and bias learning rate. Six different pre-trained network(AlexNet, VGG16,
VGG19, GoogLeNet, ResNet101 and DenseNet201) used by KR Aravind et al. [37] to
identify 10 different diseases in plants, and they achieved the highest accuracy rate of
97.3% using GoogleNet. A pretrained VGG16 as the feature extractor and multiclass SVM
were used in [38] to classify different eggplant diseases. Different color spaces (RGB,
HSV, YCbCr, and grayscale) were used to evaluate performance; using RGB images, the
highest classification accuracy of 99.4% was achieved. In [39], the authors classified maize-
leaf diseases from healthy leaves using deep-forest techniques. In their approach, they
varied the deep-forest hyperparameters regarding number of trees, forests, and grains,
and compared their results with those of traditional machine-learning models such as
SVM, RF, LR, and KNN. Lee et al. compared different deep-learning architectures in the
identification of plant diseases [22]. To improve the accuracy of the model, Ghazi et al.
used a transfer-learning-based approach on pretrained deep-learning models [40].
In [41], the authors used a shallow CNN with SVM and RF classifiers to classify
three different types of plant diseases. In their work, they mainly compared their results
with those of deep-learning methods and showed that classification using SVM and RF
classifiers with extracted features from the shallow CNN outperformed pretrained deep-
learning models. A self-attention convolutional neural network (SACNN) was used in [42]
to identify several crop diseases. To examine the robustness of the model, the authors
added different noise levels in the test-image set.
Oyewola et al. [43] identified 5 different cassava-plant diseases using plain convolu-
tional neural network (PCNN) and deep residual network (DRNN), and found that DRNN
outperformed PCNN by a margin of 9.25%. Ramacharan et al. [4] used a transfer-learning
approach in the identification of three diseases and two pest-damage types in cassava
plants. The authors then extended their work on the identification of cassava plant diseases
using a smartphone-based CNN model and achieved accuracy of 80.6% [44].
A NASNet-based deep CNN architecture was used in [45] to identify leaf diseases
in plants, and an accuracy rate of 93.82% was achieved. Rice- and maize-leaf diseases
were identified by Chen et al. [2] using the INC-VGGN method. In their approach, they
replaced the last convolutional layer of VGG19 with two inception layers and one global
average pooling layer. A shallow CNN (SCNN) was used by Yang Li et al. [41] in the
identification of maize, apple, and grape diseases. First, they extracted CNN features and
classified them using SVM and RF classifiers. Sethy et al. [1] used different deep-learning
models to extract features and classify them using an SVM classifier. Using ResNet50 with
SVM, they achieved the highest performance accuracy. A VGG16, ResNet, and DenseNet
model was used by Yafeng Zhao et al. [46] to identify plant diseases from the plant village
dataset. To increase the dataset size, they used a double generative adversarial network
(DoubleGAN), which improved the performance results. A summary of the related work
on plant-disease identification based on leaf images is shown in Table 1.
Electronics 2021, 10, 1388 5 of 19
Table 2. Comparison among different CNN architectures regarding layer number and parameter size.
Parameters
Model No. of Layer Size
(Million)
AlexNet 8 60 -
VGGNet-16 23 138 528 MB
VGGNet-19 26 143 549 MB
Inception-V1 27 7 -
Inception-V3 42 27 93 MB
ResNet-152 152 50 132 MB
ResNet-101 101 44 171 MB
InceptionResNetV2 572 55 215 MB
MobileNet-V1 28 4.2 16 MB
MobileNet-V2 28 3.37 14 MB
EfficientNet B0 - 5 -
Convolutional neural networks became familiar in machine vision since the AlexNet
model was popularized in DL architecture. The development of the Inception model
was important in the field of machine vision. Inception is a simple and more powerful
DL network with sparsely connected filters, which can replace fully connected network
architectures, especially inside convolutional layers, as shown in Figure 1b. The Inception
model’s computational efficiency and number of used parameters are much lower in
comparison with those of other models such as AlexNet and VGGNet. An inception layer
consists of differently dized convolutional layers (e.g., 1 × 1, 3 × 3, and n × n convolutional
layers) and pooling layers with all outputs integrated together and propagating to the
input of the next layer. Instead of using standard convolution in the inception block, we
used depthwise separable convolution. Tables 3 and 4 show the required parameters in
standard convolution and depthwise separable convolution, respectively. The number
of parameters required in depthwise separable convolution is much less than that of
standard convolution.
Filter Concat
DS Conv
1 1
pointwise
1 1
pointwise
n n n n
depthwise depthwise 1 1
1 1 1 1 Pool 1 1
Base
Table 4. Required parameters using depthwise separable convolution in the Inception block.
Reduction B
Avg Pooling
Reduction A
Softmax
Dropout
Stem
Input
Relu Activation
Relu Activation
1 1 Conv
1 1Conv
3 3DS Conv
7 7DS Conv
3 3DS Conv 3 3DS Conv 1 1 Conv
1 1Conv
1 1 Conv 1 1 Conv 1 1 Conv
(a) (b)
Figure 3. (a) Modified structures of InceptionResnet-A. (b) Structures of InceptionResnet-B of
InceptionResNetV2 model.
Relu Activation
1 1 Conv
3 1 Conv
1 1 Conv 1 3 Conv
1 1 Conv
Relu Activation
The main intention behind the use of MobileNetV2 architecture is the convolutional
layer, which is quite expensive in normal convolutions in comparison with in MobileNetV2.
To improve efficiency, depthwise separable convolution is used in the MobileNetV2 archi-
tecture [51,52]. Depthwise convolution is independently performed for each input channel.
The blocks of MobileNetV2 are shown in Figure 1a. The first layer is called the expansion
layer of 1 × 1 convolution, and its purpose is to expand the number of channels in the
data. Next is the projection layer. In this layer, a high number of dimensions is reduced to a
smaller number. Except for the projection layer, each layer comprises a batch-normalization
function and activation function ReLU. In the MobileNetV2 architecture, there is one
residual connection between input and output layers. The residual network tries to learn
already learned features; those that are not useful in decision making are discarded. This
architecture can reduce the number of computations and of parameters. The MobileNetV2
architecture consists of 17 building blocks in a row followed by a 1 × 1 convolutional layer,
global average pooling layer, and classification layer.
A deep-learning architecture aims to achieve better performance accuracy and ef-
ficiency with smaller models. Unlike other state-of-the-art deep=learning models, the
EfficientNet architecture is a compound scaling method that uses a compound coefficient
Electronics 2021, 10, 1388 9 of 19
to uniformly scale network width, depth, and resolution [29]. EfficientNet consists of 8
different models from B0 to B7. Instead of using the ReLU activation function, EfficientNet
uses a new activation function, swish activation. EfficientNet uses inverted bottleneck
convolution, which was first introduced in the MobileNetV2 model, which consists of a
layer that first expands the network and then compresses the channels [52]. This archi-
tecture reduces computation by a factor of f 2 as compared to normal convolution, where
f is the filter size. The authors in [29] showed that EfficientNetB0 is the simplest of all 8
models and uses fewer parameters. So, in our experiment, we directly used EfficientNetB0
to evaluate performance. Figure 5 shows the basic block diagram of EfficientNetB0.
MBConv6 5 5
MBConv6 5 5
MBConv6 5 5
MBConv1 3 3
MBConv6 3 3
MBConv6 3 3
MBConv6 3 3
Conv 3 3
Conv1 1
Pooling
FC
Figure 5. Basic block diagram of EfficientNet model.
3.3. Dataset
For training and testing purposes, we used the standard open-access PlantVillage
dataset [53], which consists of 54,305 numbers of healthy- and infected-plant leaves. De-
tailed database information, the number of classes and images in each class, their com-
mon and scientific names, and the disease-causing viruses are shown in Tables 5 and 6.
The database contains 38 different classes of 14 different plant species with healthy- and
disease-affected-leaf images. All images were captured in laboratory conditions. Figure 6
shows some sample leaf images from the PlantVillage datasets [53].
In our experiment, we used three different formats of PlantVillage datasets. First, we
ran the experiment with colored leaf images, and then with segmented leaf images of the
same dataset. In the segmented images, the background was smoothed, so that it could
provide more meaningful information that would be easier to analyze. Lastly, we used
grayscale images of the same dataset to evaluate the performance of the implemented
methods. All leaf images were divided into two sets, a training set and the testing set.
To evaluate performance, we split leaf images into three different sets, namely 80–20 (80%
training images and 20% testing images), 70–30 (70% training images and 30% testing
images), and 60–40 (60% training images and 40% testing images).
Electronics 2021, 10, 1388 10 of 19
4. Results
The implemented CNN architectures, as described in the previous section, used the
parameters in Table 7. EfficientNetB0 achieved the best accuracy in comparison with
that of InceptionV3, MobileNetV2, and InceptionResNetV2. To evaluate performance, we
used different parameters, for example, performance accuracy, F1 score, precision, recall,
Electronics 2021, 10, 1388 12 of 19
training loss, and time required per epoch. As in our experiment, we used three different
representations (i.e., color, grayscale, segmented) of PlantVillage image data, which showed
different performance metrics in all cases. The color-image dataset performed better than
those with grayscale and segmented images; the same number of CNN network parameters
was maintained in all cases. Figure 7a–c shows the graphs for testing the accuracy, loss, and
F1-score regarding the number of epochs for the implemented models. Figure 7d represents
the accuracy graph of the InceptionResnetV2 model with different training and testing split
images. A summary of the performance comparisons of the implemented models based on
testing accuracy and testing loss is represented in Table 8. The performance metrics that
are considered in our proposed work are as follows.
• Performance accuracy: the total number of correctly classified images to the total
number of images.
• Loss function: how well the architecture models the data.
• Precision: the ratio of the number of correctly predicted observations (true positives)
to the total number of positive predictions (true positives + false positives).
• Recall: the ratio of correctly predicted observations (true positives) to all observations
in that class (true positives + false negatives).
• F1 score: the harmonic mean between precision and recall.
• Time requirement (in sec) per epoch for training each DL model.
Parameters Value
Training epoch 30–50
Batch size 32–180
Dropout 0.2–0.8
Learning rate 0.01–0.0001
To avoid overfitting, we phasewise divided the dataset into different training and
testing ratios. In the case of 80% of training and 20% of testing image data, we achieved an
accuracy of 98.42% in InceptionV3, 99.11% in InceptionResNetV2, 97.02% in MobilenetV2,
and 99.56% in EfficientNetB0 for color images. After splitting the dataset into different
training and testing ratios, there was not much variation in the accuracy of the models.
Hence, they did not suffer from the problem of overfitting.The accuracy of all models
for different image types with loss and number of epochs are shown in Table 9. Table 10
Electronics 2021, 10, 1388 13 of 19
presents the precision, recall, and F1 score of the implemented models on splitting the
dataset into 80–20% training and testing ratios. EffcientNetB0 had a precision value of
0.9953, recall of 0.9971, and F1 score of 0.9961, which were higher than those of the other
models.
Table 9. Accuracy and loss of implemented models regarding different image types along with
different train-test split ratios.
Deep-Learning
Precision Recall F1-Score
Model
InceptionV3 0.9836 0.9911 0.9873
InceptionResNetV2 0.9921 0.9961 0.9940
MobileNetV2 0.9732 0.9962 0.9845
EfficientNetB0 0.9953 0.9971 0.9961
1 .6
1 0 0
1 .4
9 5
1 .2 In c e p tio n V 3
9 0 In c e p tio n R e s N e tV 2
1 .0 E ff ic ie n tN e t B 0
8 5
A c c u ra y (% )
M o b ile N e tV 2
In c e p tio n V 3 0 .8
8 0
L o s s
In c e p tio n R e s N e tV 2
7 5 0 .6
E ff ic ie n tN e t B 0
M o b ile N e tV 2 0 .4
7 0
6 5 0 .2
6 0 0 .0
0 1 0 2 0 3 0 4 0 5 0 0 1 0 2 0 3 0 4 0 5 0
E p o c h E p o c h
(a) (b)
1 0 0
1 .0
9 5
0 .9 9 0
A c c u ra c y (% )
C o lo r Im a g e 8 5 T r a in a n d T e s t im a g e r a tio
F 1 -s c o re
0 .8 G r a y S c a le 6 0 -4 0
8 0 8 0 -2 0
S e g m e n te d
7 0 -3 0
7 5
0 .7
7 0
0 .6 6 5
6 0
0 1 0 2 0 3 0 4 0 5 0 0 1 0 2 0 3 0 4 0 5 0
E p o c h E p o c h
(c) (d)
Figure 7. (a) Performance accuracy of implemented model. (b) Performance loss of implemented
model. (c) F1 score of InceptionV3. (d) Accuracy of InceptionResNetV2 grouped by training.
5. Discussion
The early detection and identification of plant diseases using deep-learning techniques
has recently made tremendous progress. Identification using traditional approaches heavily
Electronics 2021, 10, 1388 16 of 19
depends on some factors such as image enhancement, the segmentation of disease regions,
and feature extraction.
Our approach is based on the identification of diseases using a deep-learning-based
transfer-learning approach. Instead of using standard convolution, we used depthwise
separable convolution in the inception block, which reduced the number of parameters by
a large margin. To use both the inception and the residual network connection layer, we
used the InceptionResNetV2 model. The model both has higher accuracy and requires less
training time than the original architecture does, as the used parameters are much fewer.
To check the performance towards a smartphone-implemented lightweight model to assist
in plant-disease diagnosis, we implemented the MobileNetV2 model. We also implemented
EfficientNetB0, which considers depth, width, and resolution during convolution.
Although the convolutional-neural-network-based deep-learning architecture achieved
high success rates in the detection of plant diseases, it has some limitations, and there is
a scope for future works. A little noise in the sample images led to misclassification by
the deep-learning model [55,56]. Future work includes evaluating performance on noisy
images and improving it. The dataset that we used to evaluate performance included 38
different diseases and healthy leaves. However, there is a need for the expansion of the
dataset with wider land areas and more varieties of disease images. The dataset can also
be improved with aerial photos, which are captured by drones. Another important issue
is that the testing images are all from the same image dataset. Testing the network with
real-time field images is an important challenging issue. The images that were used to
test performance were all captured in laboratory conditions. The images that we used for
testing our model are part of the same dataset, the training dataset. There is a need for
the development of an efficient machine-learning system that could identify diseases in
real-time scenarios and from collected data from different datasets. Some researchers are
working on this field; they tested their model with real-time images, and performance
worsened by a huge margin—around 25–30%. Mohanty et al. [24] conducted an experiment
where they tested their model with different images from those in the training dataset
and achieved an accuracy rate of 31.5%. Ferentinos et al. [25] measured performance with
training images in laboratory conditions and tested the images in real-time conditions, and
achieved an accuracy rate of 33%. To improve this, we need wide variety in databases,
for example, with images taken in different lighting conditions, from different geograph-
ical areas, and with cultivating conditions. In addition, we aim to carry this research
forward by implementing it with a new deep-learning model, such as ACNet [57], and a
transformer-based architecture, such as ViT [58] and the MLP Mixer [59] method, in plant
disease identification, and evaluate its performance.
6. Conclusions
There are many developed methods in the detection and classification of plant diseases
using diseased leaves of plants. However, there is still no efficient and effective commercial
solution that can be used to identify the diseases. In our work, we used four different DL
models (InceptionV3, InceptionResnetV2, MobileNetV2, EfficientNetB0) for the detection
of plant diseases using healthy- and diseased-leaf images of plants. To train and test the
model, we used the standard PlantVillage dataset with 53,407 images, which were all
captured in laboratory conditions. This dataset consists of 38 different classes of different
healthy- and diseased-leaf images of 14 different species. After splitting the dataset into
80–20 (80% of whole data for training, 20% whole images for testing), we achieved the
best accuracy rate of 99.56% in EfficientNetB0 model. On average, less time was required
to train the images in the MobileNetV2 and EfficientNetB0 architectures, and it took 565
and 545 s/epoch, respectively, on colored images. In comparison with other deep-learning
approaches, the implemented deep-learning model has better predictive ability in terms
of both accuracy and loss. The required time to train the model was much less than
that of other machine-learning approaches. Moreover, the MobileNetV2 architecture is
Electronics 2021, 10, 1388 17 of 19
an optimized deep convolutional neural network that limits the parameter number and
operations as much as possible, and can easily run on mobile devices.
References
1. Sethy, P.K.; Barpanda, N.K.; Rath, A.K.; Behera, S.K. Deep feature based rice leaf disease identification using support vector
machine. Comput. Electron. Agric. 2020, 175, 105527.
2. Chen, J.; Chen, J.; Zhang, D.; Sun, Y.; Nanehkaran, Y.A. Using deep transfer learning for image-based plant disease identification.
Comput. Electron. Agric. 2020, 173, 105393.
3. Bai, X.; Cao, Z.; Zhao, L.; Zhang, J.; Lv, C.; Li, C.; Xie, J. Rice heading stage automatic observation by multi-classifier cascade
based rice spike detection method. Agric. For. Meteorol. 2018, 259, 260–270. [CrossRef]
4. Ramcharan, A.; Baranowski, K.; McCloskey, P.; Ahmed, B.; Legg, J.; Hughes, D.P. Deep Learning for Image-Based Cassava
Disease Detection. Front. Plant Sci. 2017, 8, 1852. [CrossRef]
5. Camargo, A.; Smith, J. An image-processing based algorithm to automatically identify plant disease visual symptoms. Biosyst.
Eng. 2009, 102, 9–21.
6. Singh, J.; Kaur, H. Plant disease detection based on region-based segmentation and KNN classifier. In Proceedings of the
International Conference on ISMAC in Computational Vision and Bio-Engineering 2018, Palladam, India, 16–17 May 2018;
pp. 1667–1675.
7. Camargo, A.; Smith, J. Image pattern classification for the identification of disease causing agents in plants. Comput. Electron.
Agric. 2009, 66, 121–125.
8. Chaudhary, A.; Kolhe, S.; Kamal, R. An improved random forest classifier for multi-class classification. Inf. Process. Agric. 2016,
3, 215–222.
9. Phadikar, S.; Sil, J.; Das, A.K. Rice diseases classification using feature selection and rule generation techniques. Comput. Electron.
Agric. 2013, 90, 76–85. [CrossRef]
10. Munisami, T.; Ramsurn, M.; Kishnah, S.; Pudaruth, S. Plant leaf recognition using shape features and colour histogram with
K-nearest neighbour classifiers. Procedia Comput. Sci. 2015, 58, 740–747.
11. Ebrahimi, M.; Khoshtaghaza, M.; Minaei, S.; Jamshidi, B. Vision-based pest detection based on SVM classification method.
Comput. Electron. Agric. 2017, 137, 52–58. [CrossRef]
12. Garcia-Ruiz, F.; Sankaran, S.; Maja, J.M.; Lee, W.S.; Rasmussen, J.; Ehsani, R. Comparison of two aerial imaging platforms for
identification of Huanglongbing-infected citrus trees. Comput. Electron. Agric. 2013, 91, 106–115. [CrossRef]
13. Yao, Q.; Guan, Z.; Zhou, Y.; Tang, J.; Hu, Y.; Yang, B. Application of support vector machine for detecting rice diseases using
shape and color texture features. In Proceedings of the 2009 International Conference on Engineering Computation, Hong Kong,
China, 2–3 May 2009; pp. 79–83.
14. Islam, M.; Dinh, A.; Wahid, K.; Bhowmik, P. Detection of potato diseases using image segmentation and multiclass support
vector machine. In Proceedings of the 2017 IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE),
Windsor, ON, Canada, 30 April–3 May 2017; pp. 1–4.
15. Tan, J.W.; Chang, S.W.; Kareem, S.B.A.; Yap, H.J.; Yong, K.T. Deep Learning for Plant Species Classification using Leaf Vein
Morphometric. IEEE/ACM Trans. Comput. Biol. Bioinform. 2018, 17, 82–90 . [CrossRef] [PubMed]
16. McCallum, A.; Nigam, K. A comparison of event models for naive bayes text classification. In Proceedings of the AAAI-98
Workshop on Learning for Text Categorization, Madison, WI, USA, 26–27 July 1998; Volume 752, pp. 41–48.
17. ÖZTÜRK, A.E.; Ceylan, M. Fusion and ANN based classification of liver focal lesions using phases in magnetic resonance
imaging. In Proceedings of the 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), Brooklyn, NY, USA,
16–19 April 2015; pp. 415–419.
18. Pujari, D.; Yakkundimath, R.; Byadgi, A.S. SVM and ANN based classification of plant diseases using feature reduction technique.
IJIMAI 2016, 3, 6–14. [CrossRef]
19. Lee, S.H.; Chan, C.S.; Mayo, S.J.; Remagnino, P. How deep learning extracts and learns leaf features for plant classification.
Pattern Recognit. 2017, 71, 1–13. [CrossRef]
Electronics 2021, 10, 1388 18 of 19
20. Shah, M.P.; Singha, S.; Awate, S.P. Leaf classification using marginalized shape context and shape+ texture dual-path deep
convolutional neural network. In Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing,
China, 17–20 September 2017; pp. 860–864.
21. Li, Y.; Yang, J. Few-shot cotton pest recognition and terminal realization. Comput. Electron. Agric. 2020, 169, 105240. [CrossRef]
22. Lee, S.H.; Goëau, H.; Bonnet, P.; Joly, A. New perspectives on plant disease characterization based on deep learning. Comput.
Electron. Agric. 2020, 170, 105220. [CrossRef]
23. Fuentes, A.; Yoon, S.; Kim, S.C.; Park, D.S. A robust deep-learning-based detector for real-time tomato plant diseases and pests
recognition. Sensors 2017, 17, 2022. [CrossRef]
24. Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using deep learning for image-based plant disease detection. Front. Plant Sci. 2016,
7, 1419. [CrossRef]
25. Ferentinos, K.P. Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agric. 2018, 145, 311–318.
[CrossRef]
26. Sladojevic, S.; Arsenovic, M.; Anderla, A.; Culibrk, D.; Stefanovic, D. Deep neural networks based recognition of plant diseases
by leaf image classification. Comput. Intell. Neurosci. 2016, 2016, 1–10. [CrossRef] [PubMed]
27. Too, E.C.; Yujian, L.; Njuki, S.; Yingchun, L. A comparative study of fine-tuning deep learning models for plant disease
identification. Comput. Electron. Agric. 2019, 161, 272–279. [CrossRef]
28. Hussain, M.; Bird, J.J.; Faria, D.R. A study on cnn transfer learning for image classification. In UK Workshop on Computational
Intelligence; Springer: Berlin/Heidelberg, Germany, 2018; pp. 191–202.
29. Tan, M.; Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the 2019 International
Conference on Machine Learning, Long Beach, CA, USA, 9–15 June 2019; pp. 6105–6114.
30. Mokhtar, U.; Ali, M.A.; Hassanien, A.E.; Hefny, H. Identifying two of tomatoes leaf viruses using support vector machine. In
Information Systems Design and Intelligent Applications; Springer: Berlin/Heidelberg, Germany, 2015; pp. 771–782.
31. Kaur, S.; Pandey, S.; Goel, S. Semi-automatic Leaf Disease Detection and Classification System for Soybean Culture. IET Image
Process. 2018, 12, 1038–1048. [CrossRef]
32. Babu, M.P.; Rao, B.S. Leaves Recognition Using Back Propagation Neural Network-Advice for Pest and Disease Control on Crops.
Available online: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.110.3632&rep=rep1&type=pdf (accessed on 1
May 2021).
33. Chouhan, S.S.; Kaul, A.; Singh, U.P.; Jain, S. Bacterial foraging optimization based radial basis function neural network (BRBFNN)
for identification and classification of plant leaf diseases: An automatic approach towards plant pathology. IEEE Access 2018,
6, 8852–8863. [CrossRef]
34. Kamilaris, A.; Prenafeta-Boldú, F.X. Deep learning in agriculture: A survey. Comput. Electron. Agric. 2018, 147, 70–90. [CrossRef]
35. Geetharamani, G.; Pandian, A. Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Comput.
Electr. Eng. 2019, 76, 323–338.
36. Jadhav, S.B.; Udupi, V.R.; Patil, S.B. Identification of plant diseases using convolutional neural networks. Int. J. Inf. Technol. 2020,
1–10. [CrossRef]
37. Rangarajan Aravind, K.; Raja, P. Automated disease classification in (Selected) agricultural crops using transfer learning. Autom.
Časopis Autom. Mjer. Elektron. Računarstvo Komun. 2020, 61, 260–272. [CrossRef]
38. Rangarajan, A.K.; Purushothaman, R. Disease classification in eggplant using pre-trained vgg16 and msvm. Sci. Rep. 2020,
10, 1–11.
39. Arora, J.; Agrawal, U. Classification of Maize leaf diseases from healthy leaves using Deep Forest. J. Artif. Intell. Syst. 2020,
2, 14–26. [CrossRef]
40. Ghazi, M.M.; Yanikoglu, B.; Aptoula, E. Plant identification using deep neural networks via optimization of transfer learning
parameters. Neurocomputing 2017, 235, 228–235. [CrossRef]
41. Li, Y.; Nie, J.; Chao, X. Do we really need deep CNN for plant diseases identification? Comput. Electron. Agric. 2020, 178, 105803.
[CrossRef]
42. Zeng, W.; Li, M. Crop leaf disease recognition based on Self-Attention convolutional neural network. Comput. Electron. Agric.
2020, 172, 105341. [CrossRef]
43. Oyewola, D.O.; Dada, E.G.; Misra, S.; Damaševičius, R. Detecting cassava mosaic disease using a deep residual convolutional
neural network with distinct block processing. PeerJ Comput. Sci. 2021, 7, e352. [CrossRef] [PubMed]
44. Ramcharan, A.; McCloskey, P.; Baranowski, K.; Mbilinyi, N.; Mrisho, L.; Ndalahwa, M.; Legg, J.; Hughes, D.P. A mobile-based
deep learning model for cassava disease diagnosis. Front. Plant Sci. 2019, 10, 272. [CrossRef] [PubMed]
45. Adedoja, A.; Owolawi, P.A.; Mapayi, T. Deep learning based on NASNet for plant disease recognition using leave images. In
Proceedings of the 2019 International Conference on Advances in Big Data, Computing and Data Communication Systems
(icABCD), Winterton, South Africa, 5–6 August 2019; pp. 1–5.
46. Zhao, Y.; Chen, Z.; Gao, X.; Song, W.; Xiong, Q.; Hu, J.; Zhang, Z. Plant Disease Detection using Generated Leaves Based on
DoubleGAN. IEEE/ACM Trans. Comput. Biol. Bioinform. 2021. [CrossRef] [PubMed]
47. Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556.
48. Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; et al.
ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. (IJCV) 2015, 115, 211–252. [CrossRef]
Electronics 2021, 10, 1388 19 of 19
49. Szegedy, C.; Ioffe, S.; Vanhoucke, V.; Alemi, A. Inception-v4, inception-resnet and the impact of residual connections on learning.
In Proceedings of the AAAI Conference on Artificial Intelligence 2017, San Francisco, CA, USA, 4–9 February 2017; Volume 31.
50. He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778.
51. Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. Mobilenets: Efficient
convolutional neural networks for mobile vision applications. arXiv 2017, arXiv:1704.04861.
52. Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.C. Mobilenetv2: Inverted residuals and linear bottlenecks. In
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018, Salt Lake City, UT, USA, 18–23 June 2018;
pp. 4510–4520.
53. Plant Village Dataset. Available online: https://github.com/spMohanty/PlantVillage-Dataset (accessed on 16 February 2019).
54. Toda, Y.; Okura, F. How convolutional neural networks diagnose plant disease. Plant Phenomics 2019, 2019, 1–14. [CrossRef]
55. Kwon, H.; Yoon, H.; Park, K.W. Acoustic-decoy: Detection of adversarial examples through audio modification on speech
recognition system. Neurocomputing 2020, 417, 357–370. [CrossRef]
56. Kwon, H.; Yoon, H.; Choi, D. Restricted evasion attack: Generation of restricted-area adversarial example. IEEE Access 2019,
7, 60908–60919. [CrossRef]
57. Hu, X.; Yang, K.; Fei, L.; Wang, K. Acnet: Attention based network to exploit complementary features for rgbd semantic
segmentation. In Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 22–25
September 2019; pp. 1440–1444.
58. Dosovitskiy, A.; Beyer, L.; Kolesnikov, A.; Weissenborn, D.; Zhai, X.; Unterthiner, T.; Dehghani, M.; Minderer, M.; Heigold, G.;
Gelly, S.; et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv 2020, arXiv:2010.11929.
59. Tolstikhin, I.; Houlsby, N.; Kolesnikov, A.; Beyer, L.; Zhai, X.; Unterthiner, T.; Yung, J.; Keysers, D.; Uszkoreit, J.; Lucic, M.; et al.
Mlp-mixer: An all-mlp architecture for vision. arXiv 2021, arXiv:2105.01601.