Microsoft Word - ETASR_V11_N5_pp7678-7683


Engineering, Technology & Applied Science Research Vol. 11, No. 5, 2021, 7678-7683 7678 
 

www.etasr.com Nuanmeesri: A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf … 

 

A Hybrid Deep Learning and Optimized Machine 

Learning Approach for Rose Leaf Disease 

Classification 
 

Sumitra Nuanmeesri 

Department of Information Technology 
Faculty of Science and Technology 
Suan Sunandha Rajabhat University 

Bangkok, Thailand 
sumitra.nu@ssru.ac.th 

 

 

Abstract-Analysis of the symptoms of rose leaves can identify up 

to 15 different diseases. This research aims to develop 

Convolutional Neural Network models for classifying the diseases 
on rose leaves using hybrid deep learning techniques with 

Support Vector Machine (SVM). The developed models were 

based on the VGG16 architecture and early or late fusion 

techniques were applied to concatenate the output from a fully 

connected layer. The results showed that the developed 

models based on early fusion performed better than the 

developed models on either late fusion or VGG16 alone. In 
addition, it was found that the models using the SVM classifier 

had better efficiency in classifying the diseases appearing on rose 

leaves than the models using the softmax function classifier. In 

particular, a hybrid deep learning model based on early fusion 

and SVM, which applied the categorical hinge loss function, 

yielded a validation accuracy of 88.33% and a validation loss of 

0.0679, which were higher than the ones of the other models. 
Moreover, this model was evaluated by 10-fold cross-validation 

with 90.26% accuracy, 90.59% precision, 92.44% recall, and 
91.50% F1-score for disease classification on rose leaves. 

Keywords-hybrid deep learning; neural networks; rose leaf 

diseases; support vector machine  

I. INTRODUCTION  

Roses are widely produced and exported globally. In 2019, 
the export value of roses was more than 175 million US 
dollars. The top five countries with the highest export rankings 
are Netherlands, Denmark, Uganda, Germany, and Canada [1]. 
In cultivating roses, pest problems such as insect infestations 
are often encountered along with pathogens caused by fungi, 
viruses, and bacteria [2]. There are also diseases caused by 
nutritional deficiencies such as in nitrogen, iron, zinc, and 
magnesium. Disease symptoms can be detected in roots, stems, 
branches, leaves, and buds or flowers. Especially the leaves are 
a source of various infectious disease symptoms. However, 
classifying an infected disease requires skill and experience. 
For example, rose mosaic disease is a common disease 
worldwide and can sometimes be caused by more than one 
pathogen [3]. Image processing methods for plant disease 
classification are currently being studied [4] combined with 

machine learning such as Support Vector Machine (SVM) [5] 
or K-Nearest Neighbors (KNN) [6]. For example, the authors 
in [7] classified 4 rose leaf diseases using machine learning 
with with at least 94% accuracy. In addition to machine 
learning, other methods such as deep learning and neural 
networks are applied to recognize and classify plant diseases. 
The author in [8] developed a Convolutional Neural Network 
(CNN) model, which applied MobileNet and transfer learning 
for rose disease classification. Over 30 and at least 15 rose 
diseases can be observed on the leaves [2]. 

Most of the research used a single perspective or a single 
set of images as the dataset for model training. However, in the 
deep learning model training, it is necessary to use images with 
multiple perspectives, such as image augmentation, and include 
image segmentation to highlight features that appear on the 
image. This approach usually increases the accuracy of the 
model. Moreover, there are currently very few studies that have 
applied hybrid deep learning models to classify plant diseases. 
Therefore, this research aims to develop rose leaf disease 
classification models using hybrid deep learning. Besides, this 
work also compares the performance of models using different 
classifiers, namely softmax function and SVM. 

II. RESEARCH METHODOLOGY 

A. Image Data Collection 

This study classifies rose diseases by identifying the 
symptoms on leaves based on image processing and CNN. A 
program was developed using the Google search engine and 
ChromeDriver utility to search and download rose leaf images 
with dimensions of at least 224 pixels. All downloaded images 
were rechecked and labeled. Moreover, the author took photos 
of rose leaves with and without diseases with an Android 
mobile phone. Therefore, a dataset of 4,032 downloaded and 
taken pictures was formed. The imagres were categorized to 16 
different classes with regard to the shown rose disease (15 
diseases + 1 normal/control) as shown in Table I. Finally, all 
images were resized and cropped to the dimension of 224×224 
pixels. 

Corresponding author: Sumitra Nuanmeesri



Engineering, Technology & Applied Science Research Vol. 11, No. 5, 2021, 7678-7683 7679 
 

www.etasr.com Nuanmeesri: A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf … 

 

TABLE I.  ROSE LEAF IMAGES CLASSIFICATION 

No. Label 
Disease 

Caused by 
Amount 

(images) 

1 BS Black spot Fungi 295 

2 DM Downy mildew Fungi 272 

3 PM Powdery mildew Fungi 281 

4 BM Black mold Fungi 245 

5 BB Botrytis blight Fungi 234 

6 VW Verticillium wilt Fungi 220 

7 CLS Cercospora leaf spot Fungi 279 

8 ATN Anthracnose Fungi 276 

9 RT Rust Fungi 280 

10 RM Rose mosaic Virus 270 

11 RR Rose Rosette Virus 236 

12 RSD Rose spring dwarf Virus 281 

13 SLR Strawberry latent ringspot Virus 183 

14 IB Insect bites Insect 192 

15 ND Nutrient deficiencies - 238 

16 NM Normal (disease-free) - 250 

 

B. Image Augmentation 

During the deep learning training mstage many images are 
needed to increase the performance of the model. If a particular 
class has a small number of images, it can affect classification 
accuracy. Thus, the author increased the number of training 
images by using the image augmentation technique, including 
vertical and horizontal flips, rotation (45, -45, 90, -90 degrees), 
shearing (45 and -45 degrees), and random zoom-in up to 
200%. Thus, the number of the images increased from 4,032 to 
40,320 images. The example of image augmentation is shown 
in Figure 1. 

 

 
Fig. 1.  Example of image augmentation. 

C. Image Processing 

Image processing was applied to emphasize the physical 
appearance of the rose leaves. The preliminary step is that the 
rose leaf was separated from the background pixels with the 
GrabCut [9] method based on the graph-cut technique. Such an 
output image is illustrated in Figure 2. 

 

 
Fig. 2.  The background pixels are removed by the GrabCut method. 

The images obtained after the removal of the background 
pixels were subjected to image color-spacing and image 
thresholding processing. 

1) Hue, Saturation, Value Color Space 

Hue, Saturation, Value (HSV) is a color space model which 
includes ranges of color type between 0 to 360 degrees, 
vibrancy, and color brightness. This work focused on color 
ranges around 120 degrees, which are related to the green color 
of a rose leaf. All green areas were desaturated with the lower 
saturation as grayness. As a result, any color not related to 
green was accelerated to become more emphatic. 

2) Truncated Adaptive Gaussian Thresholding 

Truncated Adaptive Gaussian Thresholding (TAGT) is a 
combination technique between truncate and adaptive Gaussian 
thresholding. For truncate thresholding, an image without 
background pixels is processed. Pixels greater than the 
threshold value ����� = 127, were assigned that value [10]: 

����	, �� 
 �threshold, if	���	,�� � ��������	,��, otherwise     (1) 
where ���	,��  refers to the input pixel coordination, and 
����	, �� refers to the output pixel coordination. 

Next, the threshold was adjusted from the weighted sum of 
the block size of the pixel neighborhood at 7×7 using adaptive 
Gaussian and binary thresholding, as in (2) [10]. 

����	,�� 
 ���	���, if	���	, �� � ���	,��0,													otherwise     (2) 
where ��	���  refers to the maximum value assigned to the 
pixels and ���	,��  refers to the individual threshold 
calculation of each pixel. 

3) Double Inverse-Binary Thresholding 

Double Inverse-Binary Thresholding (DIBT) is a 
thresholding method with twice applied inverse-binary 
thresholding. First, the image without background pixels is 
taken through a thresholding process between inverse-binary 
and binary, where the threshold values are set to 100 and 0 
respectively. The resulting image from the first step was 
adjusted to the threshold value of 127 by inverse-binary 
thresholding, calculated in (3) [10]. 

����	,�� 
 �0,														if	���	,�� � ���	,����	���, otherwise     (3) 
This results in an image emphasizing the expected 

coordinates of the suspected position of disease infection or 
wilt on the rose leaf. Each original image will result to 3 more 
images, namely HSV, TAGT, and DIBT, as shown in Figure 3. 

 

 
Fig. 3.  Example of each image processing. 



Engineering, Technology & Applied Science Research Vol. 11, No. 5, 2021, 7678-7683 7680 
 

www.etasr.com Nuanmeesri: A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf … 

 

D. Hybrid Deep Learning Modeling 

In this step the CNN models for the classification of 
diseases on a rose leaf were developed. Twelve models were 
developed as follows. 

1) Visual Geometry Group16-Based CNN Model 

Visual Geometry Group16 (VGG16) model is a CNN 
architecture presented in [11]. The input images of the VGG16-
based CNN model were set to 224×224 pixels for processing 
through 16 weight layers, including 13 convolution layers and 
3 fully connected layers. All convolution layers have a 3×3 
kernel size, 1 pixel of padding size, and the Rectified Linear 
Unit (ReLU) activation function. Spatial pooling followed with 
5 max-pooling layers with a 2×2 pixel filter and stride 2. 
Further, 1 flatten layer was included before feeding the output 
to the fully connected layers. Furthermore, the softmax 
activation function was applied with 1,000 output classes in the 
last fully connected layer. Thus, the total trainable parameters 
of this model were 138,357,544 as shown in Figure 4. 

 

 
Fig. 4.  VGG16-based CNN model architecture. 

According to Figure 4, the "Process: A" refers to feature 
extraction layers, "Process: B" refers to the flatten layer, and 
"Process: C" refers to the fully connected layers. This research 
used the original image dataset with 16 labeled output classes 
(see Table I) to develop the VGG16-based CNN model. 
Therefore, the softmax layer (in Process: C) was set to 16 
instead of 1000 classes. The overall trainable parameters of 
this model were 134,326,096. 

2) Early Fusion Model 

The early fusion (EF) model was developed based on the 
VGG16-based CNN model. It starts with the images that have 
undergone each image thresholding processing separately 
(original, HSV, TAGT, and DIBT images) to each channel of 
CNN for extracting features (see Process: A in Figure 4) with 
the VGG16 architecture. The outputs obtained for each dataset 
were fused and flattened before being classified with the fully 
connected layers, as shown in Figure 5. The sum of the 
trainable parameters was 484,041,973. 

3) Late Fusion Model 

The VGG16-based CNN model was extended to the Late 
Fusion (LF) model in this work. The LF model starts with each 
processed image as input (as the EF model) for each CNN 
channel, then fused each output obtained after classification by 
the softmax activation function. After the fusion of the results 
obtained from the 4 image types, they were classified by 2 
dense layers of size 4,096 and were finalized with the softmax 
function to 16 output classes (Figure 6). The total trainable 
parameters were 586,665,136. 

7  

Fig. 5.  VGG16-based early fusion model. 

 
Fig. 6.  VGG16-based late fusion model. 

4) VGG16-Based SVM Models 

According to the VGG16-based CNN model, the softmax 
activation function was used to classify the final output at the 
last layer. In contrast, this VGG16-based SVM model applied 
the SVM classifier instead of the softmax activation function, 
as shown in Figure 7.  

 

 
Fig. 7.  VGG16-based SVM model. 

SVM is a popular classifier for supervised learning 
algorithms, especially for binary classification. In this work, 
multi-class SVM is required to classify 16 classes of rose leaf 
disease images. There are several classifiers for multi-class 
SVM. In this work various multi-class SVM classifiers were 
applied including L2-SVM, Categorical Hinge Loss SVM 
(CHL-SVM), and Weston-Watkins SVM (WW-SVM), to the 
VGG16-based CNN models as follows. 

The L2-SVM is based on the optimization of L2 norm and 
Squared Hinge Loss (SHL) which is calculated in (4) and (5). 



Engineering, Technology & Applied Science Research Vol. 11, No. 5, 2021, 7678-7683 7681 
 

www.etasr.com Nuanmeesri: A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf … 

 

� 
 � 	! + #    (4) 
$ 
 ∑ max�0,1− �+!��,-!./     (5) 

where �  refers to the weight of dataset 0, 	!  refers to the 
augmentation of sample data vectors, # refers to the bias, 1 
refers to the number of samples in a dataset, �+ refers to the 
actual class, and � refers to the predicted class. 

Then, the SHL was optimized with a minimum of 
Euclidean norm and a large error penalty. Thus, the L2-SVM 
was formulated in (6). 

min
/

,
‖�‖,

, + 4 ∑ max(0,1 − �+!(�
 	! + #��

,-
!./     (6) 

where ‖�‖,  refers to the Euclidean norm (L2 norm 
regularization), and 4  refers to the large error penalty for 
misclassification in which 4 > 0. 

The CHL-SVM or multi-class hinge loss function was 
implemented with TensorFlow 2 based Keras and is calculated 
in (7) [12]. 

$ = max50,1 + max5(1 − �+��6 − ∑ �+!�!
-
!./ 6    (7) 

Regarding the WW-SVM or Weston-Watkins hinge loss 
[13], the linear classifier was calculated in (8), and the 
optimization was formulated in (9). 

$ = ∑ ∑ max(0,1 + �! − �7�789:
�
!./     (8) 

min
/

,
∑ ‖�7‖

,;
7./ + 4 ∑ ∑ max(0,1 + �! − �7�789:

�
!./     (9) 

where � refers to the weight, < refers to the number of classes, 
= refers to the number of samples in the dataset, � refers to the 
predicted class, and 4  refers to the large error penalty for 
misclassification in which 4 > 0. 

Finally, the last fully connected layer with the softmax 
function was replaced with the multi-class SVM to classify the 
final output. Therefore, 3 VGG16-based SVM models, namely 
VGG16 & L2-SVM, VGG16 & CHL-SVM, and VGG16 & 
WW-SVM, were developed with different multi-class SVM 
classifiers. 

5) Early Fusion-Based SVM Models 

The early fusion-based SVM model applied the 3 different 
multi-class SVM classifiers to the last fully connected layer 
with softmax of the EF model. Thus, 3 EF models were 
developed, namely EF & L2-SVM, EF & CHL-SVM, and EF 
& WW-SVM. 

6) Late Fusion-Based SVM Models 

The LF model included two softmax functions at two 
layers: before fusion and at the last layer of the model. Thus, 
the softmax classifier of the last layer was bypassed and 
replaced with the multi-class SVM classifiers. Therefore, 3 late 
fusion-based SVM models were developed: LF & L2-SVM, LF 
& CHL-SVM, and LF & WW-SVM. 

By default, all models are based on VGG16 and CNN 
architecture. The image dataset was randomly split into 70%, 
15%, and 15% for training, validating, and testing respectively. 
The hyperparameters were set as follows: the batch size was 

64, the learning rate was 0.001, and training took 200 epochs. 
The models were compiled with the Adam optimizer. 

E. Model Evaluation 

All models were evaluated and validated by the accuracy 
and loss value during the training processing. In addition, the 
VGG16-based CNN, EF, and LF models that applied the 
softmax function at the fully connected layer were evaluated 
using the categorical cross-entropy loss [14]: 

Cross-entropy = −∑ ∑ �!,B log5E!,B6
F
B./

7
!./     (10) 

where � refers to the total of input, � refers to the number of 
classes, �!,B  refers to the input � of class G, E!,B  refers to the 
probability of the predicted class G by input �. 

Further, the k-fold cross-validation was used to estimate the 
learning skill of the model based on an unseen dataset. The k-
fold cross-validation is mainly used to measure performance 
for machine learning models but can also be applied to deep 
learning models. Thus, all 12 models were evaluated by 10-fold 
cross-validation in this work. The performance of the models 
was validated on accuracy (ACC) [15], precision (PREC) [16], 
recall (REC) [17], and F1-Score. 

III. RESULTS 

All 12 models were trained, validated, and tested and their 
performances were compared. 

A. Model Training and Validation Performance 

The results showed that the models developed with the 
early fusion technique performed better than late fusion and 
VGG16 models. Especially, the model developed with the 
early fusion method and categorical hinge loss for the SVM 
(EF & CHL-SVM) gave the best accuracy among the models 
as shown in Table II. 

TABLE II.  ACCURACY AND LOSS VALUES RESULTS BETWEEN 
TRAINING AND VALIDATION OF THE MODELS 

Models 
Training Validation 

ACC Loss ACC Loss 

VGG16 (Softmax) 94.71 0.1847 83.28 0.4063 

VGG16 & L2-SVM 95.09 0.1656 83.79 0.3643 

VGG16 & CHL-SVM 96.03 0.1185 84.32 0.2607 

VGG16 & WW-SVM 95.59 0.1404 84.25 0.3090 

EF (Softmax) 97.09 0.0654 87.31 0.1438 

EF & L2-SVM 97.37 0.0514 87.62 0.1130 

EF & CHL-SVM 98.28 0.0309 88.33 0.0679 

EF & WW-SVM 97.91 0.0443 88.07 0.0974 

LF (Softmax) 96.44 0.0981 84.19 0.2159 

LF & L2-SVM 96.86 0.0770 84.87 0.1695 

LF & CHL-SVM 97.21 0.0597 85.44 0.1313 

LF & WW-SVM 96.97 0.0714 85.02 0.1570 

 

According to Table II, the EF & CHL-SVM model yielded 
a training accuracy of 98.28% and a training loss of 0.0309. In 
addition, it gave a validation accuracy of 88.33% and a 
validation loss of 0.0679. The accuracy and loss error between 
training and validation of the EF & CHL-SVM are shown in 
Figure 8. The validation accuracy of the EF & CHL-SVM 
model for rose leaf disease classification can be normalized and 
displayed as a confusion matrix, as shown in Figure 9. The EF 



Engineering, Technology & Applied Science Research Vol. 11, No. 5, 2021, 7678-7683 7682 
 

www.etasr.com Nuanmeesri: A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf … 

 

& CHI-SVM model was able to classify the disease-free (NM) 
rose leaves with 98.95% accuracy. The most accurate 
classifications of rose leaf diseases were VW, IB, and DM, 
with 98.48%, 94.08%, and 92.68% accuracy respectively. For 
most of the other diseases the accuracy was higher than 87%, 
except for BB, ATN, CLS, and SLR which had less than 83%. 
Especially, the SLR disease had the lowest accuracy of 

74.44%. 

 

 
Fig. 8.  The performance of training and validation of the EF & CHL-SVM 

model. 

 
Fig. 9.  The validation accuracy of the EF & CHL-SVM model in a 

confusion matrix. 

B. Model Evaluation 

All developed models were tested and evaluated by 10-fold 
cross-validation with a test dataset. The result showed that the 
performances of the EF-based models were higher than the LF-
based and VGG16-based models'. Regarding the EF-based 
models, the EF & CHL-SVM had the highest performance with 

90.26% accuracy, 90.59% precision, 92.44% recall, and 
91.50% F1-score as shown in Table III.  

TABLE III.  CROSS-VALIDATION PERFORMANCE 

Models ACC PREC REC F1-Score 

VGG16 (Softmax) 86.16 87.03 89.05 88.03 

VGG16 & L2-SVM 86.37 87.27 89.16 88.20 

VGG16 & CHL-SVM 86.90 87.81 89.47 88.63 

VGG16 & WW-SVM 86.62 87.53 89.30 88.41 

EF (Softmax) 89.54 90.20 91.90 91.04 

EF & L2-SVM 89.85 90.51 92.14 91.32 

EF & CHL-SVM 90.26 90.59 92.44 91.50 

EF & WW-SVM 90.08 90.63 92.42 91.51 

LF (Softmax) 87.62 88.56 90.04 89.30 

LF & L2-SVM 87.83 88.78 90.19 89.48 

LF & CHL-SVM 88.31 89.13 90.68 89.90 

LF & WW-SVM 88.05 88.88 90.43 89.65 

 

IV. CONCLUSION 

This research developed 12 models for classifying rose 
diseases from the symptoms that appear on the rose leaves 
using a CNN model based on VGG16 architecture and image 
processing. The classification of rose diseases consists of 16 
classes (9 classes for diseases caused by fungi, 4 for virus 
diseases, 1 for insect bit, 1 for nutrient deficiencies, and 1 
disease-free class). The 12 developed CNN models were 
divided into three groups: VGG16, EF, and LF. In addition, 
each group was divided into two classifier types: softmax and 
SVM. The softmax function was used in 3 models, namely the 
VGG16-based CNN, EF, and LF models. The utilized multi-
class SVM classifiers were L2-SVM, CHL-SVM, and WW-
SVM. There were 4,032 rose leaf images for model training. 
The images were resized to 224×224 pixels and underwent 
image augmentation, resulting in a dataset of 40,320 images. 
These images were subjected to image processing, including 
removal of background pixels, HSV color space, TAGT, and 
DIBT, to emphasize their features. Both TAGT and DIBT are 
based on image thresholding processing. Ultimately, the dataset 
was split to 70% for training, 15% for validation, and 15% for 
model testing by 10-fold cross-validation. 

The results showed that the EF-based models gave the 
highest training, validation, and testing performance values, 
followed by the LF-based and the VGG16-based models. In 
addition, the models developed with the SVM classifier 
performed higher than the models using the softmax function. 
The model using CHL-SVM showed the highest performance, 
followed by the models using WW-SVM, L2-SVM, and 
softmax function. Thus, the EF & CHL-SVM, a developed 
model based on the early fusion method and employing the 
SVM categorical hinge loss function was the most suitable 
model for classifying diseases on rose leaves with an accuracy 
of at least 88.33%. The models developed in [7, 8] had 
accuracy not less than 94%, which is higher than the accuracy 
of the CHL-SVM model in this work. However, these two 
studies only classified 4 rose leaf diseases, unlike this study 
which classified 15. 

Moreover, it is evident that image processing can improve 
rose leaf disease classification accuracy, especially when the 
features are fused. Besides, it was found that SVM gave better 



Engineering, Technology & Applied Science Research Vol. 11, No. 5, 2021, 7678-7683 7683 
 

www.etasr.com Nuanmeesri: A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf … 

 

results as a classifier than the softmax activation function, 
which is consistent with the findings in [18]. 

Regarding further work, the author plans to develop a 
model based on U-net deep learning and a transfer learning 
approach to detect and classify diseases on plants and then 
integrate it to the Internet of Things. 

ACKNOWLEDGMENT 

The author wishes to thank the Institute for Research and 
Development, Suan Sunandha Rajabhat University, for 
supporting this research. 

REFERENCES 

[1] "Top countries for Export of Roses," NationMaster. 

https://www.nationmaster.com/nmx/ranking/export-of-roses (accessed 
Sep. 21, 2021). 

[2] R. K. Horst and R. A. Cloyd, Compendium of Rose Diseases and Pests. 

Second Edition, 2nd ed. St. Paul, MI, USA: The American 
Phytopathological Society, 2007. 

[3] I. Vazquez-Iglesias et al., "High throughput sequencing and RT-qPCR 

assay reveal the presence of rose cryptic virus-1 in the United 
Kingdom," Journal of Plant Pathology, vol. 101, no. 4, pp. 1171–1175, 

Nov. 2019, https://doi.org/10.1007/s42161-019-00307-5. 

[4] S. Minaee, M. Jafari, and N. Safaie, "Design and development of a rose 

plant disease-detection and site-specific spraying system based on a 
combination of infrared and visible images," Journal of Agricultural 

Science and Technology, vol. 20, no. 1, pp. 23–36, Jan. 2018. 

[5] D. Das, M. Singh, S. S. Mohanty, and S. Chakravarty, "Leaf Disease 
Detection using Support Vector Machine," in 2020 International 

Conference on Communication and Signal Processing (ICCSP), 
Chennai, India, Jul. 2020, pp. 1036–1040, https://doi.org/ 

10.1109/ICCSP48568.2020.9182128. 

[6] A. A. Bharate and M. S. Shirdhonkar, "A review on plant disease 
detection using image processing," in 2017 International Conference on 

Intelligent Sustainable Systems (ICISS), Palladam, India, Dec. 2017, pp. 
103–109, https://doi.org/10.1109/ISS1.2017.8389326. 

[7] K. Swetharani and V. Prasad, "Design and Implementation of an 

Efficient Rose Leaf Disease Detection using K-Nearest Neighbours," 
International Journal of Recent Technology and Engineering, vol. 9, no. 

3, pp. 21–27, Sep. 2020, https://doi.org/10.35940/ijrte.C4213.099320. 

[8] A. Rajbongshi, T. Sarker, Md. M. Ahamad, and Md. M. Rahman, "Rose 
Diseases Recognition using MobileNet," in 2020 4th International 

Symposium on Multidisciplinary Studies and Innovative Technologies 
(ISMSIT), Istanbul, Turkey, Oct. 2020, https://doi.org/10.1109/ 

ISMSIT50672.2020.9254420. 

[9] C. Rother, V. Kolmogorov, and A. Blake, "‘GrabCut’: interactive 
foreground extraction using iterated graph cuts," ACM Transactions on 

Graphics, vol. 23, no. 3, pp. 309–314, Aug. 2004, https://doi.org/ 
10.1145/1015706.1015720. 

[10] "OpenCV: Miscellaneous Image Transformations," OpenCV. 
https://docs.opencv.org/master/d7/d1b/group__imgproc__misc.html 

(accessed Sep. 21, 2021). 

[11] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks 
for Large-Scale Image Recognition," arXiv:1409.1556 [cs], Apr. 2015, 

Accessed: Sep. 21, 2021. [Online]. Available: http://arxiv.org/ 
abs/1409.1556. 

[12] "tf.keras.losses.CategoricalHinge," TensorFlow. https://www.tensorflow 

.org/api_docs/python/tf/keras/losses/CategoricalHinge (accessed Sep. 
21, 2021). 

[13] J. Weston and C. Watkins, "Support Vector Machines for Multi-Class 

Pattern Recognition," presented at the 7th European Symposium on 
Artificial Neural Networks, Bruges, Belgium, Jan. 1999. 

[14] L. Poomhiran, P. Meesad, and S. Nuanmeesri, "Improving the 

Recognition Performance of Lip Reading Using the Concatenated Three 
Sequence Keyframe Image Technique," Engineering, Technology & 

Applied Science Research, vol. 11, no. 2, pp. 6986–6992, Apr. 2021, 
https://doi.org/10.48084/etasr.4102. 

[15] S. Nuanmeesri, "Development of community tourism enhancement in 

emerging cities using gamification and adaptive tourism 
recommendation," Journal of King Saud University - Computer and 

Information Sciences, Apr. 2021, https://doi.org/10.1016/ 
j.jksuci.2021.04.007. 

[16] S. Nuanmeesri and W. Sriurai, "Thai Water Buffalo Disease Analysis 

with the Application of Feature Selection Technique and Multi-Layer 
Perceptron Neural Network," Engineering, Technology & Applied 

Science Research, vol. 11, no. 2, pp. 6907–6911, Apr. 2021, 
https://doi.org/10.48084/etasr.4049. 

[17] A. N. Saeed, "A Machine Learning based Approach for Segmenting 
Retinal Nerve Images using Artificial Neural Networks," Engineering, 

Technology & Applied Science Research, vol. 10, no. 4, pp. 5986–5991, 
Aug. 2020, https://doi.org/10.48084/etasr.3666. 

[18] H. Hasan, H. Z. M. Shafri, and M. Habshi, "A Comparison Between 

Support Vector Machine (SVM) and Convolutional Neural Network 
(CNN) Models For Hyperspectral Image Classification," IOP 

Conference Series: Earth and Environmental Science, vol. 357, Nov. 
2019, Art. no. 012035, https://doi.org/10.1088/1755-1315/357/1/012035. 

 

AUTHOR'S PROFILE 

 

Sumitra Nuanmeesri received her Ph.D. in Information 

Technology at the King Mongkut’s University of 
Technology North Bangkok, Thailand. She is an Assistant 

Professor in the Information Technology Department, 
Faculty of Science and Technology at Suan Sunandha 

Rajabhat University, Thailand. Her research interests 
include speech recognition, data mining, deep learning, image processing, 

mobile application, supply chain management system, internet of things, 
robotics, augmented reality, and virtual reality