Content uploaded by Balamurugan S.P.
Author content
All content in this area was uploaded by Balamurugan S.P. on Aug 01, 2022
Content may be subject to copyright.
Content uploaded by Punithavathi Rasappan
Author content
All content in this area was uploaded by Punithavathi Rasappan on Aug 01, 2022
Content may be subject to copyright.
Computer Vision and Deep Learning-enabled Weed Detection Model for
Precision Agriculture
R. Punithavathi
1
, A. Delphin Carolina Rani
2
, K. R. Sughashini
3
, Chinnarao Kurangi
4
, M. Nirmala
5
,
Hasmath Farhana Thariq Ahmed
6
and S. P. Balamurugan
7
,
*
1
Department of Information Technology, M.Kumarasamy College of Engineering, Karur, 639113, India
2
Department of Computer Science and Engineering, K. Ramakrishnan College of Technology, Tiruchirapalli, 621112, India
3
Department of Electronics and Instrumentation, Easwari Engineering College, Tamil Nadu, 600089, India
4
Pondicherry University, Puducherry, 605014, India
5
Department of computer science and engineering, The Oxford college of Engineering, Bangalore, 560068, India
6
Department of Computer Science Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical
Sciences, Saveetha University, Chennai, 602105, India
7
Department of Computer and Information Science, Faculty of Science, Annamalai University Chidambaram, 608002, India
*Corresponding Author: S. P. Balamurugan. Email: spbcdm@gmail.com
Received: 22 January 2022; Accepted: 06 March 2022
Abstract: Presently, precision agriculture processes like plant disease, crop yield
prediction, species recognition, weed detection, and irrigation can be accom-
plished by the use of computer vision (CV) approaches. Weed plays a vital role
in influencing crop productivity. The wastage and pollution of farmland's natural
atmosphere instigated by full coverage chemical herbicide spraying are increased.
Since the proper identification of weeds from crops helps to reduce the usage of
herbicide and improve productivity, this study presents a novel computer vision
and deep learning based weed detection and classification (CVDL-WDC) model
for precision agriculture. The proposed CVDL-WDC technique intends to prop-
erly discriminate the plants as well as weeds. The proposed CVDL-WDC techni-
que involves two processes namely multiscale Faster RCNN based object
detection and optimal extreme learning machine (ELM) based weed classification.
The parameters of the ELM model are optimally adjusted by the use of farmland
fertility optimization (FFO) algorithm. A comprehensive simulation analysis of
the CVDL-WDC technique against benchmark dataset reported the enhanced out-
comes over its recent approaches interms of several measures.
Keywords: Precision agriculture; smart farming; weed detection; computer vision;
deep learning
1 Introduction
Presently, several smart agriculture tasks, namely crop yield prediction, plant disease detection, weed
detection, water and soil conservation, and species identification, are comprehended by using computer
vision (CV) technique [1]. Weed control is a significant method for improving crop production [2].
This work is licensed under a Creative Commons Attribution 4.0 International License, which
permits unrestricted use, distribution, and reproduction in any medium, provided the original
work is properly cited.
Computer Systems Science & Engineering
DOI: 10.32604/csse.2023.027647
Article
ech
T
PressScience
Significant research has presented accurate variable spraying methods to avoid herbicide residual issues and
waste created by the conventional full coverage spraying [3]. To accomplish accurate variable spraying, the
main problem that needs to be resolved is how to understand realtime accurate recognition and classification
of weeds crops [4]. In traditional agriculture settings, herbicide is employed at uniform rate to the entire field
although distribution of weed is patchy. It causes environmental pollution and leads to higher input costs for
farmers [5]. In contradiction of this, Precision Agriculture (PA) purposes necessity-based on site-specific
application [6].
Adapting PA practice for using herbicides needs precise weed mapping by categorizing host plants and
weeds [7]. Classification of plants is a tedious process due to spectral resemblances among distinct kinds of
plants. The current mapping method assumes that host plant is planted in rows. The line detection approach is
utilized for categorizing plants in a row as host plant, and plant that falls out of seeding line as weeds. The
interline method failed to identify weed plants positioned inside crop lines and host plant falls out of crop line
[8]. Method to realize weed recognition through CV technique primarily consist of deep learning and
conventional image processing. Once weed recognition is implemented by using conventional image-
processing technique, feature extraction, namely color, shape, and texture, of the image and combined
with conventional machine learning (ML) approaches like Support Vector Machine (SVM) or random
forest, for weed detection is needed [9]. This method needs to develop features automatically and have
higher dependence on image acquisition method, pre-processing method, and the quality of feature
extraction. Due to the development in computing power and the growth in data dimensions, DL
approaches could extract multi-scale and multi-dimensional spatial semantic feature data of weeds by
using Convolution Neural Network (CNN) because of improved data expression capability, avoiding the
drawbacks of conventional extraction method. Hence, they have received growing interest towards the
authors [10].
Lottes et al. presented a novel crop-weed classification model which depends on fully convolutional
networks (FCN) with encoding-decoding infrastructure and incorporates spatial data with assuming image
sequence [11]. The exploitation the crop arrangement data that is noticeable in the image orders allows
this technique for robustly estimating pixel-wise labeling of images as to crop and weed, for instance, a
semantic segmentation. The RGB color images of seedling rice are taken from paddy fields, and ground
truth (GT) images are attained by manually labeling the pixel from the RGB image with 3 distinct types
such as weed, rice seedling, and background [12]. The class weight co-efficient is computed for solving
the problem of unbalance of the amount of classification type. The GT as well as RGB
A software is established, Pynovisão that with utilize of superpixel segmentation technique SLIC is
utilized for building a robust image data set and classify image utilizing the method training by Caffe
software [13]. For comparing the outcomes of ConvNets, SVMs, AdaBoost, and RF are utilized in
conjunction with group of shape, color, and texture feature extracting approaches. A novel method is
developed which combined different shape features for establishing a pattern for all varieties of plants.
For enabling the vision system from the detection of weeds dependent upon its patterns, SVM and ANN
are utilized [14]. Four species of general weed from sugar beet field are considered. The shape feature
fixed contained Fourier descriptors and moment invariant feature. Pereira et al. [15] presented the
automatic identification of any species using techniques of supervised pattern detection approach and
shape descriptor for composing an adjacent future expert method to automatic application of correct
herbicide. The experimentally utilizing several recent approaches have demonstrated the robustness of
utilized pattern detection approaches.
1.1 Paper Contributions
The major contributions of the study are discussed as follows. This study presents a novel computer
vision and deep learning based weed detection and classification (CVDL-WDC) model for precision
2760 CSSE, 2023, vol.44, no.3
agriculture. The proposed CVDL-WDC technique intends to properly discriminate the plants as well as
weeds. The proposed CVDL-WDC technique involves two processes namely multiscale Faster RCNN
based object detection and optimal extreme learning machine (ELM) based weed classification. The
parameters of the ELM model are optimally adjusted by the use of farmland fertility optimization (FFO)
algorithm. A comprehensive simulation analysis of the CVDL-WDC technique against benchmark dataset
and the results are examined under diverse dimensions.
1.2 Paper Organization
The rest of the study is organized as follows. Section 2 elaborates the working of CVDL-WDC
technique and the experimental results are offered in Section 3. Lastly, Section 4 concludes the study.
2 The Proposed Model
This study has developed a new CVDL-WDC technique for proper discrimination of plants and weeds in
precision agriculture. The proposed CVDL-WDC technique encompasses a series of subprocesses namely
WF based pre-processing, Multi-scale Faster RCNN based object detection, ELM based classification,
and FFO based parameter optimization. The proposed model properly identified the weeds among crops,
reduce the usage of herbicide and improve productivity. Fig. 1 illustrates the overall prcoess of CVDL-
WDC technique.
2.1 Pre-processing Using WF Technique
At the initial stage, the WF approach can be utilized for eradicating the noise that exists in the image.
Noise removal is an image pre-processing approach proposed to optimize the feature of the image corrupted
by noise [16]. A certain instance is adoptive filtering whereby the denoising is typically performed according
to the noise content existing in the image. Consider the corrupted image is described as ^
Ix;yðÞ, the noise
Figure 1: Overall process of CVDL-WDC technique
CSSE, 2023, vol.44, no.3 2761
variance over the whole image is represented as r2
y;the local mean is shown as b
lLnear a pixel window and
the local variance in a window is represented as ^
r2
y:
b
^
I¼^
Ix;yðÞ
r2
y
^
r2
y
^
Ix;yðÞ
b
lL
(1)
when the noise variance through the image is equivalent to zero, r2
y¼0¼>^
^
I¼^
Ix;yðÞ. When the
global noise variance is smaller, and the local variance is large when compared to the global variance,
next the ration is nearly is equivalent to one,
When ^
r2
yr2
y, then ^
^
I¼^
Ix;yðÞ. While a higher local variance represents the incidence of edge in the
image window. The global and local variances are equivalent to b
^
I¼b
lLas ^
r2
yr2
y. This is the average
intensity in a standard region.
2.2 Multiscale Faster RCNN Based Object Detection
During object detection process, the multiscale Faster RCNN model is applied to identify the weeds as
well as plants. Indeed, the recognized object is smaller in size and lower in resolution. The earlier models
(i.e., Fast RCNN) has better recognition performance for larger objects cannot efficiently identify smaller
object in an image [17]. The primary reason is that this model depends on DNN which makes the image
evaluated with downsampled and convolution for obtaining high-level and more abstract features. Every
downsampling causes the image to be minimized by half. When the object is analogous to the size of
object in the PASCAL VOC, the object detailed feature is attained by using this downsampling and
convolution. But, When the recognized object is on a smaller scale, the last feature might be left
1-2 pixels afterward several downsampling. Consequently, some characteristics could not completely
determine the features of the object and the current recognition technique could not efficiently identify
the smaller target object. The deep the convolutional process, the more abstract the object feature could
denote the higher-level feature of object. The shallow convolutional layer extracts the lower-level feature
of object. However, for smaller objects, the lower-level feature ensures effective object features. For
getting higher-level and abstract object features and ensuring that there is sufficient pixel to determine
smaller objects, we combined the feature of distinct scales for ensuring the local detail of the object.
Simultaneously, focus more interest on the global features of the object depending upon the Fast RCNN.
The multiscale Faster RCNN method is separated into four portions: the initial one is the feature
extraction that contains 2 pooling layers, 3 RoI pooling layers, 5 convolutional layers, and 5 ReLU
layers. Then, standardize the output of 3th, 4th, and 5th convolution, correspondingly. The standardized
output is transmitted to the RPN layer and the feature combinational layers for the extracted multiscale
feature and the generation of PR, correspondingly. Next is the feature combinational layer which
integrates distinct scales feature of 3rd, 4th, and 5th layer into 1D feature through connection process.
Then the RPN layer largely comprehends the generation of PR. The final layer is utilized for realizing
bounding box regression and classification of objects are in PR which is made up of BBox and softmax.
To attain the combinational feature vector, needed to normalize the feature vector of distinct scales.
Generally, the deep convolutional layer outputs the small scale feature. In contrast, the low convolutional
layer output the large scale feature. The weight of largescale feature would be large when compared to of
smaller scale feature in the network weight that is tuned when the feature of this distinct scale is
integrated that resulting in the low recognition performance. To avoid this largescale feature from
covering smaller scale features, the feature tensor i.e., outputted from distinct RoI pooling must be
standardized beforehand this tensor is concatenated. In the study, we employed L2 normalization. The
normalized process, that is utilized for processing each feature vector i.e., pooled, is positioned afterward
2762 CSSE, 2023, vol.44, no.3
RoI pooling. Afterward, normalization, the scale of feature vector of 3th;4th;and 5th layers would be
regularized to a unified scale.
^
X¼X
kXk2
(2)
kXk2¼ð
X
d
i¼1
jxijÞ1=2(3)
Whereas X represents the original vector from 3th,4th,and5th layers, ^
Xdenotes normalization feature vector,
and Dindicates the channel amount of RoI pooling. The vector X would be scaled uniformly by scale factor
Y¼c^
X(4)
Whereas Y¼½y1;y2;...;ydT. In the procedure of error BP, we needed to alter the scale factor cand
input vector X:
@l
@^
X¼c@l
@y(5)
@l
@X¼@l
@^
X
I
kXk2
XX T
kXk3
2
! (6)
@l
@c¼X
y
@l
@y
^
X(7)
2.3 Optimal ELM Based Weed Classification
At the time of weed classification, the features are received by the ELM to classify into distinct classes.
Huang et al. presented ELM for improving the network trained speed, afterward extensive the concept of
ELM in neuron hidden node to another hidden node [18]. The trained instances are signified as
fxi;tign
i¼1, where nimplies the trained instances number, xirefers the input of ith sample with m
dimensional and tihas resultant of ith samples. Afterward, to provide the input vector x;the resultant of
SLFNs with Lhidden node is expressed as:
fx
ðÞ
¼X
L
i¼1
bihix
ðÞ
¼hTx
ðÞ
b(8)
where hx
ðÞ
¼½h1x
ðÞ
hLx
ðÞ
Trefers the hidden outcome, and b¼½b1bLTrepresents the resultant
weight. Considered that output of these ntrained instances are estimated with zero error, the compact
design is as follows
Hb¼t(9)
where H¼½hx
1
ðÞhx
n
ðÞ
Tis termed as hidden resultant matrix. The solution of resultant weight bonly
contains an easy linear formula, and the solution is matching to minimized of training error that is
min kHbtk. An optimum evaluation of resultant weights are demonstrated by Moore-Penrose
generalization inverse Hyas follows:
^
b¼Hyt(10)
CSSE, 2023, vol.44, no.3 2763
Usually, orthogonal projection is utilized for solving the generalization inverse Hy. When HTHis non-
singular, Hy¼ðHTHÞ1HT, or when HHTis non-singular, Hy¼HTðHHTÞ1:
In order to boost the classification efficiency of the ELM model, the FFO algorithm is applied to it. A
metaheuristic is a type of model-free method to resolve different kinds of optimization issues which are
newly exploited in a wide-ranging application. The FFO approach involves six major portions which are
described below [19]:
1. Initialization: here, the possible solution and the number of sections for (n) in the farmland are
determined. Regarding, the population (N) is modeled by the following equation:
Nn(11)
Whereas kirepresents a positive digit within 1;N½;and ndefines an integer value. The kvalue is
chosen as two that can be accomplished using errors and trials. For making the first individual in the
possible range, the subsequent formula is adapted:
Xij ¼LjþUjLj
d(12)
Whereas, Ljand Ujrepresents the lower and upper bounds in the variable j, and dindicates a random
value within 0;1½:The farmland is separated into three subsections of local memory A;B;and CðÞand a
global memory whereby the minimum quality soil is located in section A.
2. Evaluate the quality of soil in each section of the farmland: this phase directs the farmland decision
variable in the section. Calculate the cost function values for the decision variable. Likewise, the soil quality
was attained as follows:
Ss¼XajðÞ;a¼ns1ðÞ:nss ¼1;...;k½;j¼1;2;3;4 (13)
3. Update the memory: here, the local and global memories are upgraded. The optimal solution of the
farmland is saved in the local memory and the solutions amongst them are taken into account as global
memory. For determining the amount of optimum local and global memories, the subsequent formulas are
utilized:
Mlocal ¼round t nðÞ (14)
MGIobaI ¼round t NðÞ (15)
Whereas, t2O:1;1½, and Mlocal and MGlobal determine the amount of stored solutions in local and
global memory, correspondingly.
4. Soil quality difference for all the sections: define the quality of section and store the optimal one in the
local memory. Moreover, the optimal solution is saved in the global memory. To improve the worst-case
result, they are upgraded by integrating to the optimal-case solution of global memory. At last, the
variable of the solution is upgraded by:
Xnew ¼hXij XMGlobaI
þXij (16)
In the equation, XMGlobal symbolizes an arbitrary number by using global solution, Xij indicates a worst-
case i.e., chosen to update, and hdefines a decimal value in the following:
h¼ar1(17)
2764 CSSE, 2023, vol.44, no.3
in which, adenotes a constant number within 0;1½, and r1indicates an arbitrary number within [−1, 1].
Xnew ¼hXij XMGlobal
þXij (18)
h¼br2(19)
while r2indicates an arbitrary number within 0;1½, and bdefines a constant within 0;1½that is assumed
initially in farmland fertility.
5. The composition of soil: afterward detecting the optimal local solution Lbest
ðÞ, the farmland optimal
soil integration is chosen by the farmers. Besides, the optimum global solution Gbest
ðÞis attained for
combining the farmland to design the quality of the soil:
H¼Xnew ¼Xij þxXij Gbest b
ðÞ
;Q.rand
Xnew ¼Xij þr3Xij Gbest b
ðÞ
;0:w:
(20)
In which, Qdetermines the optimal global integration for the solution and is a constant within
0;1½BestGlobal
ðÞ;r3characterizes an arbitrary number within 0;1½, and xindicates the variable of the
farmland fertility i.e., determined by:
x¼xRm;0,Rm,1 (21)
6. Last condition: compute the potential solution to the searching region. In the method, once the ending
condition is attained, the procedure stops, or else, it is repeated until attaining the optimal solution. FFO
algorithm derives a fitness function to attain improved classification performance. It determines a positive
integer to represent the better performance of the candidate solutions. In this study, the minimization of
the classification error rate is considered as the fitness function, as given in Eq. (22). The optimal solution
has a minimal error rate and the worse solution attains an increased error rate.
fitness xi
ðÞ¼Classifier Error Rate xi
ðÞ¼
number of misclassified instances
Total number of instances 100 (22)
3 Results and Discussion
This section examines the weed detection and classification results of the CVDL-WDC technique using
the benchmark dataset [20]. Fig. 2 demonstrates the sample images consisting of healthy plants as well as
weeds. Fig. 3 illustrates the visualization result analysis of the CVDL-WDC technique. The figure stated
that the CVDL-WDC technique has effectively recognized and classified weeds among other plants.
Tab. 1 and Fig. 4 offers a brief classification result analysis of the CVDL-WDC technique under distinct
sizes of training/testing data. The results indicated that the CVDL-WDC technique has the ability to attain
improved classifier results under all sizes of training/testing data. With training/testing data of 80:20, the
CVDL-WDC technique has offered SENSY,SPECY,ACCUY,FSCORE, and MCC of 98.98%, 98.92%,
98.33%, 98.34%, and 98.68% respectively. Eventually, with training/testing data of 70:30, the CVDL-
WDC technique has accomplished SENSY,SPECY,ACCUY,FSCORE, and MCC of 97.64%, 98.70%,
97.50%, 98.94% and 98.30% respectively. Meanwhile, with training/testing data of 60:40, the CVDL-
WDC technique has provided SENSY,SPECY,ACCUY,FSCORE, and MCC of 96.46%, 97.09%, 97.10%,
97.51%, and 96.86% respectively.
Fig. 5 offers the accuracy and loss graph analysis of the CVDL-WDC approach on the test dataset. The
outcomes demonstrated that the accuracy value tends to increase and loss value tends to reduce with an
increase in epoch count. It is also observed that the training loss is low and validation accuracy is
maximum on the test dataset.
CSSE, 2023, vol.44, no.3 2765
Tab. 2 offers a detailed comparative study of the CVDL-WDC technique with recent methods. Fig. 6
illustrates the comparative SENSYanalysis of the CVDL-WDC technique with existing methods. The
results show that the FCN-PF and RF techniques have obtained least SENSYvalues of 79.30% and
60.65%. At the same time, the HOG-SVM model has showcased slightly increased SENSYvalue of
82.24%. Besides, the GW-GFD, GLCM, and FCN-RCWD techniques have obtained moderately closer
SENSYvalues of 93.03%, 92.94%, and 91.61% respectively. However, the CVDL-WDC technique has
outperformed the other methods with the maximum SENSYof 98.98%.
Figure 2: Sample images
2766 CSSE, 2023, vol.44, no.3
Figure 3: Annotated images-crop indicated in green box weed indicated in red box
Table 1: Result analysis of CVDL-WDC technique with different measures
Training/Testing Sensitivity Specificity Accuracy F-Score MCC
80:20 98.98 98.92 98.33 98.34 98.68
70:30 97.64 98.70 97.50 98.94 98.30
60:40 96.46 97.09 97.10 97.51 96.86
CSSE, 2023, vol.44, no.3 2767
Fig. 7 depicts the comparative SPECYanalysis of the CVDL-WDC technique with existing algorithms.
The results show that the FCN-PF and RF techniques have reached minimum SPECYvalues of 74.87% and
65.67%. Likewise, the HOG-SVM model has showcased slightly increased SPECYvalue of 83.51%.
Besides, the GW-GFD, GLCM, and FCN-RCWD techniques have attained moderately closer SPECY
values of 93.29%, 93.13%, and 94.32% correspondingly. At last, the CVDL-WDC system has
outperformed the other methods with the maximal SPECYof 98.92%.
Fig. 8 showcases the comparative ACCUYanalysis of CVDL-WDC technique with existing approaches.
The results show that the FCN-PF and RF techniques have obtained least ACCUYvalues of 78.65% and
63.97%. At the same time, the HOG-SVM model has showcased slightly increased SENSYvalue of
83.50%. Besides, the GW-GFD, GLCM, and FCN-RCWD approaches have obtained moderately closer
ACCUYvalues of 93.75%, 91.60%, and 93.88% correspondingly. Lastly, the CVDL-WDC technique has
outperformed the other methods with the maximum ACCUYof 98.33%.
Fig. 9 portrays the comparative FSCORE analysis of CVDL-WDC technique with existing techniques.
The results show that the FCN-PF and RF techniques have gained least FSCORE values of 74.20% and
66.11%. In addition, the HOG-SVM model has showcased slightly increased FSCORE value of 81.79%. In
addition, the GW-GFD, GLCM, and FCN-RCWD techniques have reached moderately closer FSCORE
values of 92.72%, 92.64%, and 92.40% respectively. But, the CVDL-WDC methodology has
demonstrated the other approaches with the maximum FSCORE of 98.34%.
Fig. 10 demonstrates the detailed MCC analysis of the CVDL-WDC technique with existing
methodologies. The results outperformed that the FCN-PF and RF techniques have reached least MCC
values of 73.54% and 67.58%. Also, the HOG-SVM technique has showcased somewhat higher MCC
value of 81.04%. Likewise, the GW-GFD, GLCM, and FCN-RCWD systems have reached moderately
closer MCC values of 92.45%, 94.18%, and 92.82% correspondingly. Finally, the CVDL-WDC system
has outperformed the other methods with the maximum MCC of 98.68%.
Figure 4: Result analysis of CVDL-WDC technique with different measures
2768 CSSE, 2023, vol.44, no.3
Figure 5: Accuracy and loss analysis of CVDL-WDC technique
Table 2: Comparative analysis of CVDL-WDC technique with recent methods
Methods Sensitivity Specificity Accuracy F-Score MCC
HOG-SVM 82.24 83.51 83.50 81.79 81.04
GW-GFD 93.03 93.29 93.75 92.72 92.45
(Continued)
CSSE, 2023, vol.44, no.3 2769
Lastly, a comprehensive computational time (CT) analysis of the CVDL-WDC technique takes place in
Tab. 3 and Fig. 11 [21]. The results show that the HOG-SVM and GW-GFD techniques have required
increased CT of 235 and 205 s respectively. Along with that, the GLCM, FCN-PF, and RF techniques
have needed slightly decreased CT of 185, 137, and 156 s respectively. In line with, the FCN-RCWD
technique has accomplished somewhat considerable CT of 78 s. However, the proposed CVDL-WDC
technique has attained minimal CT of 43 s. From the results and discussion, it is evident that the CVDL-
WDC technique has reached effective weed detection and classification performance.
Table 2 (continued)
Methods Sensitivity Specificity Accuracy F-Score MCC
GLCM 92.94 93.13 91.60 92.64 94.18
FCN-RCWD 91.61 94.32 93.88 92.40 92.82
FCN-PF 79.30 74.87 78.65 74.20 73.54
RF Model 60.65 65.67 63.97 66.11 67.58
CVDL-WDC 98.98 98.92 98.33 98.34 98.68
Figure 6: Sensyanalysis of CVDL-WDC technique with recent approaches
2770 CSSE, 2023, vol.44, no.3
Figure 8: Accyanalysis of CVDL-WDC technique with recent approaches
Figure 7: Specyanalysis of CVDL-WDC technique with recent approaches
CSSE, 2023, vol.44, no.3 2771
Figure 10: MCC analysis of CVDL-WDC technique with recent approaches
Figure 9: Fscore analysis of CVDL-WDC technique with recent approaches
2772 CSSE, 2023, vol.44, no.3
4 Conclusion
This study has developed a new CVDL-WDC technique for proper discrimination of plants and weeds
on precision agriculture. The proposed CVDL-WDC technique encompasses a series of subprocesses namely
WF based pre-processing, Multi-scale Faster RCNN based object detection, ELM based classification, and
FFO based parameter optimization. The proposed model properly identified the weeds among crops, reduce
the usage of herbicide and improve productivity. A comprehensive simulation analysis of the CVDL-WDC
technique against benchmark dataset and the results are examined under diverse dimensions. The
comparative results reported the enhanced outcomes over its recent approaches interms of several
measures. As a part of future extension, the proposed CVDL-WDC technique can be utilized in the
Internet of Things and smartphone environment.
Funding Statement: The authors received no specific funding for this study.
Figure 11: CT analysis of CVDL-WDC technique with recent methods
Table 3: Computation time analysis of CVDL-WDC technique with recent methods
Methods Computational time (s)
HOG-SVM 235
GW-GFD 205
GLCM 185
FCN-RCWD 078
FCN-PF 137
RF Model 156
CVDL-WDC 043
CSSE, 2023, vol.44, no.3 2773
Conflicts of Interest: The authors declare that they have no conflicts of interest to report regarding the
present study.
References
[1] R. Kamath, M. Balachandra and S. Prabhu, “Paddy crop and weed discrimination: A multiple classifier system
approach,”International Journal of Agronomy, vol. 2020, no. 3 and 4, pp. 1–14, 2020.
[2] B. Liu and R. Bruch, “Weed detection for selective spraying: A review,”Current Robotics Reports, vol. 1, no. 1,
pp. 19–26, 2020.
[3] H. Huang, Y. Lan, J. Deng, A. Yang, X. Deng et al., “A semantic labeling approach for accurate weed mapping of
high resolution UAV imagery,”Sensors, vol. 18, no. 7, pp. 2113, 2018.
[4] N. Islam, M. M. Rashid, S. Wibowo, C. Y. Xu, A. Morshed et al., “Early weed detection using image processing
and machine learning techniques in an Australian CHILLI FARM,”Agriculture, vol. 11, no. 5, pp. 387, 2021.
[5] J. Yu, S. M. Sharpe, A. W. Schumann and N. S. Boyd, “Deep learning for image-based weed detection in
turfgrass,”European Journal of Agronomy, vol. 104, pp. 78–84, 2019.
[6] A. Wang, W. Zhang and X. Wei, “A review on weed detection using ground-based machine vision and image
processing techniques,”Computers and Electronics in Agriculture, vol. 158, pp. 226–240, 2019.
[7] J. Yu, A. W. Schumann, Z. Cao, S. M. Sharpe and N. S. Boyd, “Weed detection in perennial ryegrass with deep
learning convolutional neural network,”Frontiers in Plant Science, vol. 10, pp. 1422, 2019.
[8] A. N. Veeranampalayam Sivakumar, J. Li, S. Scott, E. Psota, A. Jhala et al., “Comparison of object detection and
patch-based classification deep learning models on mid- to late-season weed detection in UAV imagery,”Remote
Sensing, vol. 12, no. 13, pp. 2136, 2020.
[9] A. Kamilaris and F. Prenafeta-Boldú, “Deep learning in agriculture: A survey,”Computers and Electronics in
Agriculture, vol. 147, no. 2, pp. 70–90, 2018.
[10] K. Hu, G. Coleman, S. Zeng, Z. Wang and M. Walsh, “Graph weeds net: A graph-based deep learning method for
weed recognition,”Computers and Electronics in Agriculture, vol. 174, no. 7, pp. 105520, 2020.
[11] P. Lottes, J. Behley, A. Milioto and C. Stachniss, “Fully convolutional networks with sequential information for
robust crop and weed detection in precision farming,”IEEE Robotics and Automation Letters, vol. 3, no. 4, pp.
2870–2877, 2018.
[12] X. Ma, X. Deng, L. Qi, Y. Jiang, H. Li et al., “Fully convolutional network for rice seedling and weed image
segmentation at the seedling stage in paddy fields,”PLoS ONE, vol. 14, no. 4, pp. e0215676, 2019.
[13] A. dos Santos Ferreira, D. Matte Freitas, G. Gonçalves da Silva, H. Pistori and M. Theophilo Folhes, “Weed
detection in soybean crops using ConvNets,”Computers and Electronics in Agriculture, vol. 143, no. 11, pp.
314–324, 2017.
[14] A. Bakhshipour and A. Jafari, “Evaluation of support vector machine and artificial neural networks in weed
detection using shape features,”Computers and Electronics in Agriculture, vol. 145, pp. 153–160, 2018.
[15] L. Pereira, R. Nakamura, G. de Souza, D. Martins and J. Papa, “Aquatic weed automatic classification using
machine learning techniques,”Computers and Electronics in Agriculture, vol. 87, no. 1, pp. 56–63, 2012.
[16] J. Chen, J. Benesty, Y. Huang and S. Doclo, “New insights into the noise reduction Wiener filter,”IEEE
Transactions on Audio, Speech, and Language Processing, vol. 14, no. 4, pp. 1218–1234, 2006.
[17] G. X. Hu, Z. Yang, L. Hu, L. Huang and J. M. Han, “Small object detection with multiscale features,”
International Journal of Digital Multimedia Broadcasting, vol. 2018, no. 2, pp. 1–10, 2018.
[18] G-B. Huang, Q-Y. Zhu and C-K. Siew, “Extreme learning machine: Theory and applications,”Neurocomputing,
vol. 70, no. 1–3, pp. 489–501, 2006.
[19] H. Shayanfar and F. S. Gharehchopogh, “Farmland fertility: A new metaheuristic algorithm for solving continuous
optimization problems,”Applied Soft Computing, vol. 71, no. 4, pp. 728–746, 2018.
[20] K. Sudars, J. Jasko, I. Namatevs, L. Ozola and N. Badaukis, “Dataset of annotated food crops and weed images for
robotic computer vision control,”Data in Brief, vol. 31, no. 1, pp. 105833, 2020.
[21] Z. Wu, Y. Chen, B. Zhao, X. Kang and Y. Ding, “Review of weed detection methods based on computer vision,”
Sensors, vol. 21, no. 11, pp. 3647, 2021.
2774 CSSE, 2023, vol.44, no.3