sustainability

Article
Image Acquisition, Preprocessing and Classification of Citrus
Fruit Diseases: A Systematic Literature Review
Poonam Dhiman 1 , Amandeep Kaur 2 , V. R. Balasaraswathi 3 , Yonis Gulzar 4, * , Ali A. Alwan 5
and Yasir Hamid 6, *

1 Department of Higher Education, Government PG College, Ambala Cantt 133001, India

2 Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab 713104, India
3 Department of Networking and Communications, School of Computing,
SRM Institute of Science and Technology, Kattankullattur 462003, India
4 Department of Management Information Systems, College of Business Administration, King Faisal University,
Al-Ahsa 31982, Saudi Arabia
5 Schools of Theoretical and Applied Science, Ramapo College of New Jersey, Mahwah, NJ 07430, USA
6 Department of Information Security and Engineering Technology, Abu Dhabi Polytechnic,
Abu Dhabi 111499, United Arab Emirates
* Correspondence: [email protected] (Y.G.); [email protected] (Y.H.)

Abstract: Different kinds of techniques are evaluated and analyzed for various classification models
for the detection of diseases of citrus fruits. This paper aims to systematically review the papers
that focus on the prediction, detection, and classification of citrus fruit diseases that have employed
machine learning, deep learning, and statistical techniques. Additionally, this paper explores the
present state of the art of the concept of image acquisition, digital image processing, feature extraction,
and classification approaches, and each one is discussed separately. A total of 78 papers are selected
after applying primary selection criteria, inclusion/exclusion criteria, and quality assessment criteria.
We observe that the following are widely used in the selected studies: hyperspectral imaging systems
for the image acquisition process, thresholding for image processing, support vector machine (SVM)
models as machine learning (ML) models, convolutional neural network (CNN) architectures as
deep learning models, principal component analysis (PCA) as a statistical model, and classification
Citation: Dhiman, P.; Kaur, A.; accuracy as evaluation parameters. Moreover, the color feature is the most popularly used feature for
Balasaraswathi, V.R.; Gulzar, Y.; the RGB color space. From the review studies that performed comparative analyses, we find that
Alwan, A.A.; Hamid, Y. Image
the best techniques that outperformed other techniques in their respective categories are as follows:
Acquisition, Preprocessing and
SVM among the ML methods, ANN among the neural network networks, CNN among the deep
Classification of Citrus Fruit Diseases:
learning methods, and linear discriminant analysis (LDA) among the statistical techniques.This study
A Systematic Literature Review.
concludes with meta-analysis, limitations, and future research directions.
Sustainability 2023, 15, 9643. https://
doi.org/10.3390/su15129643
Keywords: citrus fruits; deep learning; machine learning; image acquisition; classification
Academic Editor: Imre J. Holb

Received: 21 January 2023

Revised: 20 February 2023
Accepted: 9 June 2023 1. Introduction
Published: 15 June 2023 In the field of agribusiness, diseases of fruit products initiate the degradation of
the economy, just as large-scale manufacturing affects the economy around the world.
Some researchers in the last decade demonstrated the criticality of the quality of fruit
products, as it impacts human wellbeing [1]. Fruit products ought to be the basis of a
Copyright: © 2023 by the authors.
sound eating regimen. Citrus fruits are a significant product in agriculture, and nearly
Licensee MDPI, Basel, Switzerland.
everybody consumes them consistently [2]. Citrus fruits include lemons, oranges, grapes,
This article is an open access article
and tangerines. Various diseases affect citrus fruits, including black spot, greasy spot,
distributed under the terms and
canker, and greening, as well as many more. Diseases of citrus fruits are a critical subject that
conditions of the Creative Commons
Attribution (CC BY) license (https://
significantly influences the quality and number of yields around the world. The utilization
creativecommons.org/licenses/by/
of pesticides by farmers to control various diseases and enhance the production of crops is
4.0/). taking place on a vast scale [3]. Diseases of fruit crops cause significant issues, such as low

Sustainability 2023, 15, 9643. https://doi.org/10.3390/su15129643 https://www.mdpi.com/journal/sustainability

Sustainability 2023, 15, 9643 2 of 23

levels of production and monetary misfortunes, for farmers. Therefore, the detection of
diseases and the identification of their severity is a primary need in the agricultural world.
Generally, symptoms of disease in citrus fruits are identified with regular monitoring using
just the naked eye. This procedure is costly in enormous manors and is less precise. In
some countries, farmers hire specialists to identify citrus fruit diseases, and again, this
is a costly and tedious task. There is a need for high returns in horticultural enterprises,
as well as a better-quality yield of fruit products, if automatic systems are developed to
help in the early discovery of infection or diseases in citrus fruit [4]. Many systems have
been examined and proposed by analysts in the landscape of artificial intelligence, machine
learning, digital image processing, and deep learning for the prediction and classification
of citrus infections.
Machine vision platforms are indeed a commercial tool for the evaluation of food
standards. All such systems are used to assess production throughout the domain and are
used for robotic post-harvest or the early diagnosis of possibly lethal diseases [1]. They
are often used in post-harvest processing for the computer-controlled investigation of
the fruits’ external quality, including the breakneck speed filtering of them together in
commercial sections.

2. Systematic Literature Review

The arrangement, organization, and formation of the systematic literature review
(SLR) were implemented by the methodology chosen by the authors [5]. The framework of
this SLR was also based on the protocols followed by the authors [6–8]. After constructing
the review methodology, a sequence of steps was carried out for this study. The procedure
is shown in Figure 1.

Figure 1. Systematic literature review steps.

• The first step is identifying the need for the SLR.

• In the second step, research questions are formulated to answer the issues being
addressed in the review.
• The third step designed is a search strategy comprised of two further steps, i.e.,
primary and secondary steps.
• The fourth step is to find relevant studies from the different resources relied upon to
answer the research questions. The inclusion and exclusion criteria for screening the
related studies are also included in this phase.
To improve consistency, we then developed the quality evaluation criteria. We mea-
sured and evaluated the collected data regarding the review questions in the sixth stage of
the SLR. Implementing the review process for any SLR is significant enough to decrease
Sustainability 2023, 15, 9643 3 of 23

the chances of biased studies. In the following section, we delineate the steps we followed
in this SLR.

3. Need for SLR

This SLR aims to provide a complete picture of computer vision systems in diagnosing
disease, particularly in citrus fruits. The goal for this SLR is to explore the research articles
in a more structured way that adopts the concept of a computer vision system for the
identification and classification of diseases present in citrus fruits.

3.1. Research Questions

This SLR aims to explain and analyze the scientific evidence from further research
using ML, DL, and methodological techniques to evaluate the classification of citrus fruit
diseases. For this purpose, the following research questions were designed and evaluated:
RQ1: Which kind of diseases affect citrus fruits?
RQ2: Which techniques have been used to capture citrus fruits’ disease-related patterns?
RQ3: Which techniques outperform other techniques in terms of classification accuracy?
RQ4: Which hybrid techniques were used to detect citrus fruit diseases?
RQ5: What evaluation metrics are commonly seen in studies for assessing techniques?
RQ6: What evaluation metrics are commonly seen in studies for assessing techniques?

3.2. Search Strategy and Study Selection

There were two steps of our core method for finding and downloading relevant studies:
a. Primary searching;
b. Secondary searching.
For primary study selection, relevant keywords were selected by including all possible
synonyms and using alternative phrases and Boolean operators, such as “OR” and “AND”.
The search string designed was:
citrus AND (fruit) AND (disease OR diseases OR infection OR infections OR decay
OR decays OR defect OR defects) AND (detection OR prediction OR classification) AND
(“neural networks” OR “neural network” OR “deep learning” OR “machine learning” OR
“statistical technique”).
For the secondary phase, references for the selected paper were also included to obtain
more relevant papers for our SLR. The research references that were focused on were the
following for the selection and compilation of our primary studies:
• IEEE Xplore;
• Scopus;
• Springer;
• Science Direct;
• Wiley;
• Google Scholar;
• ACM Digital Library.
After selecting the databases to search, the primary step was to screen the relevant
studies of interest. The full-text papers identified the relevant studies that fulfilled the
inclusion and exclusion criteria. We also included papers using the references of the selected
studies. The total number of 1357 papers was identified by searching from the databases;
the screening of papers was based upon the search motive using the selection criteria.

3.3. Quality Assessment Criteria

The quality evaluation was treated as an additive step to select the relevant studies for
the SLR. We constructed a quality assessment questionnaire to score the selected studies.
The studies with lower scores were further excluded from the SLR.
Q1. Are the goals of the study explicitly stated?
Q2. Are the techniques of analysis well-established and reasoned?
Sustainability 2023, 15, 9643 4 of 23

Q3. Are the experiments implemented with adequate datasets?

Q4. Is the experiment extended to dataset(s) processed with images?
Q5. Are the findings and outcomes explicitly stated?
Based upon these five questions, the papers were evaluated and scored from 0 to 4.
However, most researchers applied a binary scoring system (i.e., 0 or 1) for each question.
Binary scores, i.e., 0 or 1, are not the best indicators to evaluate studies. However, we
somewhat followed the authors’ method to use fuzzy linear variables [9–15]. However,
instead of using a crisp set, we chose a numeric set ranging from 0 to 4 for each question.
Mainly, we set the score for each question as follows:
0 (No);
1 (Rarely);
2 (Partly);
3 (Mostly);
4 (Yes).
Since we used the question scoring method mentioned above, the overall score for
each study can fall in the following ranges:
0–1.5 (no);
1.6–3.5 (moderate);
3.6–5.0 (yes).
As a result of the quality assessment criteria, a further 9 papers were discarded, and
78 papers were finalized. Figure 2 represents the distribution of the selected studies from
various research libraries.

Figure 2. Distribution of selected studies.

All studies having “average” and “yes” indicators were included in the SLR. Stud-
ies rated as “yes” were considered the highest quality studies according to the quality
assessment criteria.

3.4. Data Extraction and Data Synthesis

We next assessed the details of the selected papers that answered the research questions.
The primary aim of data synthesis is to collect and collate the selected studies’ information to
formulate responses with regard to the research questions. We included the authors’ names,
Sustainability 2023, 15, 9643 5 of 23

the article’s title, publishing details, dataset details, image acquisition and processing
details, feature extraction details, and the technique used. The retrieved data were saved
into an Excel file for further analysis and synthesis. The accuracy measures used in different
studies were also evaluated to validate the approaches used. The Table 1 below summarizes
and displays the results.

Table 1. Selected studies addressing our research questions.

PAPER RQ1 RQ2 RQ3 RQ4 RQ5 PAPER RQ1 RQ2 RQ3 RQ4 RQ5
[16] Yes Yes No No Yes [17] Yes Yes No No Yes
[18] Yes Yes No No Yes [19] Yes Yes No No Yes
[20] Yes Yes No No Yes [21] Yes Yes Yes No Yes
[22] Yes Yes Yes No Yes [23] Yes Yes Yes No Yes
[24] Yes Yes No No Yes [25] Yes Yes No No Yes
[26] Yes Yes No No Yes [27] Yes Yes No No Yes
[28] Yes Yes No No Yes [29] Yes Yes No No Yes
[30] Yes Yes No No Yes [31] Yes Yes No No Yes
[32] Yes Yes Yes No Yes [33] Yes Yes Yes No Yes
[34] Yes Yes No No Yes [35] Yes Yes No No Yes
[36] Yes Yes No Yes Yes [37] No Yes No No Yes
[38] Yes Yes No No Yes [39] Yes Yes No No No
[40] Yes Yes Yes No Yes [41] Yes Yes Yes No Yes
[40] Yes Yes No No Yes [42] Yes Yes Yes No Yes
[43] Yes Yes No No Yes [44] Yes Yes No No Yes
[45] Yes Yes No No Yes [46] Yes Yes No Yes Yes
[47] Yes Yes No No Yes [48] Yes Yes Yes Yes Yes
[49] Yes Yes Yes No Yes [50] Yes Yes No No Yes
[51] Yes Yes No No Yes [21] Yes Yes No No Yes
[52] Yes Yes No No Yes [53] Yes Yes No No Yes
[17] Yes Yes No No Yes [54] Yes Yes No No Yes
[55] Yes Yes Yes No Yes [56] Yes Yes No No Yes
[57] Yes Yes No No No [58] Yes Yes No No Yes
[59] Yes Yes No No Yes [60] Yes Yes Yes No Yes
[61] Yes Yes No No Yes [62] Yes Yes No No Yes
[63] Yes Yes No No Yes [64] Yes Yes No No Yes
[65] Yes Yes No No Yes [66] Yes Yes No Yes Yes
[67] Yes Yes No No No [68] Yes Yes No No Yes
[69] Yes Yes Yes No Yes [59] Yes Yes No No Yes
[70] Yes Yes No No Yes [71] Yes Yes No No Yes
[72] Yes Yes No Yes Yes [73] Yes Yes No No Yes
[74] Yes Yes Yes No Yes [75] Yes Yes No No Yes
[76] Yes Yes No No Yes [77] Yes Yes No No Yes
[78] Yes Yes Yes No Yes [79] Yes Yes No No Yes
[80] Yes Yes No No Yes [81] No Yes Yes No Yes
[82] Yes Yes No No Yes [83] Yes Yes No No Yes
[84] Yes Yes No Yes Yes [85] Yes Yes No No No
[86] Yes Yes Yes Yes Yes [87] Yes Yes No Yes Yes
[88] Yes Yes No No Yes [89] Yes Yes No No Yes
[90] Yes Yes No No Yes

4. Results and Discussion

In this section, the answers to our research questions are given based on the se-
lected studies.
RQ1: What kinds of diseases affect citrus fruits?
Citrus fruits, such as oranges, grapefruit, limes, and lemons, are affected by different
citrus diseases, including chilling/freezing, anthracnose, pitting/splitting/greening, scab,
greasy spot, etc. These are presented in Figure 3. Figure 4 shows many studies that have
encountered the particular diseases present in citrus fruits.
Sustainability 2023, 15, 9643 6 of 23

Figure 3. Types of diseases present in citrus fruit.

Figure 4. Distribution of diseases of citrus fruit addressed in selected studies.

The most widespread defects according to count are surface defects (17), P. digita-
tum and other fungus infections (14), canker (12), melanose (10), HLB (9), and blackspot
(7). Table 2 provides a brief introduction to each disease, along with relevant references.
Other miscellaneous defects with their count shown in brackets are stubborn (3), brown
rot (1), black mould (3), green spot (1), color defects (3), copper burn (2), blemishes (3),
morphological disorders (2), and stem end rot (1).
Sustainability 2023, 15, 9643 7 of 23

Table 2. Description of diseases present in citrus fruits observed by studies.

Type of Diseases Description Research Papers

It is an initial colonizer of damage, with brown-colored lesions on
Anthracnose fruits damaged by many factors, such as sunburn, chemical exposure, [76,78,88]
high temperatures, and extended storage duration.
This disease creates a slight bruise on the fruit that can rarely affect
the ultimate fruit production yield but induces visible imperfections
Melanose [17,22,26,44,50,59,63,70,78]
that decrease the profitability of fruits destined for the produce mar-
ket.
These fungal pathogens of foliage are globally present in various
citrus-cultivar-producing regions. Generally, in in-plane areas with
regular rain, the occurrence of scab is more extreme than in tropical
Citrus scab [27,59,72,76,78]
regions. Scab injuries can be found on fruits just before seven days of
contamination. These infections also present as small patches with a
coarse and distorted appearance.
These are small, round, and dangerous spots with a diameter of 0.12
Black spot [26,41,59,65,72,76,78]
to 0.4 in fruits.
The diameter of the fruit scar is about 1–10 mm and is surrounded
Canker [17,17,22,27,40,41,50,59,63,68,70,78]
by water-dipped and yellow disc-like lesions.
Another name of HLB is greening. It occurs because of liberibacter,
phloem-limited fastidious, and candidatus. It is a bacterial and most
Huanglongbing destructive disease that reduces fruit production globally. With low
[16,23,41,44,59,64,72,78]
(HLB) soluble solids and high acidity, fruit tainted by HLB juice becomes
abnormally sour. It causes the fruit to be malformed and break. It
causes malformations and cracks on fruit.
Windy weather can cause tree branches to rub or hit growing fruit.
These scars are likely to only appear on the fruit’s surface and do not,
Wind scar in general, compromise its consistency. Tissue damage contributes [22,26,34,44,58,70,75]
to the entry of bacteria and fungi and colonize the tissue, resulting in
further damage.
Infections because of Penicillium spp. fungi are a primary concern
impacting citrus development. Actual losses due to this fungus
are complex and rely on the processing location, citrus type, age,
P. digitatum fungus [21,21,25,31,48,53,56,59,60,62,65,79,86,88]
environmental conditions of the developing and harvesting stage,
the degree of apparent damage during handling, and the climate
after harvest.
It is more intense where concentrations of rust mites are high. Rind
blotch considerably lowers the extrinsic properties of fruit for sale
Greasy spot at the market. Grapefruit is of significant concern, but this disease [26,44,50,70]
can also be present in oranges and other citrus fruits. Rind blotch de-
creases the amount of grapefruit that is suitable for the fresh market.
Mechanical injury (bruises) and indications of illnesses entail sur-
[18,30,32,38,40,43,49,55,61,71,77,79,82,
Surface defects face defects. Surface injuries include fruit blemishes, burns, and
83,85,87]
wrong structures.
This post-harvest disorder occurs due to the chilling effect, and it
is a catastrophic disorder that evolves with the storage of fruits at
low temperatures that notably demotes the quality of citrus fruits
Chilling/freezing in the market or disqualifies them from the market. The impact of
[29,46]
disorders the chilling disorder depends upon the temperature at which fruits
are to be stored or the duration of the time spent by the fruit in cold
storage. Its severity increases with lower storage temperatures and
long durations of exposure.
Other miscellaneous defects are stubborn, brown rot, black mould,
Other color defects green spot, color defects, copper burn, blemishes, morphological [17,17,19,20,22,24,26,27,30,34,63,68,70]
disorders, stem-end rot, etc.
Sustainability 2023, 15, 9643 8 of 23

Summary: One of the most exemplary illustrations of the diverse tactics bacteria
use to invade particular parent species is the interaction of citrus species with various
bacterial diseases. Among several mechanisms, the most prominent and frequent are
discoloration, foul smell, and cracking. Among the proteins potentially used in obtaining
transgenic plants resistant to bacterial citrus diseases are planted recognition receptors,
master regulators of the SA pathway, cecropin, and thionins.
RQ2: Which techniques have been used to capture citrus fruits’ disease-related patterns?
It is evident that statistical techniques such as linear regression, MBLR, SLR, HMM, etc.,
were used during the initial phase. Not only were these approaches overly mathematical
and often unable to manage the noise contained in the data, more accurate models based
on machine learning techniques were implemented in later phases from 2000 onwards.
Three different classification techniques were analyzed in this SLR:
• Machine learning;
• Deep learning;
• Statistical techniques.
This literature study also found that in 1995, only one paper used two different
techniques, i.e., a neural network model and a Bayesian approach, to detect different kinds
of diseases in grapefruits, tangerine, and oranges. In 1998, one paper was found to detect
surface defects using a deep learning technique. After that, one paper was found in the
year 2001 that used the deep learning technique, and in the year 2004, one paper was found
that used two different statistical techniques for the detection of detects in citrus fruits.
Figure 5 shows the contribution of three techniques (machine learning, deep learning, and
statistical techniques) from 2006 to 2020.

Figure 5. Distribution of studies across different techniques.

Deep learning models used for capturing disease-related patterns of citrus fruits.
This SLR analyzed DL models used by the included studies. As deep models are more
complex versions of or extensions of neural networks with a more significant number of
hidden layers, we also included all types of neural networks in this section, which are
written as follows:
• Artificial neural networks (ANN);
• Convolution neural networks (CNN);
• Probabilistic neural networks (PNN);
• Multilayer perceptrons (MLP);
• Associative neural networks (AANN);
Sustainability 2023, 15, 9643 9 of 23

• Radial basis probabilistic neural networks (RBPNN);

• Back propagation neural network (BPNN).
Figure 6 shows the number of studies that used DL techniques for citrus fruit diseases.
It can be observed that the most commonly employed technique was ANN, which was
employed in about 15 studies. The second most used DL estimation technique is CNN,
which was investigated in 11 different studies. BPNN was investigated in about six studies,
and RBPNN was investigated in four, while multilayer perceptrons (MLP) were employed
in three different studies. Finally, PNN and AANN were employed in one study assessed
in this SLR.

Figure 6. Deep learning (DL) and neural networks techniques used by studies.

Machine learning models used for capturing disease-related patterns of citrus fruit
The analyzed ML techniques used by all the selected studies in SLR are as follows:
• Support vector machines (SVM);
• Bayesian networks (BN);
• K-nearest neighbors (KNNs);
• Decision trees (DT);
• Genetic programming (GP);
• Classification and regression tree (CART);
• Naïve Bayes;
• Random forest (RF);
• K-means clustering;
• Fuzzy;
• Extreme learning machine (ELM);
• Ensemble learning (Adaboost);
• Ensemble boosted tree (EBT).
Figure 7 shows the count of ML techniques that have been used in the selected
studies. The most widely employed ML technique is SVM, which was employed in nearly
17 research papers. Different kinds of SVM were used, such as multi-class SVMs, RBF
kernel (RBF-SVM), Mahalanobis kernel (MK-SVM), etc. Further, the second-most-used
estimation technique was K-nearest neighbors (kNNs), which was evaluated in about
13 different selected studies. Different types of K-nearest neighbors (kNNs) have been
used here, such as the edited multi-seed nearest neighbor technique, the nearest neighbor
prototype technique, and weighted K-nearest neighbors (W-KNN). Fuzzy was employed in
nearly 4 selected studies; CART was employed in 2 studies, while Bayesian networks were
Sustainability 2023, 15, 9643 10 of 23

employed in 2 different selected studies. GP, CART, and naïve Bayes were used in two
studies, and ELM, Adaboost, and EBT were used in one study for each technique. Finally,
DT was employed in four studies assessed in this SLR. RF and DTare were considered
by one group, whereas CART was also classified in this category by some researchers.
Different studies used the genetic algorithm and K-means clustering for feature selection
and image processing (segmentation) purposes, respectively.

Figure 7. Machine learning (ML) approaches employed.

Statistical techniques used for capturing disease-related patterns in citrus fruits.

• PLS-discriminant;
• Discriminant analysis;
• Regression;
• Decision tree (LDA);
• Principal component analysis (PCA).
Figure 8 shows many statistical techniques that have been used in the selected studies.
It was found that the most widely used statistical technique is PCA, which was used in
about 12 studies, followed by LDA, which was used in 8 studies. The regression technique
evaluated in around seven different experiments was the third most-used estimation tech-
nique. Different types of regression techniques were used, such as logistic regression (LR),
principal component regression, Gaussian process regression, multiple linear regression
method (MLR), linear regression, and multivariate regression. PLS-discriminant regression
was investigated in about three studies, and other discriminant analysis methods were
investigated in three studies.

Figure 8. Statistical techniques used by selected studies in this SLR.

Sustainability 2023, 15, 9643 11 of 23

RQ3: Which techniques outperform other techniques in terms of classification accuracy?

Table 3 shows the techniques that outperformed the other techniques in the comparison
studies performed by the different experiments. It was found in the studies that more
than one experiment may be included by a single study based on different datasets or
methodology. The first technique that performed best is SVM, which outperformed other
techniques in 8 different experiments. ANN is the second technique that performed better
than the other nine techniques in 5 experiments. The next most-well-performing techniques
are DT and CNN, which performed better than eight and five different techniques in eight
and four experiments, respectively. The most promising statistical technique we found in
the studies is LDA, which was compared with other techniques in different experiments.
In three different experiments, LDA performed better than PCA, EBT, and CART.

Table 3. Overall techniques that outperformed other techniques.

Best
Outperformed Techniques
Technique
W-KNN, EBT, CNN, ANN, KNN, KNN, Naïve- DT, Fuzzy, MLP,
SVM ANN [76] KNN [69]
DT, LDA [41] KNN [71] SRS [81] BaYes [23] ANN [33] RBF [49]
SVM, LR, Naïve
ANN SRC [81] DT [33] KNN [33,81] Fuzzy [33] LDA [29] QDA [29]
[23,29] Bayes [23,32]
Naïve
DT MLP, RB [49] Fuzzy [33] EBT [41] LDA [86] ANN [32] SMO [49]
Bayes [32]
LDA PCA [60] EBT [41] CART [48]
BaYesian NN [22]
ANN, DT,
CNN KNN [69] SVM [33,69]
Fuzzy [33]
NNRB KNN [40]
ASNN SVM, [55] BPNN [55]
PLS MLR [74]
FA PCA [21] SM [21]
Naïve
Adaboost SVM [23] LR [23] KNN [23] NN [23]
Bayes [23]
RF SVM [42]
FUZZY,
KNN CNN [71]
DT [33]
PCA SM [21]
Naïve
LR SVM [23] KNN [23]
baYes [23]
W-KNN EBT [41]
ELM SVM [42]
BPNN SVM [55]
Table Abbreviations: NNRB—neural network radial basis, AANN—associative neural network, PLS—partial
least squares regression, FA—factor analysis, RF—random forest, ELM—extreme learning machine, RB—radial
basis, BPNN—backpropagation neural net, SM—Sammon mapping.

Summary: It is observed from Table 3 that in six different experiments, SVM was the
best technique, outperforming W-KNN, EBT, DT, naïve bayes, fuzzy, and RBF techniques.
The second best-performing technique is the decision tree, which was assessed in 5 different
experiments and compared to the naïve Bayes, RB, fuzzy, EBT, and SMO techniques. We
found that the Adaboost ML technique is a significantly less-explored technique in the
classification of citrus fruit diseases. The Adaboost ML technique was used in only one
Sustainability 2023, 15, 9643 12 of 23

study and outperformed many ML and DL techniques. Lastly, some more techniques,
such as the random forest, KNN, ELM, and FA techniques were also well-performing
ML techniques.
Similarly, in some experiments, ML techniques performed better than other DL tech-
niques. SVM again performed better than DL techniques such as ANN, CNN, and MLP in
5 different experiments. Additionally, we observed that the DT, Bayesian, Adaboost, KNN,
W-KNN, and ELM techniques also performed better than other DL techniques in one or
two experiments.
It can be observed that ANN and CNN are the two best techniques that performed
better than other ML techniques in 5 and 2 experiments, respectively. We also found that
the other DL techniques, such as neural network radial basis, associative neural networks,
and backpropagation neural networks, outperformed the other ML techniques in different
experiments. It can be observed that the LDA technique is the best technique among all
the statistical techniques in comparative studies assessed in our SLR. We also found other
well-performing statistical techniques, which include partial least squares regression, PCA,
and LR.
The SVM ML algorithm is found to be the most highly performing technique compared
to all others. The ability of SVM to handle high-dimensional data comes into play in
different comparison papers with unknown distributions. Other algorithms outperform
SVM in some general papers, but these algorithms are not generally able to classify and
address unknown variables with accuracy and efficiency compared to SVM. SVM claims to
provide a significant improvement in classification accuracy over ANN. SVM proved to be
a powerful method for automatically classifying the plant diseases studied in this study.
RQ4: Which hybrid techniques were used to classify citrus fruit diseases?
A hybrid approach combines different ML, DL, and other techniques to improve
classification accuracy. This survey found that 7% of studies used hybrid models that were
either used for the feature extraction process or classification of the citrus fruit diseases.
Figure 9 represents the distribution of the studies using different techniques for citrus fruit
disease classification. It is observed that the majority of studies used ML techniques (37%),
followed by DL techniques (31%). Statistical techniques provide a total contribution of 25%
in this SLR. Table 4 shows the hybrid techniques used in this SLR, along with their brief
introduction and results.

Figure 9. Distribution of different classification techniques.

Sustainability 2023, 15, 9643 13 of 23

Table 4. Hybrid methods used in the selected studies.

Hybrid Techniques Description Result

The described AGC-A algorithm reli-
Feature extraction takes place using the Alex-Net model.
ALEX-NET and Random For- ably identifies various forms of citrus
Lastly, multiclass classification is implemented using the
est fruit diseases with an overall identifi-
random forest technique to classify different diseases.
cation rate of 97.29% [72].
The radial neurons are used as input and linear output
neurons are used as the hidden layer in the RBF neural
The shelf lives of 40 samples were esti-
network model. The analysis was formulated by the newrb
mated, and the prediction accuracy of
PCA and NN function in the Matlab programme, but this function is
the model developed in this paper was
unstable. PCA was used for feature selection to enhance
80 [84].
relative stability. A total of 10 variables were employed as
the input of the neural network.
The paper adopted a methodology determined by the col-
lective use of hyperspectral images and a classifier of the
The total accuracy on the MK-SVM
Mahalanobis kernel. More detailed and accurate findings
classifier test set through various levels
SVMs with the Mahalanobis were obtained relative to other approaches in multiple
of training samples for the clemenules
kernel scenarios and acquired images. The different intrinsic im-
and clemenvilla mandarin variants
portance of spectral channels was assessed more effectively
was 95% [86].
by this kernel, as their relative value was learned from the
results.
LDA-based genetic algorithms were used to determine one
of the most suitable bands. The fitness function was chosen The overall result for clemenules using
to re-examine the response of every execution while un- the LDA classifier with the GALDA
Genetic algorithms based on
dertaking any GA method. The more extraordinary fitness system was 90%, and the results for
LDA
feature could be chosen to produce a new generation. The clemenules using the CART classifier
study utilized the overall precision of LDA as its fitness was 95% [48].
function, and hence, the technique was called GALDA.
Soft independent class analogy model-
ing (SIMCA), a form of PCA combined
with ANN and SVM techniques, was
PCA was first used to decrease the dimensionality of the performed to recognize freezing dam-
PCA-ANN spectral data, which were then considered the input for age in sweet lemons, leading to various
the ANN modeling technique. experimental simulated freezing envi-
ronments on the entire spectral content.
Using PCA-ANN, the accuracy of clas-
sification was 100% [46].
The Brix/acid ratio of flesh juice was measured in this
research by executing a regression analysis with a CNN
(CNN regression). The most common CNN styles, com- The absolute error in the Brix/acid ra-
CNN regression prising a convolution layer, a pooling layer, and a fully tio was 2.48 employing CNN regres-
connected layer, were introduced. The regression layer sion [36].
was positioned in the final layer to implement CNN re-
gression and measure the Brix/acid ratio.
The precision of the two regression ap-
PLS-discriminant analysis (PLS-DA) with principal com-
proaches revealed that for screening
Principal component anal- ponent analysis (PCA) was used to distinguish fruit per
between internal and outside fruit and
ysis followed by PLS- the canopy position. PCA and PLS-DA methods are fo-
sorting fruit depending on susceptibil-
discriminant analysis cused on spectra obtained before harvesting, being unable
ity to RBD, both strategies could be
to distinguish fruit depending on their canopy position.
used solely or in collaboration [66].
Sustainability 2023, 15, 9643 14 of 23

Table 4. Cont.

Hybrid Techniques Description Result

Invalidating characteristics, the CNN
trained by transfer learning gained
Centered on artificial intelligence algorithms using CNN
97.5% performance, and the methodol-
and a fuzzy motor, a fruit-oriented automated quality eval-
ogy developed for the characterization
uation framework was introduced that examined a set of
Convolutional neural net- procedure was performed correctly. In
external attributes of critical value to assess the Persian
works and a fuzzy motor the three classes suggested, each lemon
lemon quality in addition to mitigating the loss variables
was correctly categorized by the fuzzy
of objectivity that could lead to an operator to diverge from
method according to the characteris-
the selection criterion.
tics of each lemon and the classification
score provided by CNN [87].
The proposed method signifi-
The most relevant features were selected by implement-
cantly outperformed the other tech-
ing a hybrid feature selection technique that comprised
niques and attains 97% accuracy
PCA and multi-class support- entropy, PCA score, and a covariance vector premised on
for the image gallery dataset, 89%
vector machine (M-SVM) skewness. For the final classification of citrus disease, the
accuracy for the consolidated dataset,
identified features were fed to the multi-class support vec-
and 90.4% accuracy for their local
tor machine (M-SVM).
dataset [69].
The ability to recognise fruits in various occluded situa-
Fruit and branch detection have typi-
tions is a crucial area of expertise for a fruit-grading robot
cal accuracies of 88.15 and 96.27%, re-
system. An unified approach was created to concurrently
spectively. The average measurement
recognise and quantify citrus fruits and branches using
errors for the diagonal dimension of
a branch segment merging method and a mask regional
fruit, the longitudinal radius of fruit,
convolutional neural network. To increase the accuracy of
and the radius of branches are 2.52,
the mask R-CNN, a segmental labelling technique was pre-
Mask R-CNN and merging 2.29, and 1.17 mm, respectively. The
sented for randomized and asymmetrical branches. The
algorithm outcomes of the tests demonstrate that
minimal enclosing rectangle of the segmental mask por-
the detecting system performs well for
tions predicted by the model was calculated to produce a
all sorts of fruits and geometric distor-
much more exact bounding box. After that, the branches
tions. The robot can effectively design
and the trunk were rebuilt using a branch segment merg-
a proper picking path and avoid colli-
ing technique. Casting the colour image out onto the con-
sions with the aid of this imaging sys-
tour allows for the measurement of the fruit and branch
tem.
diameters.

Summary: Hybrid methods of classifying datasets have not been used popularly, but
they produce results with significant accuracy. These methods produce greater accuracy and
efficiency by combining classification methods instead of using them separately [23,32,46].
The above table notes the improved results using hybrid methods in different papers
compared to the accuracy obtained by applying these methods separately to the previous
question. Combining ML, DL, and statistical methods proved beneficial for the classifica-
tion process.
RQ5: Which features are to be extracted to classify citrus fruit diseases?
Numerous features can be utilized to depict an item and can be further contrasted with
the details collected from non-objects for classification into different classes. Usually, the
most sustainable features that are simple to measure and significantly contribute towards
classification are the best [91]. The number of studies using different extracted features is
shown in Figure 10. Our review found that the color features are the most widely used
feature, followed by textural features. The results of our study show that 45% of studies
extracted color features, 34% extracted texture features, and 21% extracted shape features.
Sustainability 2023, 15, 9643 15 of 23

Figure 10. Distribution of extracted features.

Figure 11 shows the distribution of color spaces being studied. It can be observed
from Figure 11 that the most frequently used color space is RGB, which was used in about
17 (35%) studies. The second most widely utilized color space was used in around 10 (23%)
different studies. LAB color space was utilized in about nine (18%) studies; HSI was used
in seven studies (14%), and YIQ was investigated in 2 (4%) different studies. Finally, NIR,
YIQ, CMY, and YCb Cr were used in one (2%) study for each color space.

Figure 11. Distribution of color spaces found in the studies.

Several visual characteristics associated with fruit and vegetables are called features.
Initially, fruit images are taken by a camera, and then pre-processing and segmentation
techniques are applied to the images to filter, smoothen, and remove the noise of the
images. After these steps, feature extraction takes place, which further helps to classify the
diseases. Color is the most persuasive aspect and substantial descriptor that frequently
improves feature extraction for the image analysis of fruits and vegetables. Color features
play a crucial role in detecting and classifying disease in fruits. Different color spaces,
such as HSV, RGB, HIS, and YCbCr, can be employed for classification purposes. Two
important size features are area and perimeter, and these can also be evaluated by obtaining
the pixel count of the images and adding up the distance of each adjacent pixel at the
boundary, respectively. For food and vegetable quality analysis, the most common size
features are the area, perimeter, length, and width. Apart from these features, major axis
and minor axis features can also be determined for classification purposes. The major
axis is the largest line through the fruit or vegetable product, which is determined by
the measurement of the distance between the two boundary pixels of each mixture and
Sustainability 2023, 15, 9643 16 of 23

the selection of the longest distance. The textural feature computed from the pixel group
reflects the distribution of components and the morphology of the surface and is useful
for computer vision, which determines the surface in the context of entropy, roughness
orientation, contrast, etc. Numerous features can be utilized to depict an item, which can
be further contrasted with the details collected from a non-object for classification into
different classes. Table 5 shows the mathematical expressions of the important feature
metrics, such as the co-occurrence metric, the entropy, standard deviation, HIS components,
etc. Table 5 shows the various extracted shape/size features used in the selected studies.

Table 5. Mathematical expressions of important feature matrices.

Metrics Equation
β
∑αP=1 ∑q=1 {1, i f I m ( p, q) = x and Im ( p + 4 p, q + 4q) =
Co-occurrence metric Z4 p4q ( x, y)
y 0, otherwise }
Z ( x,y) 2
Inertia moment ∑x Normalization | x − y |
Z ( x,y)
The absolute value of the difference ∑ x ∑y Normalization | x − y|
Z ( x,y)
Regular value of the difference ∑ x ∑y Normalization |y − x |
Z ( x,y) | x −y|
The modified absolute value of the difference ∑ x,y ∑ Z( I,m) | x+y|
Im
 
Mean µ ∑ xM=−y1=0 ( p − q) Z4 p,4q ( x, y)
_
2
Standard deviation ∑ xM=−y1=0 ( x − y) Z4 p,4q ( x, y)
 o
M −1 2 M −1
Entropy ∑M =0 m ∑ x =y=0 Z4 p,4q ( x, y )
 2
Variance ∑ xM=−y1=0 i − µ Z4 p,4q ( x, y)
_

Kurtosis ∑ xM=−y1=0 ( x − y)4 Z4 p,4q ( x, y)

3
Skewness ∑ xN=−y1=0 ( x − y) Z4 p,4q ( x, y)
Range max (Z (x,y)) – min (Z (x,y))
2
Homogeneity ∑ xM=−y1=0 Z4 p,4q ( x, y)
Correlation ∑ xN=−y1=0 Z4 p,4q ( x, y) ( x − µ ) (y − µ )
_x _y

Contrast ∑ xM=−y1=0 Z4 p,4q ( x, y)( Z4 p4q ( x, y))

2
Energy ∑ xM=−y1=0 Z4 p,4q ( x, y)
2
Gradient module ∑ xM=1 ∑yM=1 Z ( x, y) g( x ) , g(x) = x-M+1
M
Intensity Symmetry 1- ∑ x,y ( Z ( x, y) − Z ( M − 1 − x, M − 1 − j)|
HSV Space
1 b(rc − gc )+(rc −bc )c
Hue component { θbc ≤ gc 360 − θbc ≥ gc } θ = { 2 ( √ )}
b(rc − gc )2 + (r c −bc ) gc −bc c

Saturation component 3
1- ( r c + g c + bc ) (min(rc , gc , bc )]
Intensity component 1
3 (rc + gc + bc )
Smoothness S 1- 1+ σ12 ( Z )
x L

Consistency C ∑ xM=−01 H 2 ( Zi )

RQ6: What evaluation metrics are commonly seen in studies for assessing techniques?
Sustainability 2023, 15, 9643 17 of 23

A range of metrics is used to measure the performance of different classifiers used

for citrus fruit disease classifications. These evaluation parameters are often used to
assess models developed using different DL, ML, and statistical methods. The evaluation
parameters, their mathematical formulas and descriptions, and the count of the studies in
which they are used are shown in Table 6.

Table 6. Performance Measures used in Studies.

Evaluation Parameter Formula Used Description Count

correctlyclassi f iedimages The proportion of accurate assessments among
Accuracy 47
Totalnumbero f images all the assessments.
The percentage of infected classes correctly pre-
Sensitivity TruePositives ( TP) dicted among all existing infected classes. It is 17
TruePositives ( TP)+ FalseNegatives ( FN )
also called recall and the true-positive rate (TPR).

TrueNegatives ( TN ) Healthy fruit classes that are correctly predicted

Specificity 8
TrueNegative ( TN )+ FalsePositives ( FP) among all authentic, healthy classes.
The percentage of infected fruit classes that are
Precision TruePositives ( TP) appropriately categorized among the total num- 7
TruePositives ( TP)+ FalsePositives ( FP)
ber of cases classified.

FalsePositives( FP) The percentage of healthy classes identified as

FPR 3
FalsePositives( FP)+ TrueNegatives( TN ) infected classes.

FalseNegatives ( FN ) The percentage of infectious categories classified

FNR 2
FalseNegatives( FN )+ TruePositives ( TP) as the regular class.
The harmonic means of accuracy and sensitivity.
F-measure 2∗ Precision∗ Recall It expresses the equilibrium between recall and 7
Precision+ Recall
precision.
The percentage error is the difference between
|estimatedno.− actualno.| the expected number and the actual number rel-
Percentage error × 100 5
actualno. ative to the actual number measured in the per-
centage format.

Figure 12 presents a study count that assesses performance metrics. The most widely
used performance metric is the accuracy, which is followed by recall and precision. Speci-
ficity, p-value, F-measures, and percentage error are other widely used metrics of assess-
ment. Some metrics that are not counted in the graph with only one number, namely the
G-mean, coefficient of correlation, and MCC, are less general.

Figure 12. Count of performance measures used for the classification of diseases of citrus fruits.
Sustainability 2023, 15, 9643 18 of 23

Findings: The accuracy of an experiment, object, or value is measured by how closely

its results agree with the actual or accepted value. This is the most reliable and most com-
monly used performance metric. We found different research papers utilizing classification
accuracy to compare the different methods in the conducted studies. The second-most-used
metric was found to be the recall, as the research papers in question discuss its findings
using the metric to measure sensitivity to changes. The table highlights the importance of
accuracy over other performance metrics.
The data were analyzed from the selected studies published from 1995 to 2020. In
1995, one study was found, which was published in the USA; in 1998, the one selected
study was published in Belgium. Between duration 1999 and 2000, no papers were found
that worked mainly on diseases of citrus fruits (excluding citrus leaves, stems, etc.). For the
years 2001, 2004, 2006, and 2007, only a single study was found for each year; these studies
were published in the USA, Switzerland, India, and United Kingdom. It can be observed
that in recent year, an enormous amount of work has been done in this area, specifically
in 2019; i.e., 15 studies were published in this year. Additionally, Figure 13 depicts that a
maximum contribution is provided by the Netherlands (23), India (21), and the USA (12) in
the field of the detection of diseases of citrus fruits.

Figure 13. Geographical distribution of selected studies.

5. Summary and Findings

In terms of valuation, citrus fruits are a vital fruit crop in the global market and have
also contributed to a considerable effort to simplify multiple assessment practices along the
supply chain. From automated fruit inspection inside and outside the environment to yield
analysis with verified efficiencies and accuracies, machine vision has been demonstrated to
have outstanding potential and pragmatism. Table 7 includes the meta-analysis conducted
in this SLR.
Sustainability 2023, 15, 9643 19 of 23

Table 7. Meta-synthesis.

S.No Point Facts

Which technique was popularly used for the classification of
1 Machine Learning
diseases of citrus fruits in the studies assessed in our SLR?
Popularly used deep learning technique for citrus fruit disease
2 CNN
classification
Popularly used machine learning technique for citrus fruit dis-
3 SVM
ease classification
A popularly used statistical technique for citrus fruit dis-
4 PCA
ease classification
5 Popularly used image processing technique Thresholding
Technique that outperformed other techniques (ML/Non-ML)
6 Machine Learning (SVM)
in terms of accuracy
Defect type on which most of the state-of-the-art work has
7 Surface defects
been performed
8 The most frequently studied citrus fruit Orange
9 The most commonly used evaluation parameter Accuracy
10 The number of studies using ML/DL/statistical methods
Name of the disease on which most of the work has been per-
11 Canker
formed
Name of the fungi on which most of the work has been per-
12 P. digitatum
formed

6. Limitations
There were many challenges that the researchers faced during the execution of this
work. The predominant issue was the affordability of a regular database because of the
disease, pathogens, and infections present in fruits. This shortage of accessibility for
researchers and scholars decreases the ability of a database to facilitate work to be carried
out in this area. Standard publicly accessible databases are also required to enhance the
overall efficiency of such initiatives and make wide-ranging computer-aided prognostic
models suitable for identifying and classifying various diseases with more precision. The
implementation scenarios are constrained in some situations since the development of fruit
trees is dynamic; the collection of image datasets at various durations of growing time
reflects different characteristics that significantly contribute to complex differences in the
output of the system. It is not easy to obtain real-time datasets from the orchards of citrus
fruits because of environmental variability. The choice of the disease type and the signs
that are individually described or classified for samples from another set of citrus fruits is
another important consideration for authors and researchers. There is a significant need to
implement an automated system for image analysis and classification that largely depends
on the chosen ideal wavelengths to improve citrus disease detection performance. It is also
inferred from the literature review that the fruit sample should be collected from different
areas or regions with different characteristics to achieve a fair outcome.

7. Conclusions
This paper described an SLR focused on disease identification and classification in
citrus fruits using machine learning, deep learning, and statistical techniques covering
almost two decades. A total of 78 studies were selected from 1995 to 2020 (March) for further
analysis and evaluation to obtain important information for the users. The latest review of
the outcomes associated with citrus fruit disease classification and integral methodologies is
introduced in this SLR. In the era of smart agriculture, image acquisition, image processing,
feature extraction, and classification techniques are essential components for recognizing
Sustainability 2023, 15, 9643 20 of 23

and predicting various diseases present in citrus fruits. This paper presented different
conceptualized theories related to all the essential components of the recognition and
classification of citrus fruit diseases. This SLR has addressed nearly all the state-of-the-art
frameworks applicable to the detection of diseases in citrus fruits. Our goal is to make
researchers and scholars more interested in developing and applying new technologies
in this area. The paper also addressed stepwise measures to build a necessary automatic
framework to protect fruits from apparent disease by answering nine research questions.
As for the results and comparisons, a meta-analysis section has been included in this SLR.
In future work, more importance can be given to the technical aspects or methodology used
in the most significant papers for the better promotion of the research work.

Author Contributions: Conceptualization, P.D. and A.K.; methodology, software and validation,
P.D., Y.H., V.R.B. and A.K.; formal analysis, investigation and resources, V.R.B., Y.H. and Y.G.;
writing—original draft preparation, P.D. and A.K.; writing—review and editing, A.K., Y.H. and
A.A.A.; visualization, Y.G. and A.A.A.; supervision, Y.H., V.R.B. and A.K.; funding acquisition, Y.G.
and A.A.A. All authors have read and agreed to the published version of the manuscript.
Funding: This work was supported by the Deanship of Scientific Research, Vice Presidency for Grad-
uate Studies and Scientific Research, King Faisal University, Saudi Arabia, under Project GRANT2790.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Gulzar, Y.; Hamid, Y.; Soomro, A.B.; Alwan, A.A.; Journaux, L. A convolution neural network-based seed classification system.
Symmetry 2020, 12, 2018. [CrossRef]
2. Albarrak, K.; Gulzar, Y.; Hamid, Y.; Mehmood, A.; Soomro, A.B. A deep learning-based model for date fruit classification.
Sustainability 2022, 14, 6339. [CrossRef]
3. Aggarwal, S.; Gupta, S.; Gupta, D.; Gulzar, Y.; Juneja, S.; Alwan, A.A.; Nauman, A. An Artificial Intelligence-Based
Stacked Ensemble Approach for Prediction of Protein Subcellular Localization in Confocal Microscopy Images. Sustainability
2023, 15, 1695. [CrossRef]
4. Mamat, N.; Othman, M.F.; Abdulghafor, R.; Alwan, A.A.; Gulzar, Y. Enhancing Image Annotation Technique of Fruit Classification
Using a Deep Learning Approach. Sustainability 2023, 15, 901. [CrossRef]
5. Malhotra, R.; Chug, A. Software Maintainability: Systematic Literature Review and Current Trends. Int. J. Softw. Eng. Knowl. Eng.
2016, 26, 1221–1253. [CrossRef]
6. Kitchenham, B.; Brereton, O.; Budgen, D.; Turner, M.; Bailey, J.; Linkman, S. Systematic literature reviews in software engineering—
A systematic literature review. Inf. Softw. Technol 2009, 51, 7–15. [CrossRef]
7. Malhotra, R.; Lata, K. A systematic literature review on empirical studies towards prediction of software maintainability. Soft.
Comput. 2020, 24, 16655–16677. [CrossRef]
8. Marcos-Pablos, S.; García-Peñalvo, F.J. Decision support tools for SLR search string construction. In Proceedings of the Sixth
International Conference on Technological Ecosystems for Enhancing Multiculturality (TEEM’18), Salamanca, Spain, 24–26
October 2018; pp. 660–667.
9. Ali, A.; Gravino, C. A systematic literature review of software effort prediction using machine learning methods. J. Softw. Evol.
Process 2019, 31, 1–25. [CrossRef]
10. Malhotra, R. A systematic review of machine learning techniques for software fault prediction. Appl. Soft Comput. J. 2015,
27, 504–518. [CrossRef]
11. Ramesh, T.; Vijayaragavan, M.; Poongodi, M.; Hamdi, M.; Wang, H.; Bourouis, S. Peer-to-peer trust management in intelligent
transportation system: An Aumann’s agreement theorem based approach. ICT Express 2022, 8, 340–346.
12. Sahoo, S.K.; Mudligiriyappa, N.; Algethami, A.A.; Manoharan, P.; Hamdi, M.; Raahemifar, K. Intelligent Trust-Based Utility and
Reusability Model: Enhanced Security Using Unmanned Aerial Vehicles on Sensor Nodes. Appl. Sci. 2022, 12, 1317. [CrossRef]
13. Poongodi, M.; Malviya, M.; Hamdi, M.; Vijayakumar, V.; Mohammed, M.A.; Rauf, H.T.; Al-Dhlan, K.A. 5G based Blockchain
network for authentic and ethical keyword search engine. IET Commun. 2021, 16, 442–448.
14. Poongodi, M.; Malviya, M.; Kumar, C.; Hamdi, M.; Vijayakumar, V.; Nebhen, J.; Alyamani, H. New York City taxi trip duration
prediction using MLP and XGBoost. Int. J. Syst. Assur. Eng. Manag. 2021, 13, 16–27. [CrossRef]
15. Poongodi, M.; Nguyen, T.N.; Hamdi, M.; Cengiz, K. Global cryptocurrency trend prediction using social media. Inf. Process.
Manag. 2021, 58, 102708.
16. Soini, C.T.; Abid, M.R. Citrus Greening Infection Detection (CiGID) by Computer Vision and Deep Learning. In Proceeding of
the 3rd International Conference on Information System and Data Mining, Houston, TX, USA, 6–8 April 2019; pp. 21–26.
Sustainability 2023, 15, 9643 21 of 23

17. Behera, S.K.; Jena, L.; Rath, A.K.; Sethy, P.K. Disease Classification and Grading of Orange Using Machine Learning and Fuzzy
Logic. In Proceedings of the 2018 IEEE International Conference on Communication and Signal Processing, Chennai, India, 3–5
April 2018; pp. 678–682.
18. Khoje, S.A.; Bodhe, S.K.; Adsul, A. Automated Skin Defect Identification System for Fruit Grading Based on Discrete Curvelet
Transform. Int. J. Eng. Technol. 2013, 5, 3251–3256.
19. Kamalakannan, A.; Rajamanickam, G. Surface defect detection and classification in mandarin fruits using fuzzy image thresh-
olding, binary wavelet transform and linear classifier model. In Proceeding of the 4th International Conference on Advanced
Computing, Chennai, India, 13–15 December 2012; pp. 1–6.
20. Khan, A.M.; Paplinski, A.P. Blemish detection in citrus fruits. In Proceeding of the SPIT-IEEE Colloquium and International
Conference, Mumbai, India, 2008; Volume 1, pp. 262–271.
21. Lorente, D.; Escandell-Montero, P.; Cubero, S.; Gómez-Sanchis, J.; Blasco, J. Visible-NIR reflectance spectroscopy and manifold
learning methods applied to the detection of fungal infections on citrus fruit. J. Food Eng. 2015, 163, 17–24. [CrossRef]
22. Miller, W.M. Optical defect analysis of Florida citrus. Appl. Eng. Agric. 1995, 11, 855–860. [CrossRef]
23. Lan, Y. Comparison of machine learning methods for citrus greening detection on UAV multispectral images. Comput. Electron.
Agric. 2020, 171, 105234–105234. [CrossRef]
24. Capizzi, G.; Lo, G.; Sciuto, C.; Napoli, E.; Tramontana, M.; Wozniak, M. Automatic classification of fruit defects based on
Co-occurrence matrix and neural networks. In Proceedings of the Federated Conference on Computer Science and Information
Systems, Lodz, Poland, 13–16 September 2015; pp. 861–867.
25. Gómez-Sanchis, J. Hyperspectral LCTF-based system for classification of decay in mandarins caused by Penicillium digitatum and
Penicillium italicum using the most relevant bands and non-linear classifiers. Postharvest Biol. Technol. 2013, 82, 76–86. [CrossRef]
26. Bulanon, D.M.; Burks, T.F.; Kim, D.G.; Ritenour, M.A. Citrus black spot detection using hyperspectral image analysis. Agric. Eng.
Int. CIGR J. Open 2013, 15, 171–180.
27. Stegmayer, G.; Milone, D.H.; Garran, S.; Burdyn, L. Automatic recognition of quarantine citrus diseases. Expert Syst. Appl. 2013,
40, 3512–3517. [CrossRef]
28. Choi, D.; Lee, W.S.; Schueller, J.K.; Ehsani, R.; Roka, F.; Diamond, J. A performance comparison of RGB, NIR, and depth images
in immature citrus detection using deep learning algorithms for yield prediction. In Proceedings of the 2017 ASABE Annual
International Meeting, Spokane, WA, USA, 16–19 July 2017; pp. 1–6.
29. Rahmanian, A.; Mireei, S.A.; Sadri, S.; Gholami, M.; Nazeri, M. Application of biospeckle laser imaging for early detection of
chilling and freezing disorders in orange. Postharvest. Biol. Technol. 2020, 162, 111118. [CrossRef]
30. Capizzi, G.; Lo, G.; Sciuto, C.; Napoli, E.; Tramontana, M.; Woźniak, M. A novel neural networks-based texture image processing
algorithm for orange defects classification. Int. J. Comput. Sci. Appl. 2016, 13, 45–60.
31. Gómez-Sanchis, J.; Martín-Guerrero, J.D.; Soria-Olivas, E.; Martínez-Sober, M.; Magdalena-Benedito, R.; Blasco, J. Detecting
rottenness caused by Penicillium genus fungi in citrus fruits using machine learning techniques. Expert Syst. Appl. 2012,
39, 780–785. [CrossRef]
32. Wajid, A.; Singh, N.K.; Junjun, P.; Mughal, M.A. Recognition of ripe, unripe and scaled condition of orange citrus based on
decision tree classification. In Proceeding of International Conference on Computing, Mathematics and Engineering Technologies,
Sukkur, Pakistan, 3–4 March 2018; pp. 1–4.
33. Jahanbakhshi, A.; Momeny, M.; Mahmoudi, M.; Zhang, Y.D. Classification of sour lemons based on apparent defects using
stochastic pooling mechanism in deep convolutional neural networks. Sci. Hortic. 2020, 263, 109133. [CrossRef]
34. Miller, W.M.; Drouillard, G.P. Multiple feature analysis for machine vision grading of Florida citrus. Appl. Eng. Agric. 2001,
17, 627–633. [CrossRef]
35. Dael, M.V. A segmentation and classification algorithm for online detection of internal disorders in citrus using X-ray radiographs.
Postharvest. Biol. Technol. 2016, 112, 205–214. [CrossRef]
36. Itakura, K.; Saito, Y.; Suzuki, T.; Kondo, N.; Hosoi, F. Estimation of citrus maturity with fluorescence spectroscopy using deep
learning. Horticulturae 2019, 5, 1–9.
37. Theanjumpol, P.; Wongzeewasakun, K.; Muenmanee, N. Non-destructive identification and estimation of granulation in ‘Sai Num
Pung’ tangerine fruit using near infrared spectroscopy and chemometrics. Postharvest. Biol. Technol. 2019, 153, 13–20. [CrossRef]
38. Yang, G.L.; Luo, L.; Feng, Y.Q.; Zhao, H.S. Research of navel orange defect and color detection based on machine vision. Appl.
Mech. Mater. 2014, 513, 3442–3445. [CrossRef]
39. Jhawar, J. Orange Sorting by Applying Pattern Recognition on Colour Image. Procedia Comput. Sci. 2015, 78, 691–697. [CrossRef]
40. Abdulridha, J.; Batuman, O.; Ampatzidis, Y. UAV-based remote sensing technique to detect citrus canker disease utilizing
hyperspectral imaging and machine learning. Remote Sens. 2019, 11, 1373–1373. [CrossRef]
41. Sharif, M.; Khan, M.A.; Iqbal, Z.; Azam, M.F.; Lali, M.I.U.; Javed, M.Y. Detection and classification of citrus diseases in agriculture
based on optimized weighted segmentation and feature selection. Comput. Electron. Agric. 2017, 150, 220–234. [CrossRef]
42. Qiu, S.; Wang, J.; Tang, C.; Du, D. Comparison of ELM, RF, and SVM on E-nose and E-tongue to trace the quality status of
mandarin (Citrus unshiu Marc.). J. Food Eng. 2015, 166, 193–203. [CrossRef]
43. Steinmetz, V.; Biavati, E.; Molto, E.; Pons, R.; Fornes, I. Predicting the maturity of oranges with non destructive sensors. In
Proceedings of the International Symposium on Sensors in Horticulture, Tune Landboskole, Denmark, 21–26 August 1995;
Volume 421, pp. 271–278.
Sustainability 2023, 15, 9643 22 of 23

44. Zhang, Y.; Lee, W.S.; Li, M.; Zheng, L.; Ritenour, M.A. Non-destructive recognition and classification of citrus fruit blemishes
based on ant colony optimized spectral information. Postharvest. Biol. Technol. 2018, 143, 119–128. [CrossRef]
45. Singh, H.; Gill, N. Machine Vision Based Color Grading of Kinnow Mandarin. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 2015,
5, 1253–1259.
46. Moomkesh, S.; Ahmad, S.; Sadeghi, M. ScienceDirect Early detection of freezing damage in sweet lemons using Vis/SWNIR
spectroscopy. Biosyst. Eng. 2017, 164, 157–170. [CrossRef]
47. Gawande, M.A.; Dhande, S.S. Implementation of Fruits Grading and Sorting System by using Image Processing and Data
Classifier. SSRG Int. J. Comput. Sci. Eng. 2015, 2, 22–27.
48. Gómez-Sanchis, J. Hyperspectral system for early detection of rottenness caused by Penicillium digitatum in mandarins. J. Food
Eng. 2008, 89, 80–86. [CrossRef]
49. Mercol, J.P.; Gambini, J.; Santos, J.M. Automatic classification of oranges using image processing and data mining techniques. In
Proceedings of the XIV Congreso Argentino de Ciencias de la Computación, Río Cuarto, Argentina, 14–18 October 2008.
50. Qin, J.; Burks, T.F.; Kim, M.S.; Chao, K.; Ritenour, M.A. Citrus canker detection using hyperspectral reflectance imaging and
PCA-based image classification method. Sens. Instrum. Food Qual. Saf. 2008, 2, 168–177. [CrossRef]
51. Fiona, B.O.; Thomas, M.R.; Maria, S.; Hannah, I.J. Identification Of Ripe And Unripe Citrus Fruits Using Artificial Neural
Network. J. Phys. Conf. Ser. 2019, 1362, 12033–12033. [CrossRef]
52. Zhang, Y. Navel Orange Pest Image Recognition Based on Convolution Deep Neural Network. Int. J. Simul. Syst. Sci. Technol.
2008, 17, 8–12.
53. Li, J.; Huang, W.; Tian, X.; Wang, C.; Fan, S.; Zhao, C. Fast detection and visualization of early decay in citrus using Vis-NIR
hyperspectral imaging. Comput. Electron. Agric. 2016, 127, 582–592. [CrossRef]
54. Dong, C.; Ye, Y.; Zhang, J.; Zhu, H.; Liu, F. Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging
Technology Combining PCA and B-Spline Lighting Correction Method. J. Integr. Agric. 2014, 13, 60671–60672. [CrossRef]
55. Thendral, R.; Suhasini, A. Automated skin defect identification system for orange fruit grading based on genetic algorithm. Curr.
Sci. 2017, 112, 1704–1711. [CrossRef]
56. Lorente, D.; Zude, M.; Regen, C.; Palou, L.; Gómez-Sanchis, J.; Blasco, J. Early decay detection in citrus fruit using laser-light
backscattering imaging. Postharvest. Biol. Technol. 2013, 86, 424–430. [CrossRef]
57. Kaur, M.; Sharma, R. Quality Detection of Fruits by Using ANN Technique. IOSR J. Electron. Commun. Eng. 2015, 10, 2278–2834.
58. López-García, F.; Andreu-García, G.; Blasco, J.; Aleixos, N.; Valiente, J.M. Automatic detection of skin defects in citrus fruits using
a multivariate image analysis approach. Comput. Electron. Agric. 2010, 71, 189–197. [CrossRef]
59. Li, J. Detection of early decayed oranges based on multispectral principal component image combining both bi-dimensional
empirical mode decomposition and watershed segmentation method. Postharvest. Biol. Technol. 2019, 158, 110986–110986.
[CrossRef]
60. Wen, T. Rapid detection and classification of citrus fruits infestation by Bactrocera dorsalis (Hendel) based on electronic nose.
Postharvest. Biol. Technol. 2018, 147, 156–165. [CrossRef]
61. Mohana, S.H.; Prabhakar, C.J. Automatic Detection of Surface Defects on Citrus Fruit based on Computer Vision Techniques. Int.
J. Image Graph. Signal Process 2015, 7, 11–19.
62. Cubero, S.; Blasco, J.; Cubero, S.; Blasco, J.; Ferrer, A. VIS/NIR hyperspectral imaging and N-way PLS-DA models for detection
of decay lesions in citrus fruits. Chemom. Intell. Lab. Syst. 2016, 156, 241–248.
63. Saha, R. Orange Fruit Disease Classification using Deep Learning Approach. Int. J. Adv. Trends Comput. Sci. Eng. 2020,
9, 2297–2301. [CrossRef]
64. Cevallos-Cevallos, J.M.; Futch, D.B.; Shilts, T.; Folimonova, S.Y.; Reyes-De-Corcuera, J.I. GC-MS metabolomic differentiation of
selected citrus varieties with different sensitivity to citrus huanglongbing. Plant Physiol. Biochem. 2012, 53, 69–76. [CrossRef]
65. Pourreza, A.; Lee, W.S.; Ritenour, M.A.; Roberts, P. Spectral characteristics of citrus black spot disease. Horttechnology 2016,
26, 254–260. [CrossRef]
66. Magwaza, L.S. The use of Vis/NIRS and chemometric analysis to predict fruit defects and postharvest behaviour of “Nules
Clementine” mandarin fruit. Food Chem. 2014, 163, 267–274. [CrossRef]
67. Kavitha, V.; Devi, M.R. Predicting the Diseases by Graphcut Method for Citrus Fruits. Int. Res. J. Manag. Sci. Technol. 2016,
7, 465–470.
68. Rong, D.; Rao, X.; Ying, Y. Computer vision detection of surface defect on oranges by means of a sliding comparison window
local segmentation algorithm. Comput. Electron. Agric. 2017, 137, 59–68. [CrossRef]
69. Ranjit, K.N.; Raghunandan, K.S.; Naveen, C.; Chethan, H.K.; Sunil, C. Deep Features Based Approach for Fruit Disease Detection
and Classification. Int. J. Comput. Sci. Eng. 2019, 7, 2347–2693.
70. Kim, D.G.; Burks, T.F.; Qin, J.; Bulanon, D.M. Classification of grapefruit peel diseases using color texture feature analysis. Int. J.
Agric. Biol. Eng. 2009, 2, 41–50.
71. Ashwani, Y.; Dubey, K.; Ratan, R.; Rocha, A. Computer vision based analysis and detection of defects in fruits causes due to
nutrients deficiency. Clust. Comput. 2019, 6, 10586–10605.
72. Senthilkumar, C.; Kamarasan, M. An Effective Classification of Citrus Fruits Diseases using Adaptive Gamma Correction with
Deep Learning Model. Int. J. Eng. Adv. Technol. 2020, 9, 2249–8958. [CrossRef]
Sustainability 2023, 15, 9643 23 of 23

73. Behera, S.K.; Rath, A.K.; Sethy, P.K. Automatic Fruits Identification and Disease Analysis using Machine Learning Techniques.
Int. J. Innov. Technol. Explor. Eng. 2019, 8, 103–107.
74. Kim, G.; Lee, K.; Choi, K.; Son, J.; Choi, D.; Kang, S. Defect and ripeness inspection of citrus using NIR transmission spectrum. In
Key Engineering Materials; Trans Tech Publications: Stafa-Zurich, Switzerland, 2004; pp. 1008–1013.
75. Lopez, J.J.; Aguilera, E.; Cobos, M. Defect detection and classification in citrus using computer vision. In Proceeding of the
International Conference on Neural Information Processing, Bangkok, Thailand, 1–5 December 2009; pp. 11–18.
76. Pan, W.; Qin, J.; Xiang, X.; Wu, Y.; Tan, Y.; Xiang, L. A Smart Mobile Diagnosis System for Citrus Diseases Based on Densely
Connected Convolutional Networks. IEEE Access 2019, 7, 87534–87542. [CrossRef]
77. Kumar, G.; S, Y. Identification and Classification of Fruit Diseases. In Proceeding of the International Conference on Recent
Trends in Image Processing and Pattern Recognition, Bidar, India, 16–17 December 2016; pp. 382–390.
78. Doh, B.; Zhang, D.; Shen, Y.; Hussain, F.; Doh, R.F.; Ayepah, K. Automatic citrus fruit disease detection by phenotyping using
machine learning. In Proceeding of the 25th IEEE International Conference on Automation and Computing, Lancaster, UK, 5–7
September 2019; pp. 1–5.
79. Lorente, D.; Aleixos, N.; Gómez-Sanchis, J.; Cubero, S.; Blasco, J. Selection of Optimal Wavelength Features for Decay Detection
in Citrus Fruit Using the ROC Curve and Neural Networks. Food Bioprocess Technol. 2011, 6, 530–541. [CrossRef]
80. Vijayarekha, K.; Govindaraj, R. Citrus fruit external defect classification using wavelet packet transform features and ANN.
In Proceedings of the 2006 IEEE International Conference on Industrial Technology, Mumbai, India, 15–17 December 2006;
pp. 2872–2877.
81. Bhargava, A.; Bansal, A. Automatic Detection and Grading of Multiple Fruits by Machine Learning. Food Anal. Methods 2019,
13, 751–761. [CrossRef]
82. Chen, Y.; Wu, J.; Cui, M. Automatic classification and detection of oranges based on computer vision. In Proceedings of the 4th
International Conference on Computer and Communications, Chengdu, China, 7–10 December 2018; pp. 1551–1556.
83. Xie, X. Image matching algorithm of defects on navel orange surface based on compressed sensing. J. Ambient. Intell. Humaniz.
Comput. 2018, 1, 1–9. [CrossRef]
84. Huijun, L.; Xiangfeng, W. Rapid shelf-life identification model of citrus based on near infrared spectroscopy. In Proceedings of
the International Symposium on Knowledge Acquisition and Modeling, Wuhan, China, 21–22 December 2008; pp. 298–301.
85. Pham, V.H.; Lee, B.R. An image segmentation approach for fruit defect detection using k-means clustering and graph-based
algorithm. Vietnam J. Comput. Sci. 2015, 2, 25–33. [CrossRef]
86. Turitsyna, E.G.; Webb, S. Hyperspectral detection of citrus damage with Mahalanobiskernel classifier. Electron. Lett. 2005,
41, 40–41.
87. Enciso-Aragón, C.J.; Jimenez-Moreno, R. Quality control system by means of CNN and fuzzy systems. Int. J. Appl. Eng. Res.
2018, 13, 12846–12853.
88. Patel, H.; Prajapati, R.; Patel, M. Detection of Quality in Orange Fruit Image using SVM Classifier. In Proceedings of the 3rd
International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 23–25 April 2019; pp. 74–78.
89. Taghadomi-Saberi, S.; Masoumi, A.A.; Sadeghi, M.; Zekri, M. Integration of wavelet network and image processing for
determination of total pigments in bitter orange (Citrus aurantium L.) peel during ripening. J. Food Process Eng. 2019, 42, e13120.
[CrossRef]
90. Cooper, D.; Doucet, L.; Pratt, M. Detection and classification of citrus green mold caused by Penicillium digitatum using
multispectral imaging. J. Sci. Food Agric. 2018, 98, 3542–3550.
91. Du, C. Recent developments in the applications of image processing techniques for food quality evaluation. Trends Food Sci.
Technol. 2004, 15, 230–249. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.