Mango Diseases Classification Solutions Using Machine Learning or Deep Learning: A Review ()
1. Introduction
Mango (MagniferaIndica L.) is a lucrative fruit widely grown in tropical countries. This fruit belongs to the anacardiaceous family [1]. It contains significant amounts of vitamin A and vitamin C [2]. It is called the “King of fruits” because of its alluring aroma, flavorful pulp and high nutritional value that attract many mango lovers from around the world [1] [3]. In 2021, mango was the third most traded tropical fruit after pineapple and avocado in terms of quantities exported. The Asian continent (912.510 tons exported) is the largest producer of mango in the world in 2021. It is followed by, South America (620.745 tons), Central America and the Caribbean (545.428 tons), Africa (202.010 tons), and Oceania (4.254 tons) [4].
However, mango suffers from several diseases at all stages of its life. Such diseases lead to a considerable reduction in both quality and quantity of mango production. In addition, its lead to a reduction of mango price on the local and international markets. Due to poverty and the lack of infrastructure in many parts of the word (e.g.: developing countries), the rapid diagnosis of these diseases remains difficult [5]. Mango growers and plant pathologists use naked eye observation to diagnose mango diseases and make decisions based on their experiences. Such decisions are often not accurate and biased sometimes because many types of mango diseases appear to be the same since their symptoms are similar at the early stage [6] [7]. This approach leads to unnecessary use of pesticides, which results in higher production costs. In addition, techniques used by plant pathologists are time-consuming and relatively expensive for mango growers. Timely and automatic diagnosis of mango diseases is, therefore very critical [8].
In recent years, with the advances in the field of computer vision, researchers have proposed several automatic diagnostic solutions for grading mango and diagnosing its diseases. Such solutions are based on classical Machine Learning (ML) algorithms and Deep Learning (DL) algorithms.
This paper proposes a review of mango diseases identification and automatic quality grading solutions proposed by researchers during the last decade.
The specific contributions of this paper include:
· A critical analysis of recently proposed mango diseases automatic diagnostic and quality grading solutions.
· Identification of limitations of such solutions and potential challenges could help researchers in this area.
The paper is organized as follows: Section 2 identifies the most common diseases of mango treated by researchers in recent years, Sections 3 provides a critical analysis of the proposed solutions based on classical ML and DL algorithms, Section 4 shows the potential challenges in automatic diagnosis of mango diseases and the last section concludes the paper.
2. A Review of the Most Common Mango Diseases
The production of mangoes suffers from several problems. These problems are caused by pests and diseases witch kill about 30% - 40% of the crop [2]. Mango diseases are caused by a number of pathogens like bacteria, fungi, virus, algae and insect which attack all the parts of the plant, such as trunk, brunch, leaf, twig, petiole, flower and fruit [1] [2] [8]. The causes of these diseases can also be of climatic origin or unfavorable environmental conditions [9] [10]. Table 1 provides a summary of fourteen mango disease diagnostic solutions proposed by researchers between 2017 and 2022.
![]()
Table 1. A list of fourteen treated mango diseases by researchers between 2017 and 2022.
Based on this table, we can say Anthracnose (Figure 1(a)) is the most common mango diseases treated by researchers during this period since losses of mango trees are caused up to 39% worldwide by this disease [11]. It is followed by Sooty Mold (Figure 1(b)), Powdery mildew (Figure 1(c), Gall Midge (Golmich, Golmachi or leaf Gall) (Figure 1(d)), Scab (Figure 1(e)) and Red Rust (Figure 1(f)). Figure 2 shows the number of times these diseases are treated based on fourteen topics in Table 1.
3. Automatic Diagnosis of Mango Diseases
In recent years, several solutions for automatic diagnosis of mango diseases have been proposed. These solutions can be divided into two categories: those based on classical ML algorithms on the one hand, and those based on DL on the other.
3.1. Automatic Diagnosis Based on Machine Learning
In the field of automatic plant disease detection and identification, IP techniques combined with classical ML algorithms have obtained excellent results. In the proposed models, IP techniques are used to improve the quality of images used for training and testing, while ML algorithms are used for image segmentation, feature extraction and finally, image classification.
For example, authors of [8] proposed a MLAD (mango leaf ailment detection) based on Neural Network and Support Vector Machine (SVM) classifiers. MLAD can detect and atomically classify four diseases, namely scab, anthracnose, Red Rust and Sooty Mold, with an average accuracy of 80%, although the
![]()
Figure 2. Ranking of the most common and treated mango diseases. The ranking depends on the number of time the disease is present in fourteen considered papers of Table 1.
model suffers from a lack of training data. In [16] authors proposed a novel segmentation approach to segment the diseased part by considering the vein pattern of the mango diseased leaf. Diseases treated in this study are sooty mold and powdery mildew. The leaf’s features were extracted on the basis of color and texture using canonical correlation analysis (CCA)-based fusion. They used ten different classifiers to identify leaf diseases but the best results were obtained with cubic SVM classifier (95.5% of accuracy). However, the amount of data used is very small and the time needed to identify diseased leaves is significant. Moreover, the proposed architecture does not allow for real-time identification of treated diseases. In the study of [14], a method for automatic mango leaf diseases recognition and classification is developed. Authors used k-means clustering for image segmentation, GLCM (gray level color co-occurrence metrics) for feature extraction and SVM for diseases classification. SVM classifier gets accuracy up to 96%. But one of the proposed model’s limits is that the presence of several diseases in the same region of a leaf makes image segmentation difficult. Similarly, the variation in leaf color, texture, and shape made the feature selection phase difficult. Authors of [11] used K-means clustering for image segmentation and SVM and Neural Network Ensemble (NNE) to automatically detect and identify the symptoms of mango leaf diseases namely Dag disease, Golmachi disease, Shutimold disease and Red Moricha disease. The proposed system could detect and classify the diseases with average accuracy up to 80%. However, the authors believe that by increasing the training data, the model would perform better. In [12] authors proposed an Artificial Neural Network (ANN) combined with a Modified Rotation Kernel Transformation (MRKT) system based on directional feature (shape, color or other deceptive features) extraction for recognition and classification of mango disease named anthracnose. They obtained an accuracy of 98% using the proposed MRKT. The performances obtained are very significant but the proposed system is only limited to anthracnose disease. [13] is an improvement of [12] in order to recognize diseases with more accuracy. Authors introduce an enhanced Wavelet-PCA based Statistical Feature Extraction technique with MRKT based directional features for plant disease recognition. They used an ANN to diagnose both Powdery Mildew and Anthracnose disease. They obtained 98.50%, 98.70% and 98.75% of accuracy respectively for flowers, leaves and fruits.
Several solutions have been proposed for grading the quality of mangoes according to their defects, shape, size and maturity.
For example, authors of [18] implemented a real time automated mango fruit grading scheme according to maturity level and quality attributes like shape, size and surface defect. They used Support Vector Regression (SVR) from maturity prediction, Multi Attribute Decision Making (MADM) system for quality estimation and a fuzzy incremental learning algorithm for mangoes grading. Nearly 87% of accuracy has been achieved by the proposed system. In [19] authors developed an image processing algorithm capable to identify defects and detect maturity of mango fruits based on shape, color and size features using digital images. Such method is useful since it allows automatic sorting of mango fruits. However, it is only able to identify visible defect on mango fruit. Authors of [20] developed a method based on segmentation techniques namely thresholding, K-means clustering, watershed and region growing and a multilayered back propagation neural network (BPNN) classifier for detection and grading of fruits (mango, grape and pomegranate) affected by Anthracnose fungal disease. Experimental results show that classification accuracies are 84.65% and 76.6% respectively for normal and affected anthracnose fruit. In the study of [21], authors designed and developed an efficient algorithm for detecting and sorting the mango fruit with an accuracy more than 80% in grading, compared to human expert sorting. They used Fuzzy inference to extract size, color and skin features on mango RGB images and fuzzy classification to perform the mango classification. Table 2 summarizes proposed models based on classical ML algorithms used for automatic diagnosis of mango diseases and mango quality grading.
3.2. Automatic Diagnosis Based on Deep Learning
In the last decade, in the field of automatic plant disease detection and identification, models based on DL algorithms are the most proposed by researchers. These models have achieved state-of-the-art performance on ImageNet and other benchmark datasets [22]. The latest generation of Convolutional Neural Networks (CNNs) has achieved impressive results in image classification and is considered as the leading method for object detection in computer vision [22] [23].
For example, in [2], authors proposed ResNet-CNNs (ResNet18, ResNet34 and ResNet50) coupled with Transfer Learning (TL) for automatic detection and identification of four mango leaf diseases namely, anthracnose, powdery mildew,
![]()
Table 2. Models based on ML algorithms.
This table indicates, chronologically, for each article considered, the year of publication, the objectives, the segmentation and classification algorithms used and the performances obtained.
red rust and golmich. Results show that ResNet50 gives better performance with an accuracy of 91.50%. Authors of [6] implemented a Feed-Forward Neural Network (FFNN) with Hybrid Metaheuristic Feature Selection (HMFS) for classifying 3 mango diseases named Anthracnose, Gall Midge, and Powdery Mildew. The proposed model achieved an accuracy of 89.41% more than comparative CNN such as AlexNet (78.64%), VGG16 (79.92%) and ResNet (84.88%). In the study of [7] a Multilayer Convolutional Neural Network (MCNN) model for the classification of mango leaves infected with anthracnose fungal disease is used. Authors used on the one hand, mango leaves images from Plant Village dataset and on the other hand real-time captured mango leaf images. Experimental results showed an accuracy of 97.13% in the classification of diseased leaves. However, images taken in real condition majorly suffers from the problem of Variation in Temperature, Shadowing, overlapping of leaves, and presence of multiple objects. Authors of [9] developed a model based CNN and named FrCNnet to segment and identify the diseases (Anthracnose and apical necrosis) on the mango leaves. They used TL technique in their model. To evaluate the model, they compare it with state-of-art models like VGG16, VGG19 and Unet. The proposed model’s accuracy is 99.2% with a false negative rate (FNR) of 0.8%, which is much higher than the other models. In [10] authors implemented a CNN with three hidden layers inspired by VGG-16, VGG-19 and AlexNet capable to identify five different diseases in mango leaves. These ones are Anthracnose, Alternaria leaf spots, Leaf Gall, Leaf webber and Leaf burn. The proposed model achieved an accuracy of 96.67% classifying diseased images. But the classification accuracy can be further increased by providing more images in the dataset and tuning the parameters of the CNN model. Authors of [15] proposed a CNN model based on AlexNet architecture for detecting anthracnose mango leaf disease. The system is developed using Tensor Flow framework and a dataset of mango images captured in real condition with a CDD camera. The developed system was more than 70% accurate to isolate the diseased mango leaves. The model uses data taken under real field conditions but is specific to anthracnose. In the study of [24], authors developed a CNN based on AlexNet architecture and using TL to detect and classify Mango and Grapes leaf diseases. They achieved an accuracy rate of 89% and 99% respectively for mango and grapes leaves. They implemented this model as an Android app named JIT CROPFIX. However, disease identification in real-time condition is a very challenging task compared to laboratory conditions. Another limitation of the proposed model is that the model ignores tiny or invisible defects on the fruit, which reduces the accuracy. In [17] authors proposed a novel framework for mango leaves disease classification namely Anthracnose, Bacterial black spot, and Sooty mold. They used a CNN with crossover-based levy flight distribution for better feature selection, MobileNetV2 model for the learning stage and SVM for diseases classification. The experimental results show classification performances over other state-of-art methods. Authors of [25] implemented a computer vision algorithm for defect detection on the surface of to Indian mango fruits varieties named Chausa and Dashehari. The overall efficiency and accuracy of proposed algorithm were 93.3% and 88.6%, respectively. However, multiple small defects or single large defect around the edge decreases the accuracy. Efficiency and accuracy of the proposed algorithm decrease when the severity of defect (blemishes or disease infected area) on the surface of fruit increased.
Several DL based solutions have been proposed for automatic sorting or grading mangoes. In [3] for example, combined and studied several DL models based on AlexNet, VVGGs, and ResNet to see which one performs best in classifying mangoes by quality. The results showed that the VGG16 model, combined with the Mask R-CNN algorithm (for image background removal) and the use of TL (on ImageNet) gave the best performance for this task (accuracy: 83.5%). Authors of [26] designed and implemented a system using non-destructive thermal imaging by deep learning technique for mango sorting and grading according to their quality. The proposed system is based on SqueezeNet deep CNN. Mango quality grading is performed by using parameters such as shape, defects, maturity and size. They used TL technique based pretrained SqueezeNet model and achieved 93.33% and 92.27% of accuracy for RGB and thermal images respectively, with the training time of 30.03 and 7.38 minutes for RGB and thermal images. Results show that the training time is lower with the thermal images (by factor of 4X). Table 3 summarizes proposed models based on DL and used for automatic diagnosis of mango diseases and mango automatic quality grading.
![]()
![]()
Table 3. Models based on DL algorithms.
This table presents, chronologically, for each article considered, the year of publication, the objectives, the CNN algorithms used and the performances obtained.
4. Potential Challenges in Automatic Diagnosis of Mango Diseases
Classical ML and DL algorithms have achieved excellent results in automatic detection and classification of mango diseases. However, the following challenges must be addressed:
· The models proposed so far suffer from a lack of training data, which increases the time to identify diseases and reduces the performance of these models [8] [10] [11] [16].
· The proposed models do not provide real-time diagnosis of mango diseases. This would be very beneficial for mango growers and plant pathologists [16].
· The presence of several diseases in the same region of a leaf makes segmentation difficult. This reduces the accuracy of the model [14].
· Images taken in real condition majorly suffers from the problem of the variation in leaf color, texture, shape, temperature, shadowing, overlapping of leaves and presence of multiple objects. This makes the feature extraction phase difficult. Compared to laboratory conditions disease identification in real-time condition is a very challenging task [7] [14] [24].
· Detection of tiny (or invisible) defects (disease infected area or blemishes) and single large defect around the mango leaf or mango fruit edge is also a challenge [24] [25].
· Mango diseases such as Anthracnose, Sooty Mold, Powdery mildew, Gall Midge, Scab, Red Rust, etc., can affect leaves as well as panicles, stem, flowers, leaves, twigs and fruits. But so far, researchers have focused on leaf-based diagnosis.
5. Conclusion
This paper is a review of mango’s most common diseases treated and solutions proposed for automatic diagnosis of such diseases during the last decade. We divided these solutions into to two categories: classical ML based solutions and DL based solutions. During the last five years, DL-based solutions, especially CNNs, have been the most widely used since this technology requires less or no preprocessing of images compared to other techniques and offers excellent performances. In this study, a critical analysis of the proposed solutions allowed us to know their limitations and then to identify potential challenges that could be of interest to researchers in automatic diagnosis of mango diseases. We aim, for future work, to propose a dataset of mango diseases whose images will be captured in mango orchards of a Sahelian country like Senegal. Then we will use the CNN model (e.g. VGG16, Unet, AlexNet, MobileNet, …) which will give the best performances on this dataset and finally deploy this model in a mobile application to allow mango growers to be able to diagnose diseases in their mango orchards without the intervention of plant pathologist. We will focus on anthracnose and peduncular rot diseases which causes significant damage to mango production in Senegal.