Jun 2026· Agricultural Science Digest - A Research Journal· 0 citations· 32 references
TL;DR
A sequential CNN-based framework was developed for the automated identification and classification of mango leaf images into four classes: Sooty mould, powdery mildew, gall midge and healthy, confirming the model’s capability to distinguish between disease, pest and healthy conditions with minimal misclassification.
Abstract
Background: Mango (Mangifera indica) is a commercially important fruit crop, but its yield and quality are often threatened by diseases and insect pests. Among the most common are fungal diseases such as sooty mould and powdery mildew and insect pests like gall midge. If not detected early, these cause substantial economic losses to farmers. Manual identification is time-consuming and error-prone, creating the need for automated solutions. Deep learning, particularly Convolutional Neural Networks (CNNs), has shown strong potential in plant disease and pest recognition.
Methods: In this study, a sequential CNN-based framework was developed for the automated identification and classification of mango leaf images into four classes: Sooty mould, powdery mildew, gall midge and healthy. The architecture consisted of five convolutional layers with max-pooling for feature extraction, followed by fully connected layers for classification. Model performance was assessed using accuracy, precision, recall, F1-score and confusion matrix analysis.
Result: The model achieved an overall accuracy of 96.0%, with high weighted average precision, recall and F1-scores, indicating reliable performance despite class imbalance. The confusion matrix confirmed the model’s capability to distinguish between disease, pest and healthy conditions with minimal misclassification.
The infection of mango leaves is a major yield and fruit quality loss problem, and the necessity of having a precise and early diagnostic system for sustainable agriculture. Five convolutional neural network (CNN) architectures–namely, VGG16, VGG19, ResNet50, DenseNet121, and a custom-built AlexNet variant–were evaluated for their performance in classifying eight categories of mango leaf diseases. All models were pre-trained using a well-defined dataset of healthy and infected leaves and fine-tuned using transfer learning. VGG16 had the highest test accuracy of 99%, which was better than ResNet50 (91.5%), DenseNet121 (90.5%), VGG19 (87%), and AlexNet (86.5%). Further evaluation of these models using confusion matrices and F1-scores was conducted to ensure the strength of these models for various diseases including powdery mildew, anthracnose, and bacterial canker. Overall, the results underscore that advanced CNN models—particularly VGG16— can deliver near-expert precision in automated mango leaf disease identification. The leaf disease of mango is a major issue confronting farmers in Southeast Asia, particularly in India. Mango leaf disease is one of the biggest challenges faced by the farmers of south-east Asian countries, especially India.
P. G. K., Kiran Kumar H R· 2026 International Conferenc...· 0 citations
The proposed automated leaf disease detection system using image processing and deep learning techniques can detect leaf diseases effectively and efficiently, making it a useful and cost-effective solution for supporting farmers and agricultural experts in early disease diagnosis.
Shilpa T S, K. U, A. Jajur. J· World Journal of Advanced En...· 0 citations
India is one of the biggest producers and exporters of mangoes in the world, yet its cultivation is persistently threatened diseases that reduce yield, fruit quality, and orchard longevity. Traditional disease diagnosis is based on agronomists' hand visual inspection, which is a laborious, subjective, and challenging technique to scale across vast plantations. This research provides a hybrid deep learning system that incorporates AlexNet and ResNet-50 for the automated classification of five commercially relevant mango leaf diseases: Bacterial Canker, Anthracnose, Powdery Mildew, Sooty Mould and Healthy foliage. Through a fused, jointly trained classification head, the suggested architecture combines the deep, residual feature hierarchies of ResNet-50 with the shallow, texture-sensitive representations learned by AlexNet, enabling the network to take advantage of complementary visual cues that neither backbone fully captures on its own. The hybrid model was implemented and trained using MATLAB. The trained model achieved a validation accuracy of 99.47%. Comparative analysis against standalone AlexNet, standalone ResNet-50, and other architectures reported in the recent mango plant-disease literature indicates that the hybrid fusion strategy offers a favourable balance of accuracy and convergence stability.
Ranu Solanki, D. Yadav· International Journal For Mu...· 0 citations
This research presents an automated detection method using the Single Shot Detector (SSD) framework, with ResNet-50 as the backbone and a Feature Pyramid Network (FPN) to manage multi-scale feature representations to strengthen plant disease monitoring systems.
Kusworo Adi, A. Setiadi, C. E. Widodo et al.· JOIV: International Journal...· 0 citations
Background: Groundnut farming is affected by several leaf diseases that reduce crop yield. Farmers often rely on visual inspection, which can be inaccurate and time-consuming. Early and precise identification of leaf diseases is essential for effective crop management. This study presents a deep learning-based solution to automate disease detection. Methods: A modified EfficientNetB0 architecture is proposed for classifying five types of groundnut leaf conditions: healthy, leaf spot (early and late), alternaria leaf spot, rust and rosette. The dataset is sourced from the Mendeley database that was collected from Ramchandrapur village in West Bengal, India, under natural lighting. A total of 1,720 images were captured using a DSLR camera. After verification and cleaning, the dataset was split into 1,204 training and 516 testing images. All images were resized, normalized and label-encoded. Data augmentation techniques such as rotation, flipping and zoom were used to improve generalization. Regularization was applied to reduce overfitting. The model was trained for 100 epochs using the RMSprop optimizer and early stopping. Result: The model achieved a test accuracy of 99.22%. Evaluation metrics confirm high performance across all classes. The model outperformed existing methods such as ResNet50 (82.3%), CNN with progressive resizing (96.12%) and LeafNet (97.23%). It also maintained low training and validation loss throughout training. These results highlight the model’s robustness, accuracy and potential for real-time field applications. The approach is lightweight and suitable for mobile-based disease detection tools.
Jie-Shin Lin, Y. Tai, Suh-Chen Hsiao et al.· Legume Research An Internati...· 0 citations
Agricultural production is exposed to losses when plants became infected with diseases from the environment, which in turn threatens food security; therefore, having the ability to detect plant diseases early on gives farmers the opportunity to minimize the loss they incur. Sunflower (Helianthus annuus) is Ranking among other oilseed crops worldwide for total agricultural production, and it has a high risk of being affected by diseases that cause reduced crop yield and quality, e.g., Downy mildew, grey mould, and leaf scars. Disease detection using conventional methods usually involves visual inspections by trained personnel; this process, however, is very time consuming, subjective, and could produce numerous errors. To counteract these issues, this paper proposes a hybrid learning framework for plant disease detection that combines deep feature-driven image analysis with a combination of two classifiers used in an ensemble mode to create a single final classification. The use of MobileNetV2 will act as the feature extraction process for the hybrid learning framework, while the classifier portion of the hybrid learning framework will consist of two K-Nearest Neighbour classifiers. Classification using SVM and RF classifiers will be completed using a combination of ensemble voting. Grad-CAM (gradient-weighted class activation maps) will be used to improve the interpretability of the disease classification results by identifying affected areas on images. Test results for the hybrid learning framework reveal an overall accuracy of 98.8%, compared to the accuracy of the two classifiers used separately: 95.8% for CNN, 93% for SVM, and 96.0% for RF. The confusion matrix for the two classifiers shows a significant number of accurate classifications with minimal misclassifications. The proposed hybrid learning framework for plant disease detection provides an effective method for detecting plant diseases in real time, interpretable results, and potential for scalability.
Kshirsagar Soumya, Mr. G Sekhar Reddy, D. G. L. A. Babu et al.· International Conference Com...· 0 citations
