Aug 2026· Legume Research An International Journal· 0 citations· 28 references
TL;DR
Findings indicate that the lightweight MobileNet architecture can effectively support reliable and scalable faba bean disease detection under real-world agricultural conditions.
Abstract
Background: Faba bean is a nutritionally rich legume crop that contributes significantly to food security and sustainable agriculture. However, its productivity is adversely affected by foliar diseases such as chocolate spot, gall and rust. Accurate and timely disease identification under natural field conditions remains challenging due to environmental variability and visual similarity among symptoms. Lightweight deep learning models provide an efficient solution for automated and real-time disease diagnosis. Methods: This study proposed a MobileNet-based convolutional neural network trained from scratch for four-class classification of faba bean leaf images (Chocolate Spot, Gall, Rust and Healthy). A dataset of 8,021 RGB images collected under field conditions was divided using an 80:10:10 stratified split for training, validation and testing. Images were resized to 224x224 pixels, normalized to the range [0,1] and augmented through random rotation, flipping and zooming to enhance generalization. The model was trained using the Adam optimizer with a learning rate of 5x10-5 for 50 epochs with early stopping. Performance was evaluated using confusion matrix analysis, precision, recall, F1-score, ROC and PR curves. Result: The proposed model achieved 97.36% training accuracy and 96.32% validation accuracy, with a final test accuracy of 95.14% on 1,605 unseen samples. ROC curves demonstrated near-perfect separability with AUC values approaching 1.00, while class-wise metrics confirmed balanced performance. These findings indicate that the lightweight MobileNet architecture can effectively support reliable and scalable faba bean disease detection under real-world agricultural conditions.
Background: Legumes, such as beans, are important in worldwide agriculture because of their nutritional value and soil-enriching qualities. However, bean crops are susceptible to diseases such as angular leaf spot and rust, which may reduce production and quality. Disease identification that is both effective and timely is essential to crop health and output. Traditional diagnostic approaches are often labor-intensive and susceptible to inaccuracy. Recent advances in deep learning (DL) provide interesting possibilities for automating disease categorization, possibly improving accuracy and efficiency. Methods: This study evaluates and compares the performance of two deep learning architectures, ResNet50 and VGG19, for the classification of bean leaf diseases. The dataset, sourced from Kaggle, comprises 1295 images categorized into three classes: Angular Leaf Spot, Rust and Healthy. Both systems relied on pre-trained ImageNet weights, with adjustments customized to the classification objective. The models were trained for 25 epochs and their performance was assessed based on overall accuracy. Result: The performance of the models is evaluated in terms of the confusion matrix, classification report and ROC(AUC) curves. The ResNet50 model achieved an overall accuracy of 93.75%, while the VGG19 model attained an accuracy of 91.41%. The findings indicate that ResNet50 performs better than VGG19 in terms of classification accuracy. This work demonstrates ResNet50’s performance for bean leaf disease classification tasks, providing important insights for future research and practical applications in agricultural disease control.
Yu-Yan Xu, Hui-Qing Chen, Qing-Mei Lin· Legume Research An Internati...· 0 citations
Background: Groundnut is a vital crop affected by several foliar diseases, such as leaf spot, alternaria, rust and rosette. These diseases can reduce crop quality and yield. Manual identification is time-consuming and may lack accuracy. Deep learning methods offer a reliable alternative for automated disease detection. Methods: This study proposes a fine-tuned InceptionV3 convolutional neural network to classify five groundnut leaf classes. A dataset (Sourced from the Mendeley database) of 1,720 high-resolution images was used. These were collected under natural conditions from fields in Ramchandrapur village, West Bengal, India. Images were resized, normalized and augmented to improve model generalization. Transfer learning was applied using the InceptionV3 base model. A custom classification head was added with dense layers, batch normalization, dropout and L2 regularization. The model was trained with the RMSprop optimizer and evaluated using performance matrices, area under the curve (AUC) and Cohen’s Kappa. Result: The proposed model achieved a test accuracy of 98.26%. The macro average F1-score was 0.9872 and cohen’s kappa reached 0.9762. AUC values were above 0.998 for all classes. The model showed excellent performance, especially for minority classes like rosette and rust. It correctly classified almost all samples, with very few misclassifications. Compared to earlier studies, the model performed competitively and offered high interpretability and efficiency. These results support its use in real-world disease diagnosis in agriculture.
Zhe Li, Xue-Lu Qiu· Legume Research An Internati...· 0 citations
A modified AlexNet architecture for classifying field-captured tomato leaf images into seven disease categories was developed and generally focused on symptom-bearing leaf regions, whereas target spot was the most difficult category to classify.
Debabrat Bharali, Kanak C. Bora, Rashel Sarkar et al.· Journal of Scientific Resear...· 0 citations
Background: Faba bean is an important legume crop valued for its nutritional and soil-enriching benefits, yet its productivity is severely affected by foliar diseases. Automated image-based detection using deep learning provides a rapid and reliable approach for early disease identification and improved crop management. Methods: This study developed a machine learning-based automated framework for multi-class classification of Faba bean leaf diseases using transfer learning with the VGG16 convolutional neural network. A dataset of 8,021 RGB images collected under natural field conditions was used, comprising four classes: healthy, rust, gall and chocolate spot. Images were resized to 224 × 224 pixels and normalized prior to training. The pretrained convolutional layers of VGG16 were frozen and a custom classification head with global average pooling and dropout regularization was added. Model performance was evaluated using classification metrics. Result: The proposed model achieved an overall classification accuracy of 92.34% and a macro-averaged F1-score of 0.9227 on the test dataset. Strong classification performance was observed across all disease categories, with particularly high predictive accuracy for healthy and rust classes. The findings demonstrate the effectiveness of transfer learning for plant disease detection and highlight its potential for scalable, automated crop health monitoring in precision agriculture.
Hsin-Yin Hsieh, Meng-Dar Shieh· Legume Research An Internati...· 0 citations
A deep learning-based solution to automate disease detection of groundnut leaf conditions that outperformed existing methods such as ResNet50, CNN with progressive resizing, LeafNet and LeafNet and maintained low training and validation loss throughout training.
Jie-Shin Lin, Y. Tai, Suh-Chen Hsiao et al.· Legume Research An Internati...· 0 citations
Plant diseases are crucial for improving crop yield and ensuring sustainable agricultural practices, particularly for staple crops such as groundnut and paddy leaf. However, existing methods often suffer from limited feature discrimination, inadequate attention to disease-affected regions, and reduced performance under real-world conditions. To address these limitations, this research introduces a novel deep learning (DL)-based GOPI-NET framework for precise groundnut and paddy leaf disease classification. Initially, the input leaf images are enhanced using Bilateral Filtering (BF) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to reduce noise and improve contrast. Subsequently, HSV color space segmentation is employed to precisely isolate disease-affected regions. The proposed Dual Attention Network (DuAtNet) integrates channel and spatial attention mechanisms within a ConvNeXt backbone to capture discriminative disease-specific features. An efficient Fuzzy Extreme Learning Machine (FELM) classifier is then utilized for final categorization into Healthy, Leaf Spot, Bacterial Wilt, and Leaf Blight classes. The effectiveness of the GOPI-NET is evaluated using precision, recall, specificity, accuracy, and F1-score. The experimental results demonstrate that GOPI-NET achieves an overall accuracy of 98.32%. The GOPI-NET improves classification accuracy by 1.29%, 1.40%, and 2.23% compared to GLDICCNN, DNN-CSA, and LeafNet respectively.
S. Sharmila, V. Jeyalakshmi· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
