| Data: |
2026 |
| Resum: |
Purpose: Early and accurate detection of plant leaf diseases is vital for safe- guarding crop yield and supporting sustainable agricultural practices. However, practical deployment faces challenges such as inconsistent lighting conditions, overlapping leaves, low-contrast early-stage symptoms, and noisy image data-all of which hinder the reliability of deep learning models in field environments. This study aims to develop a robust, scalable, and interpretable classification framework capable of performing effectively under such real-world conditions. Method: We propose a hybrid classification pipeline that integrates deep feature extraction from three pre-trained Convolutional Neural Networks (CNNs) based VGG16, ResNet50, and DenseNet201-with a linear Support Vector Machine (SVM) classifier. To enhance robustness to varying illumination, all images are converted from RGB to HSV colour space, enabling chromatic features to be isolated from brightness fluctuations. Features are extracted from the final global pooling layers of each CNN, then concatenated to construct a unified high-dimensional feature vector. This vector is passed to the SVM classifier for binary classification (healthy vs. diseased). The system was trained and validated using a publicly available dataset comprising 4,503 labelled images, balanced between healthy and diseased samples. A comprehensive data augmentation strategy-including rotation, flipping, and scaling-was employed to improve generalisation and mitigate overfitting. Results: Among the evaluated configurations, the DenseNet201 + SVM model achieved the highest accuracy of 95%, outperforming both standalone CNN mod- els and other hybrid variants including, VGG16-SVM, and ResNet50-SVM. The hybrid approach demonstrated enhanced generalisability, particularly in images affected by noise and lighting inconsistencies. Precision, recall, F1-score, and confusion matrix metrics confirmed the model's strong performance across both classes. Conclusion: The proposed hybrid CNN-SVM framework offers a robust and interpretable solution for real-world leaf disease detection. By leveraging HSV colour space transformation and combining diverse CNN feature representations, the model effectively addresses common challenges in agricultural image classi- fication. This work presents a scalable pipeline with potential for deployment in precision agriculture systems, including smartphone-based or drone-assisted monitoring platforms. |
| Resum: |
Purpose: Early and accurate detection of plant leaf diseases is vital for safe-guarding crop yield and supporting sustainable agricultural practices. However,practical deployment faces challenges such as inconsistent lighting conditions,overlapping leaves, low-contrast early-stage symptoms, and noisy image data-allof which hinder the reliability of deep learning models in field environments. This study aims to develop a robust, scalable, and interpretable classificationframework capable of performing effectively under such real-world conditions. Method: We propose a hybrid classification pipeline that integrates deep featureextraction from three pre-trained Convolutional Neural Networks (CNNs) basedVGG16, ResNet50, and DenseNet201-with a linear Support Vector Machine(SVM) classifier. To enhance robustness to varying illumination, all imagesare converted from RGB to HSV colour space, enabling chromatic features tobe isolated from brightness fluctuations. Features are extracted from the finalglobal pooling layers of each CNN, then concatenated to construct a unifiedhigh-dimensional feature vector. This vector is passed to the SVM classifier forbinary classification (healthy vs. diseased). The system was trained and validatedusing a publicly available dataset comprising 4,503 labelled images, balancedbetween healthy and diseased samples. A comprehensive data augmentationstrategy-including rotation, flipping, and scaling-was employed to improvegeneralisation and mitigate overfitting. Results: Among the evaluated configurations, the DenseNet201 + SVM modelachieved the highest accuracy of 95%, outperforming both standalone CNN mod-els and other hybrid variants including, VGG16-SVM, and ResNet50-SVM. Thehybrid approach demonstrated enhanced generalisability, particularly in imagesaffected by noise and lighting inconsistencies. Precision, recall, F1-score, andconfusion matrix metrics confirmed the model's strong performance across bothclasses. Conclusion: The proposed hybrid CNN-SVM framework offers a robust andinterpretable solution for real-world leaf disease detection. By leveraging HSVcolour space transformation and combining diverse CNN feature representations,the model effectively addresses common challenges in agricultural image classi-fication. This work presents a scalable pipeline with potential for deploymentin precision agriculture systems, including smartphone-based or drone-assistedmonitoring platforms. |
| Drets: |
Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.  |
| Llengua: |
Anglès |
| Document: |
Article ; recerca ; Versió publicada |
| Matèria: |
Plant disease detection ;
CNNs ;
Hsv colour space ;
Feature fusion ;
Hybrid models ;
SVM |
| Publicat a: |
ELCVIA, Vol. 25, Num. 2 (2026) , p. 55-68 (Regular Issue) , ISSN 1577-5097 |
visitant ::
identificació
