A Hybrid Framework Integrating Novel Segmentation and Hybrid Feature Engineering with M-SVM for the Detection and Classification of Wheat Rusts and Septoria

Abstract

This study introduces a hybrid framework for the precise detection and classification of wheat rusts (Leaf Rust, Stem Rust, and Stripe Rust) and Wheat Leaf Septoria, aiming to enhance diagnostic accuracy and support effective disease management. The framework comprises key stages: lesion segmentation, Hybrid Feature Engineering and disease classification. Advanced machine learning and image enhancement methods are combined to effectively segment lesions using a multilevel hybrid segmentation model, followed by feature extraction involving shape, color, texture, and edge properties refined through PCA, entropy and skewness. To address challenges related to limited datasets and model overfitting, robust handcrafted features are utilized instead of deep feature dependency. Finally, a Multi-Class Support Vector Machine (M-SVM) is employed for classification.

Evaluated on four wheat diseases—septoria, stem rust, leaf rust, and stripe rust—the framework achieved a segmentation performance index of 98.21% on 40 images per disease and a classification accuracy of 99.1% using 10-fold cross-validation on 1,000 images. With an F1-score of 0.989, AUC of 0.991, and minimal error rates, the system outperforms existing methods, averaging 5.8 seconds per image, demonstrating its robustness and efficiency.