Enhanced Red Chilli Disease Intensity Detection: A Novel Approach Integrating CNN and SVM for Precise Disease Assessment

A commonly grown crop, red chillies are susceptible to several illnesses, which significantly reduce yields and degrade product quality. To detect the intensity of red chilli sickness, this study suggests combining Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). The model uses SVMs for precise categorization of disease intensity levels and CNNs for feature extraction from high-resolution photos of afflicted red chilli plants. To improve model generalisation, the dataset—which includes photos with varied degrees of disease severity—is augmented using data augmentation techniques. The model successfully detects disease intensity levels with good accuracy, precision, recall, and F1-score metrics, according to experimental results. By providing farmers with accurate and fast disease assessments for enhanced crop management and yield, the suggested methodology advances precision agriculture. To improve the performance of the model, future work may incorporate more optimisations, investigations into different CNN architectures, and kernel functions for SVM. Overall, the combined CNNSVM model shows significant promise for transforming crop management practises for sustainable and effective agriculture and revolutionising the detection of red chilli disease intensity