Geranium Prognosis: Unveiling Floral Mysteries through CNN & SVM Fusion

The abstract of this study emphasizes the impressive precision of the CNN-SVM hybrid model in predicting the presence of eight different diseases that can affect geranium flowers. Precision, recall, and Fl-Score metrics are used to rigorously assess the model's performance, revealing regularly elevated values, each exceeding 95%, for every illness class. This remarkable precision demonstrates the model's superior capacity for accurately detecting and categorizing a wide range of diseases that harm geranium plants. The model's overall competency is highlighted by both macro-level and weighted averages, which show an outstanding accuracy of around 96.57%. The micro-average supports this, showing that the model performs exceptionally well in predicting diseases across the board. The study uses a combination of convolutional neural networks (CNNs) for feature extraction and support vector machines (SVMs) for classification, showing promise for real-world application in geranium cultivation with disease management. The model's remarkable reliability provides essential assistance to producers in the early detection of diseases, which in turn improves the general health and productivity of geranium plants. The findings have important implications for automated disease identification in plant pathology.