The CNN-SVM Fusion for Improved Classification: A Revolutionary Approach to the Diagnosis of Jackfruit Leaf Disease

This research overview summarizes the results and measurements used to develop a disease classification model for Jackfruit leaves. For example, when it comes to distinguishing between healthy and unhealthy leaves, such as those affected by downy mildew, black rot, bacterial leaf spot, clubroot, and white rust, the model has a very good memory, accuracy, and F1 classification. This task is achieved by mixing CNN and Support Vector Machine (SVM). The most accurate values of the model (96.32% for the healthy class and 96.38% for the unhealthy class) show that it can correctly identify a large part of the real cases of each condition. The true and correct classification of the model is confirmed by the F1 score, which shows a balanced relationship between recall and precision. 1,000 images were used for training and evaluation. The accuracy of the model is impressive at 96.32%. Additionally, the Support column provides information on the model’s ability to handle datasets important to real-world agricultural applications. Regardless of the class, the model does a good job. These results show that the model is good for automatically classifying Jackfruit fruit diseases. It also provides tools that can change agricultural practices in terms of disease control.