Unified Approach for Avocado Leaf Disease Classification: CNN-SVM Fusion

This paper provides a thorough examination of an algorithm for automatically diagnosing avocado leaf diseases. The approach combines a Convolutional Neural Network (CNN) and a Support Vector Machine (SVM). The classification model's performance indicators show favorable results in all disease classes, including Healthy, Anthracnose, Avocado Root Rot, Avocado Sunblotch, and Bacterial Canker. The model exhibits remarkable accuracy, recall, and F1-score values, showing that it can reliably detect a variety of avocado leaf illnesses. By evaluating the support column, one may gain a better understanding of the dataset's composition. This column gives useful information regarding the distribution of incidence across various disease categories. Furthermore, the support proportion makes it easier to examine class frequencies in relation to the entire size of the dataset, providing valuable context for model evaluation. Given the model's outstanding accuracy, our findings highlight the promise of employing CNN-SVM fusion to improve disease diagnosis and management techniques in avocado production. Further research should look into approaches to improve model design and evaluation methodologies in order to successfully handle growing difficulties and increase the efficiency of automated disease detection systems in agricultural settings.