Automatic Classification of Olive Leaves Disease Based on Adaptive Neuro-Fuzzy Inference System with Hybrid Features

Modern economies in many nations owe a great deal to the production of crops. Foliar diseases may cause immense damage to many different types of crops. These crops include wheat, olive, fruit, and many more. New AI breakthroughs require more precise identification of olive leaf diseases. An adaptive neuro-fuzzy inference system (ANFIS) is suggested based on mixed features to determine whether olive leaves are healthy or infected. Images of olive leaves are processed in various ways to enhance them, such as increasing contrast and filtering to remove unwanted noise. Olive leaf segmentation is performed using the k-means method. Several methods are combined to create hybrid features, including statistical moment invariants, a feature histogram, and a grey-level co-occurrence matrix (GLCM). The obtained characteristics are analyzed in this study to measure their potential discriminative ability between healthy and diseased olive leaves. In conclusion, the proposed approach provides a more accurate and efficient result for categorization. The suggested model achieves a remarkable 98.5% accuracy in its predictions.7