Dynamic Clustering Strategies Boosting Deep Learning in Olive Leaf Disease Diagnosis

Artificial intelligence has many applications in various industries, including agriculture. It can help overcome challenges by providing efficient solutions, especially the early stages of development. When working with tree leaves to identify type disease, diseases often show up through changes leaf color. Therefore, it is crucial improve color brightness before using them intelligent agricultural systems. Color improvement should achieve a balance where no new colors appear, as this could interfere accurate identification and diagnosis disease. This considered one field. work proposes an effective model for olive disease diagnosis, consisting five modules: image enhancement, feature extraction, clustering, deep neural network. In noise reduction, balanced colors, CLAHE are applied LAB space channels quality visual stimulus. raw images processed triple convolutional layers, max pooling operations, flattening CNN phase. The classification process starts dividing data into clusters based on density, followed use proposed was tested over 3200 compared two learning algorithms (VGG16 Alexnet). results accuracy loss rate that achieves (98%, 0.193), while VGG16 Alexnet reach (96%, 0.432) (95%, 1.74), respectively. demonstrates robust approach combines enhancement techniques learning-based reliable results.