The identification of plant diseases through image analysis is crucial in precision agriculture. Traditional methods rely on extensive manual inspection, which is time-consuming and prone to error. Deep learning approaches, particularly convolutional neural networks (CNNs), offer a promising solution for automating this process. This research focuses on preprocessing, augmenting, and analyzing image data to build a robust model capable of distinguishing between healthy and diseased apple leaves. The proposed hybrid model combines MobileNetV3Small and Res MLP architectures, achieving a balance between accuracy and computational efficiency. The novelty of this research lies in the integration of advanced preprocessing techniques and a hybrid deep learning model specifically designed for apple disease detection.