Precision agriculture utilizes advanced computational methods to enhance crop health surveillance and improve disease management strategies. This paper delivers an in-depth survey of cutting-edge techniques in plant disease identification, highlighting the integration of Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and Computer Vision (CV) paradigms. It examines conventional ML such as Support Vector Machines (SVM), Random Forests (RF), and k-Nearest Neighbours (k-NN)—in contrast with advanced DL architectures like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and transformer-based frameworks. Furthermore, it explores intelligent hybrid systems that synergize AI with Internet of Things (IoT) devices and Edge Computing infrastructures to facilitate low-latency, real-time disease diagnostics in agricultural environments. A comparative analysis highlights the advantages, limitations, and performance trade-offs of these techniques concerning accuracy, computational complexity, and scalability. The study underscores the significance of CV in automating plant disease diagnosis through high-resolution imaging and spectral analysis. The findings provide insights into future research directions, emphasizing the integration of AI-driven models with edge AI and cloud-based solutions for enhanced precision agriculture.