<p>Wind energy is recognized as an eco-friendly and sustainable energy source. However, offshore wind turbine blades are prone to various defects such as cracks, erosion, and paint peeling as they are operated in harsh marine environments, and if defects are not detected early, blade damage will likely worsen, leading to reduced power generation performance and increased maintenance costs. Recently, research on blade defect detection using artificial intelligence (AI) technology has been underway. This paper analyzes and summarizes AI-based detection technologies for internal and external blade defects, considering deep learning and machine learning-based object detection, classification, and segmentation, along with measurement methods such as ultrasound, thermographic imaging, and X-ray. In addition to examining the performance and limitations of defect detection using various AI models, this study explored improvement methods based on convergence with thermographic and ultrasonic detection techniques. Furthermore, transfer learning, data augmentation, and synthetic data generation techniques to address the issue of data scarcity were also reviewed.</p> Graphical Abstract <p></p>