The construction industry is increasingly embracing digital technologies to improve quality control and reduce human dependency in inspections. Traditional quality assurance methods, though widely used, are often time-consuming, error-prone, and inefficient in large-scale projects. This review explores the integration of image processing techniques into automated construction quality control systems. It covers the fundamental principles of computer vision, the types of imaging sensors utilized, and the role of machine learning and deep learning in defect detection. Applications such as crack identification, concrete monitoring, dimensional verification, and quality assurance in prefabricated components are examined. Furthermore, the review identifies key challenges including environmental variability, dataset limitations, real-time processing demands, and scalability issues. Future directions emphasize AI-driven inspections, integration with digital twins, and the need for standardized protocols. The findings highlight the transformative potential of image-based automation in enhancing construction quality, safety, and efficiency.