The combination of computer vision and artificial intelligence is fundamentally transforming a broad spectrum of industries by enabling machines to interpret and act upon visual data with high-levels of accuracy. As the biggest and by far the most popular open-source computer vision library, OpenCV library provides an extensive suite of programming functions supporting real-time computer vision. Bugs in the OpenCV library can affect the downstream computer vision applications, and it is critical to ensure the reliability of the OpenCV library. This paper introduces VistaFuzz, a novel technique for harnessing large language models (LLMs) for document-guided fuzzing of the OpenCV library. It utilizes LLMs to standardize information from API documentation, extracting constraints on individual input parameters and dependencies between them based on this standardized API information to generate new input values for testing each target API. We evaluate the effectiveness of VistaFuzz in testing 330 APIs in the OpenCV library, and the results show that VistaFuzz detected 17 new bugs, where 10 bugs have been confirmed, and 5 of these have been fixed.