Supporting Database: Annotations, Training Configurations, and YOLO Model Files for Surface Defect Identification on Traditional Chaoshan Dwelling Exterior Walls

This dataset, “Supporting Database,” provides the annotation files, training configurations, and model-related materials used in a research study on surface defect identification in traditional Chaoshan dwellings. It contains the essential non-image components needed to understand the model training setup and reproduce the reported results, excluding the raw image data. The dataset is organized into the following subfolders: 1.Annotation and Training Data – Annotation files, class labels, and training configurations associated with the defect images, including data splits for training, validation, and testing. 2.YOLO Model – The YOLOv12 model configuration files, trained model weights, and related parameter settings used in the experiments. Please note: The original defect image dataset is not included in this repository due to confidentiality considerations. Access to the images may be requested separately from the authors, subject to reasonable conditions. This database is provided solely for the purpose of verifying the authenticity of the associated research and supporting peer review; no other uses are permitted.