Thangka Image Segmentation Dataset (Images, Masks, JSON Annotations) and Model Weights

This dataset contains supporting materials for the paper "Research on the Semantic Segmentation of Thangka Images via an Improved PIDNet". Contents:- tkyt/: Original Thangka images.- masks/: Segmentation mask annotations corresponding to the original images.- tkjs/: Annotated JSON files for the Thangka images.- Model weights: Pre-trained weights of the improved PIDNet model used in the study. All files are provided to ensure full reproducibility of the experiments in the paper. The dataset can be used for research on semantic segmentation of cultural heritage images, especially for Thangka image analysis. Related code repository:https://github.com/JikD-591/thangka-seg