First, the cluster number K is calculated by fusing local binary patterns (LBP) and gray-level co-occurrence matrix (GLCM) characteristic values. This study proposes a method based on an unsupervised clustering algorithm for the segmentation of Tujia brocades. Due to the lack of a standard Tujia brocade dataset, deep learning technology cannot be employed. The weave texture of a Tujia brocade is coarse, and the textural features of the background are prominent, making it challenging to achieve good segmentation effects using classical algorithms. A total of over 200 clear Tujia brocade patterns were collected and divided into seven categories based on traditional meanings. Classic graphic elements were separated from Tujia brocade patterns to establish a Tujia brocade graphic element database, which serves as a valuable resource for the protection and inheritance of traditional national culture. The database records the most detailed and authentic cultural history of the Tujia nationality and is one of the National Intangible Cultural Heritage. Tujia brocades are crucial carriers of Chinese Tujia national culture and art.
0 Comments
Leave a Reply. |