Research on traditional Chinese cultural material identification and database construction technology based on Mask R-CNN

摘要

By studying the feature extraction technology of text materials, labelme feature extraction technology of Chinese cultural image materials based on spatial information and Mask RCNN image recognition technology, the classification and recognition method of image materials based on feature selection and combination is established to realize efficient semantic retrieval of text and image materials. Then we construct the material library of Chinese cultural elements. In this way, the material presented in the library can realize its reconstruction and apply in the field of cultural design.