.Qinghai embroidery is an artistic treasure of folk embroidery in Qing-hai Province.Classifying them to understand the differences between them is an important task.However,currently,there is a lack of a systematic cl....Qinghai embroidery is an artistic treasure of folk embroidery in Qing-hai Province.Classifying them to understand the differences between them is an important task.However,currently,there is a lack of a systematic classifi-cation method for Qinghai embroidery.First,by studying the history of Qinghai embroidery and a large number of Qinghai embroidery patterns,this paper divides Qinghai embroidery patterns into three categories:animals and plants,auspicious meanings,and geometric decoration.This method breaks through the regional classification system for the Qinghai embroidery.Second,this article utilizes four CNN models to classify the Qinghai embroidery datasets,exploring the differ-ences in the classification of Qinghai embroidery by different models andfinding the optimal classification model.The results show that the GoogLeNet model per-forms the best in the classification of Qinghai embroidery images,achieving the highest accuracy rate.This is mainly due to the small size of the Qinghai embroi-dery datasets and the application of the Inception structure and batch normalization technology in the GoogLeNet model,enabling it to better extract features and clas-sify Qinghai embroidery images.Through this research,we can provide a certain reference and assistance for the classification of Qinghai embroidery images and provide technical support for the protection and inheritance of cultural heritage.展开更多
文摘.Qinghai embroidery is an artistic treasure of folk embroidery in Qing-hai Province.Classifying them to understand the differences between them is an important task.However,currently,there is a lack of a systematic classifi-cation method for Qinghai embroidery.First,by studying the history of Qinghai embroidery and a large number of Qinghai embroidery patterns,this paper divides Qinghai embroidery patterns into three categories:animals and plants,auspicious meanings,and geometric decoration.This method breaks through the regional classification system for the Qinghai embroidery.Second,this article utilizes four CNN models to classify the Qinghai embroidery datasets,exploring the differ-ences in the classification of Qinghai embroidery by different models andfinding the optimal classification model.The results show that the GoogLeNet model per-forms the best in the classification of Qinghai embroidery images,achieving the highest accuracy rate.This is mainly due to the small size of the Qinghai embroi-dery datasets and the application of the Inception structure and batch normalization technology in the GoogLeNet model,enabling it to better extract features and clas-sify Qinghai embroidery images.Through this research,we can provide a certain reference and assistance for the classification of Qinghai embroidery images and provide technical support for the protection and inheritance of cultural heritage.
