Open AccessClassification Method of Ethnic Minority Patterns Based on Faster R-CNN
Author(s) -
Qian Kong,
Z. Shi,
Yaokai Feng,
Ming Yang,
Mengxue Zhang,
Shuzhen Zeng,
LI Rong-bin,
Ke Yu,
Jing Shen
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1575/1/012137
Subject(s) - nationality , computer science , pattern recognition (psychology) , artificial intelligence , set (abstract data type) , ethnic group , clothing , data set , geography , archaeology , immigration , sociology , anthropology , programming language
The pattern on the costumes and brocades of ethnic minorities are of profound significance, but they are various and often composed of many kinds of patterns. It is not accurate and time-consuming to classify them only by artificial methods. Taking Yao’s pattern symbols as an example, this paper collects and arranges the pattern pictures on clothing and brocade, preprocesses the pictures and labels the patterns on the processed pictures according to the preliminary classification. After the data set is made, the data set is trained and tested by Faster R-CNN algorithm. The results show that this method can effectively identify and classify the patterns of Yao nationality while reducing the time-consuming, and the average accuracy can reach 88.71%. It provides a useful exploration to help more ethnic minorities realize the intelligent classification of patterns.