Abstract
For the task of searching images of ethnic costumes, a current problem is that the extracted features cannot express the costumes of ethnic minorities well, resulting in unsatisfactory retrieval accuracy. In order to improve the accuracy of the task of searching images of ethnic costumes, this paper proposes a retrieval strategy for the task of searching images of ethnic costumes based on the characteristics of ethnic costumes. The main process is as follows: First perform semantic segmentation on the collected ethnic clothing images. Then extract the characteristics of each part of the clothing and the overall characteristics of the clothing for feature fusion, and use the merged features as the retrieval features of the ethnic clothing images. Finally using a hierarchical search method, in the search process, first classify the ethnic group to which the clothing belongs, and then search in the search feature database of the ethnic group. The experimental results show that the retrieval strategy based on the Wa and Hani data sets, the classification accuracy and retrieval accuracy have been improved to different extents, which verifies the effectiveness of the layered retrieval strategy of ethnic clothing based on semantic feature fusion in this paper.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adegbola, O.A., Adeyemo, I.A., Semire, F.A., et al.: A principal component analysis-based feature dimensionality reduction scheme for content-based image retrieval system. Telkomnika 18(4), 1892–1896 (2020)
Gao, J.: Clothing image retrieval based on lightweight neural network. Sci. Technol. Innov. 31, 94–95 (2020)
Yang, F., Guohui, W., Cao, H.: Research progress on content-based medical image retrieval. Laser Optoelectron. Prog. 57(06), 38–50 (2020)
Ma, C., Guan, L., Chen, F.: Design of content-based remote sensing image change information retrieval and relevance feedback model. Rem. Sens. Technol. Appl. 35(03), 685–693 (2020)
Liu, Z., Luo, P., Qiu, S., et al.: Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1096–1104 (2016)
Huang, D., Liu, L., Fu, X.: Clothing retrieval via co-segmentation and feature matching. J. Comput.-Aid. Des. Comput. Graph. 29(06), 1075–1084 (2017)
Hou, Y., He, R., Li, M.: Clothing image retrieval method combining convolutional neural network multi-layer feature fusion and k-means clustering. Comput. Sci. 46(S1), 215–221 (2019)
Zhao, W.: Minority national costume image retrieval based on multi-feature fusion. J. Shandong Ind. Technol. 01, 293–294 (2017). https://doi.org/10.16640/j.cnki.37-1222/t.2017.01.254
Zhang, Q., Liu, L., Fu, X.: Clothing image retrieval by label optimization and semantic segmentation. J. Comput.-Aid. Des. Comput. Graph. 32(09), 1450–1465 (2020)
Ouyang, Z.: Ethnic minority costume retrieval based on region-to-image asymmetric matching. Softw. Guide 19(06), 227–230 (2020)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recog-nition. arXiv preprint arXiv:1409.1556 (2014)
Chen, C., Feng, Q.: Review on development of convolutional neural network and its application in computer vision. Comput. Sci. 46(03), 63–73 (2019)
Acknowledgement
This work is supported by National Natural Science Foundation of China (No. 61862068), Major Science and Technology Project of Yunnan Province (No. 202002AD080001), and Yunnan Expert Workstation of Xiaochun Cao.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wu, W., Zhou, J., Ouyang, Z. (2021). Research on Hierarchical Retrieval Method of Ethnic Clothing Based on Semantic Feature Fusion. In: Tan, Y., Shi, Y., Zomaya, A., Yan, H., Cai, J. (eds) Data Mining and Big Data. DMBD 2021. Communications in Computer and Information Science, vol 1454. Springer, Singapore. https://doi.org/10.1007/978-981-16-7502-7_16
Download citation
DOI: https://doi.org/10.1007/978-981-16-7502-7_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7501-0
Online ISBN: 978-981-16-7502-7
eBook Packages: Computer ScienceComputer Science (R0)