基于深度学习的服饰属性标签识别技术
Recognition Technology of Clothing Attrib-ute Label Based on Deep Learning

DOI: 10.12677/CSA.2020.104064, PP. 619-628

Keywords: 深度学习，卷积神经网络，Inception网络，服饰属性标签识别
Deep Learning, CNN, Inception Network, Clothing Attribute Label Identification

Full-Text   Cite this paper   Add to My Lib

Abstract:

在对深度学习领域和神经网络结构深入探究及理解基础之上，针对现有方法大都基于服饰整体而忽略服饰细节要素特征的问题，本文设计并实现一种基于深度学习的服装属性标签识别的方法，采用来自阿里电商数据的网络服饰图像数据库，基于深度学习的神经网络快速高效地完成服饰图像中关键特征信息的提取，并基于提取的数据特征进行建模分析，从而达到对服饰属性的精准识别与分类。实验结果表明：该方法能有效地实现服饰属性标签的识别与分类，分类准确率有效提高，可有效解决服饰属性标签识别分类困难的问题，实现服饰图像局部属性的高效识别分类。
On the basis of deep exploration and understanding of deep learning field and neural network structure, in view of the problem that the existing methods are mostly based on the whole dress and ignore the characteristics of dress details, in this paper, we design and implement a clothing attribute label recognition method based on deep learning, using the online clothing image data-base from Ali ecommerce data, the neural network based on deep learning can quickly and efficiently extract the key feature information in clothing image, and modeling and analysis based on extracted data features, so as to achieve accurate identification and classification of clothing at-tributes. The experimental results show that this method can effectively realize the recognition and classification of clothing attribute labels, improve the classification accuracy effectively, effectively solve the difficult problem of clothing attribute label recognition and classification, and realize the efficient recognition and classification of local attributes of clothing image.

References

[1]	辛晨. 基于深度学习的图像分类及应用研究[D]: [硕士学位论文]. 北京: 中国科学院大学, 2017.
[2]	卢兴敬. 基于内容的服装图像检索研究及实现[D]: [硕士学位论文]. 哈尔滨: 哈尔滨工业大学,2008.
[3]	青平. 基于深度学习的服装图像分类与检索[D]: [硕士学位论文]. 杭州: 浙江大学, 2017.
[4]	Wang, X.C. and Li, K.J. (2008) Pattern Recognition Based on Fuzzy Cluster for Recognizing Garment Style in the Photo. Proceedings of 2008 IEEE 9th International Conference on Computer-Aided Industrial Design & Conceptual Design, Vol. 1, 2008.
[5]	Cheng, C.I. and Liu, D.S.M. (2008) An Intelligent Clothes Search System Based on Fashion Styles. Proceedings of the 7th Inter-national Conference on Machine Learning and Cybernetics, Kunming, 12-15 July 2008, 1592-1597. https://doi.org/10.1109/ICMLC.2008.4620660
[6]	Simo-Serra, E., Fidler, S., Moreno-Noguer, F., et al. (2015) A High Performance CRF Model for Clothing Parsing. Computer Vision ACCV 2014, Springer International Publishing, 64-81. https://doi.org/10.1007/978-3-319-16811-1_5
[7]	Yang, W., Luo, P. and Lin, L. (2014) Clothing Co-Parsing by Joint Image Segmentation and Labeling. 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, 23-28 June 2014, 3182-3189. https://doi.org/10.1109/CVPR.2014.407
[8]	Zhang, H. and Jiang, Y. (2011) Research of Style-Based Clothing Image Retrieval. 2011 International Conference on E-Business and E Government (ICEE), Shanghai, 6-8 May 2011, 14. https://doi.org/10.1109/ICEBEG.2011.5882416
[9]	Bossard, L., Dantone, M., Leistner, C., et al. (2012) Apparel Classification with Style. Asian Conference on Computer Vision, Springer-Verlag, 321-335. https://doi.org/10.1007/978-3-642-37447-0_25
[10]	Liang, X.D., Gong, K., Shen, X.H. and Lin, L. (2018) Look into Person: Joint Body Parsing Pose Estimation Network and a New Benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 871-885. https://doi.org/10.1109/TPAMI.2018.2820063

Full-Text