amsys 15(5): e3

Research Article

Clothing Style Recognition using Fashion Attribute Detection

Download1703 downloads
  • @ARTICLE{10.4108/icst.mobimedia.2015.259089,
        author={Guang-Lu Sun and Xiao Wu and Hong-Han Chen and Qiang Peng},
        title={Clothing Style Recognition using Fashion Attribute Detection},
        journal={EAI Endorsed Transactions on Ambient Systems},
        volume={2},
        number={5},
        publisher={EAI},
        journal_a={AMSYS},
        year={2015},
        month={8},
        keywords={clothing style, fashion, attribute},
        doi={10.4108/icst.mobimedia.2015.259089}
    }
    
  • Guang-Lu Sun
    Xiao Wu
    Hong-Han Chen
    Qiang Peng
    Year: 2015
    Clothing Style Recognition using Fashion Attribute Detection
    AMSYS
    EAI
    DOI: 10.4108/icst.mobimedia.2015.259089
Guang-Lu Sun1,*, Xiao Wu1, Hong-Han Chen1, Qiang Peng1
  • 1: School of Information Science and Technology, Southwest Jiaotong University
*Contact email: sunguanglu66@126.com

Abstract

In this paper, a new framework is proposed for clothing style recognition in natural scenes. Clothing region is first detected through the fusion of super-pixel segmentation, saliency detection and Gaussian Mixture Model (GMM). Next, a group of fashion attribute detectors are trained to get the likelihood of each attribute in the clothing image. Finally, the correlation matrix between clothing styles and fashion attributes is adopted to predict the clothing style. For evaluation, we collect a dataset for clothing style recognition which contains 5 styles and 14 fashion attributes. Extensive experiments demonstrate that the proposed framework has a promising ability to recognize the clothing style.