JOURNAL OF TEXTILE RESEARCH ›› 2017, Vol. 38 ›› Issue (05): 122-127.doi: 10.13475/j.fzxb.20160504706

Previous Articles     Next Articles

Clothing style recognition approach using Fourier descriptors and support vector machines

  

  • Received:2016-05-19 Revised:2017-01-21 Online:2017-05-15 Published:2017-05-16

Abstract:

In the current clothing style recognition field, clothing contour feature extraction technique was complicated, classification efficiency was low and adaptability was poor. In order to solve these problem and recognize the clothing styles, a novel approach was proposed. In this approach, the contours were extracted from the clothing images, which were taken from the newly created sample database. Then the contour features were described by Fourier descriptors(FD). Finally, the clothing styles were classified by multiclass support vector machines(SVM). The experimental results show that this novel approach can accurately extract the contours of clothing. The recognition effect of the Fourier descriptors is better than the Hu moment invariant and feature fusion (Hu moment invariant and Fourier descriptor). Principal component analysis of FD can’t improve the recognition accuracy, and the classification effect of SVM is better than ELM. This approach can achieve a recognition rate above 95%. In particular, contour features obvious style has a better recognition rate.

Key words: clothing style recognition, Fourier descriptor, support vector machine, Hu moment invariant, principal component analysis, extreme learning machine

[1] . Single component textile identification based on continuous projection algorithm and least squares support vector machine [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(08): 46-51.
[2] . Prediction on filtration performance of melt blown nonwoven fabric based on rough set theory and support vector machine [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(06): 142-148.
[3] . Identification of fiber tensile fracture acoustic emission signal based on principal component analysis [J]. JOURNAL OF TEXTILE RESEARCH, 2018, 39(01): 19-24.
[4] . Classification of body shape based on longitudinal section curve [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(06): 86-91.
[5] . Structural damage evaluation of three-dimensional braided composite based on damage index [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(05): 69-74.
[6] . Prediction of garment standard time based on processes similarity [J]. JOURNAL OF TEXTILE RESEARCH, 2016, 37(11): 114-119.
[7] . Computer recognition and simulation  of fabric color from matching to standard color chip [J]. JOURNAL OF TEXTILE RESEARCH, 2016, 37(05): 150-0.
[8] . Quantitative analysis of pore shape in spunbonded nonwovens [J]. JOURNAL OF TEXTILE RESEARCH, 2015, 36(08): 56-61.
[9] . Feature slice fitting and girth prediction using Elliptic Fourier [J]. JOURNAL OF TEXTILE RESEARCH, 2014, 35(8): 76-0.
[10] Xin YuWANG. Twist optimization of polypropylene filament /aramid wrapped yarn [J]. JOURNAL OF TEXTILE RESEARCH, 2014, 35(6): 40-0.
[11] . Research on image retrieval algorithm by relevance feedback technology and shape features [J]. JOURNAL OF TEXTILE RESEARCH, 2014, 35(2): 94-0.
[12] YING Le-Bin, DAI Lian-Kui, WU Jian-Jian, SUN Guo-Jun. Identification of Single Cotton Fiber and Flax Fiber Based on Microscopic Fiber Images in the Longitudinal View [J]. JOURNAL OF TEXTILE RESEARCH, 2012, 33(4): 12-18.
[13] ZHANG Xiumei;SUN Yongjian;GUO Liangwei. Forecasting model for apparel demand based on improved least squares support vector machine (LS-SVM)oriented to mass customization [J]. JOURNAL OF TEXTILE RESEARCH, 2010, 31(5): 141-145.
[14] GENG Yanlei;CUI Yunhua;CHENG Longdi;HUANG Shuyun. Property testing and classification of bamboo fiber yarns with different structures [J]. JOURNAL OF TEXTILE RESEARCH, 2010, 31(4): 35-38.
[15] LIN Zhigui; FANG Wei; HUANG Weizhi. Analysis of fabric drape evaluation based on support vector machine [J]. JOURNAL OF TEXTILE RESEARCH, 2009, 30(01): 51-54.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!