Clothing Style Recognition using Fashion Attribute Detection
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 like...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
European Alliance for Innovation (EAI)
2015-08-01
|
Series: | EAI Endorsed Transactions on Ambient Systems |
Subjects: | |
Online Access: | http://eudl.eu/doi/10.4108/icst.mobimedia.2015.259089 |
id |
doaj-f8ee5c2d893f4910bc3a442d523f7beb |
---|---|
record_format |
Article |
spelling |
doaj-f8ee5c2d893f4910bc3a442d523f7beb2020-11-25T01:18:24ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Ambient Systems2032-927X2015-08-01251410.4108/icst.mobimedia.2015.259089Clothing Style Recognition using Fashion Attribute DetectionGuang-Lu Sun0Xiao Wu1Hong-Han Chen2Qiang Peng3School of Information Science and Technology, Southwest Jiaotong University; sunguanglu66@126.comSchool of Information Science and Technology, Southwest Jiaotong UniversitySchool of Information Science and Technology, Southwest Jiaotong UniversitySchool of Information Science and Technology, Southwest Jiaotong UniversityIn 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.http://eudl.eu/doi/10.4108/icst.mobimedia.2015.259089clothing stylefashionattribute |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Guang-Lu Sun Xiao Wu Hong-Han Chen Qiang Peng |
spellingShingle |
Guang-Lu Sun Xiao Wu Hong-Han Chen Qiang Peng Clothing Style Recognition using Fashion Attribute Detection EAI Endorsed Transactions on Ambient Systems clothing style fashion attribute |
author_facet |
Guang-Lu Sun Xiao Wu Hong-Han Chen Qiang Peng |
author_sort |
Guang-Lu Sun |
title |
Clothing Style Recognition using Fashion Attribute Detection |
title_short |
Clothing Style Recognition using Fashion Attribute Detection |
title_full |
Clothing Style Recognition using Fashion Attribute Detection |
title_fullStr |
Clothing Style Recognition using Fashion Attribute Detection |
title_full_unstemmed |
Clothing Style Recognition using Fashion Attribute Detection |
title_sort |
clothing style recognition using fashion attribute detection |
publisher |
European Alliance for Innovation (EAI) |
series |
EAI Endorsed Transactions on Ambient Systems |
issn |
2032-927X |
publishDate |
2015-08-01 |
description |
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. |
topic |
clothing style fashion attribute |
url |
http://eudl.eu/doi/10.4108/icst.mobimedia.2015.259089 |
work_keys_str_mv |
AT guanglusun clothingstylerecognitionusingfashionattributedetection AT xiaowu clothingstylerecognitionusingfashionattributedetection AT honghanchen clothingstylerecognitionusingfashionattributedetection AT qiangpeng clothingstylerecognitionusingfashionattributedetection |
_version_ |
1725142731686150144 |