UM
Skin color segmentation by texture feature extraction and K-mean clustering
Ng P.; Pun C.-M.
2011-09-26
Source PublicationProceedings - 3rd International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2011
Pages213-218
AbstractSkin Segmentation plays an important role in many computer vision applications. The aim of skin segmentation is to isolate skin regions in unconstrained input images. In this paper, a skin color segmentation approach by texture feature extraction and k-meaning clustering is proposed. We improved the traditional skin classification by combining both color and texture features for skin segmentation. After the color segmentation using a 16 - Gaussian Mixture Models classifier, the texture features are extracted using effective wavelet transform with a 2-D Daubechies Wavelet and represented as a list of Shannon entropy. The non-skin regions can be eliminated by the Skin Texture-cluster Elimination using K-mean clustering. Experimental results based on common datasets show that our proposed can achieve better performance of the existing methods with true positive of 93.8% and with false positives 28.4%. © 2011 IEEE.
KeywordK-mean clustering Skin segmentation Texture feature Wavelet transform
DOI10.1109/CICSyN.2011.54
URLView the original
Language英語
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionUniversity of Macau
AffiliationUniversidade de Macau
Recommended Citation
GB/T 7714
Ng P.,Pun C.-M.. Skin color segmentation by texture feature extraction and K-mean clustering[C],2011:213-218.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ng P.]'s Articles
[Pun C.-M.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ng P.]'s Articles
[Pun C.-M.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ng P.]'s Articles
[Pun C.-M.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.