CASIA OpenIR  > 类脑智能研究中心
Towards Independent Color Space Selection for Human Skin Detection
Tao Xu; Yunhong Wang; Zhaoxiang Zhang
2012-12-04
Conference NamePacific-Rim Conference on Multimedia
Source PublicationPCM 2012
Conference Date4-6 December 2012
Conference PlaceSingapore, Singapore
AbstractSkin color detection plays an important role in video based applications. Without considering the selection of suitable color space, a novel skin color detection method is proposed based on the flexible neural tree, which can identify the important components of color spaces automatically. With large training data sets, our method builds a flexible neural tree structure and optimizes its parameters using Genetic Programming and Particle Swarm Optimization algorithms. In experiments, features comprised of all channels extracted from RGB, YCbCr and HSV color spaces are used for the constructing and evaluating of the novel skin color model, in which six most important components, i.e., R, G, B, Y, Cr and S are selected for testing. Furthermore, our method achieves higher accuracy and lower false positive rate than state of the art methods on Compaq and ECU data set.
KeywordSkin Detection Color Space Flexible Neural Tree Skin Classification
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13257
Collection类脑智能研究中心
Corresponding AuthorZhaoxiang Zhang
Recommended Citation
GB/T 7714
Tao Xu,Yunhong Wang,Zhaoxiang Zhang. Towards Independent Color Space Selection for Human Skin Detection[C],2012.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tao Xu]'s Articles
[Yunhong Wang]'s Articles
[Zhaoxiang Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tao Xu]'s Articles
[Yunhong Wang]'s Articles
[Zhaoxiang Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tao Xu]'s Articles
[Yunhong Wang]'s Articles
[Zhaoxiang Zhang]'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.