CASIA OpenIR  > 类脑智能研究中心
Codebook Reconstruction with Word Correlation Feedback Mechanism
Yuhang Zhao; Zhaoxiang Zhang; Yunhong Wang
2011-08-12
Conference NameInternational Conference on Image and Graphics
Source PublicationICIG 2011
Conference Date12-15 August 2011
Conference PlaceHefei, China
AbstractBag of feature model has been shown to be one of the most successful methods in generic image categorization problems. However, creating codebook by clustering local feature vectors (e.g. Kmeans) may lose holistic information of images. This paper presents a novel process called Correlation Feedback for codebook construction. It introduces semantic similarities of words by measuring correlation between distributions of them within one image. Further more, we employ label propagation process to spread the affinities among all features. An enhanced codebook is constructed based on fusion of the new similarity matrix with spectral clustering. Experimental results on Caltech101 and the 15 nature scenes datasets shows promising performance of importing the novel similarity to dictionary construction.
KeywordSpectral Clustering Codebook Reconstruction
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/13295
Collection类脑智能研究中心
Corresponding AuthorZhaoxiang Zhang
Recommended Citation
GB/T 7714
Yuhang Zhao,Zhaoxiang Zhang,Yunhong Wang. Codebook Reconstruction with Word Correlation Feedback Mechanism[C],2011.
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
[Yuhang Zhao]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yuhang Zhao]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yuhang Zhao]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'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.