全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

二次式距离上基于SVD的高维图像索引方法

DOI: 10.11834/jig.20060482

Keywords: 维数灾难,二次式距离,近邻搜索,奇异值分解,向量近似

Full-Text   Cite this paper   Add to My Lib

Abstract:

向量近似方法(vectorapproximationfile)是解决高维索引中维数灾难问题的一种有效方法,但是它不能直接支持二次式距离上的近邻搜索,为此,提出一种基于奇异值分解(SVD)的二次式距离上的向量近似方法,通过奇异值分解技术将二次式距离变换为欧氏距离形式,对变换后的特征向量进行近似得到近似向量。进行近邻搜索时采用低维过滤算法,先在较高能量的低维子空间内计算近似距离进行过滤,再对过滤结果进行高维距离计算。实验结果表明,低维过滤算法可以过滤掉大部分特征向量,而只有小部分数据需要进行高维距离运算,该方法可以显著提高大型高维图像数据库的近邻搜索性能。

References

[1]  Bohm C,Berchtold S,Keim D.Searching in high-dimensional spaces-index structures for improving the performance of multimedia databases[J].ACM Computing Surveys,2001,33 (3):322 ~ 373.
[2]  Weber R,Schek H J,Blott S.A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces[A].In:Proceedings of 24th International Conference on Very Large Database[C],New York,1998:194 ~205.
[3]  Cui Y.High-dimensional Indexing:Transformational Approaches to High-dimensional Range and Similarity Searches[A].In:Lecture Notes in Computer Science[M],Heidelberg:Springer-Verlag,2002,2341.
[4]  Hafner J,Sawhney H S,Equitz W,et al.Efficient color histogram indexing for quadratic form distance functions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17 (6):729 ~ 736.
[5]  Rui Y,Huang T S,Chang S F.Image retrieval:current techniques,promising directions,and open issues[J].Journal of Visual Communication and Image Representation,1999,10 (4):36 ~ 92.
[6]  Berchtold S,Bohm C,Keim D,et al.A cost model for nearest neighbor search in high-dimensional data space[A].In:Proceedings of ACM Symposium on Principles of Database Systems[C],Tuscon,Arizona,USA,1997:78 ~ 86.
[7]  Ferhatosmanoglu H,Tuncel E,Agrawal D.Vector approximation based indexing for non-uniform high dimensional data sets[A].In:Proceedings of the ACM Int\'l Conference on Information andKnowledge Management (CIKM 2000)[C].New York,2000:202 ~ 209.
[8]  Wu P,Manjunath B,Chandrasekaran S.An adaptive index structure for high-dimensioanl similarity search[A].In:Proceedings of Advances in Multimedia Information Processing[C],Berlin,Germeny,2001:71 ~77.
[9]  Cha G H,Chung C W.The GC-Tree:A high-dimensional index structure for similarity search in image databases[J].IEEE Transactions on Multimedia,2002,4 (2):235 ~ 247.
[10]  Resch B.Mixtures of Gaussians,A Tutorial for Course Computational Interlligence[EB/OL].http://www,igi.tugraz,at/lehre/CI.2004-08-14
[11]  Manjunath B S,Ohm J R,Vasudevan V V,et al.Color and texture descriptors[J].IEEE Transactions on Circuits and Systems for Video Technology,2001,11(6):703 ~714.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133