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...

基于LBP和小波纹理特征的室内室外场景分类算法

DOI: 10.11834/jig.20100505

Keywords: 室内室外场景识别,旋转不变,LBP,小波变换,纹理特征

Full-Text   Cite this paper   Add to My Lib

Abstract:

室内室外场景识别是图像处理的基本问题之一。对此问题提出了一种不需要图像分割和目标识别的方法。首先,利用小波变换对原图像进行五层小波分解,然后用旋转不变的LBP(localbinarypattern)算法对第二层至第五层的LL子图提取纹理特征,再计算第二层和第一层LH,HL,HH子图的能量均值和方差,最后连接这两个过程形成的低维特征向量进行室内室外图像场景分类。实验结果表明此算法分类效果比较好,且识别室内室外场景并不需要目标形状等局部详细信息,只需要图像模糊化的全局纹理信息。

References

[1]  Lipson P,Grimson E,Sinha P,Configuration based scene classification and image indexing,Washington DC,USA:IEEE Computer Society,1997.
[2]  Walker Renninger L,Malik J,When is scene identification just texture recognition,Vision Research,2004(19).
[3]  Ojala T,Pietikainen M,Harweod D,A comparative study of texture measures with classification based on feature distributions,Pattern Recognition,1996(29).
[4]  木拉提?哈米提.刘伟.童勤业 纹理谱直方图与潜在语义标引在图像检索中的应用 [J].-科技通报2006(3)
[5]  Liao Shu,Fan Wei,Chung Albert C S,Facial expression recognition using advanced local binary patterns,Tsallis entropies and global appearance features,New York,USA:IEEE Press,2006.
[6]  Schwaighofer A SVM code which is implemented by Anton Schwaighofer 2008
[7]  Oliva A,Torralba A,Modeling the shape of the Bcene:A holistic representation of the spatial envelope,International Journal of Computer Vision,2001(3).
[8]  Lasehnik S,Sehmid C,Ponce J,Beyond bags of features:spatial pyramid matching for recognizing natural scene categories,New York,NY,USA:IEEE Computer Society,2006.
[9]  Szummer M,Picard R W,Indoor-outdoor image classification,Bombay,India:[s.n.],1998.
[10]  Payne A,Singh S,Indoor VS outdoor scene classification in digital photographs,Pattern Recognition,2005(10).
[11]  Heikkila M,Pietikainen M,A texture-based method for modeling the background and detecting moving objects,IEEE Transactions on Pattern Analysis and Machine Intelligence,2006(4).
[12]  杨志民,刘广利,不确定性支持向量机原理及应用,北京:科学出版社,2007.
[13]  Ponce J The uiuc database from UIUC research group 2008

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133