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...

高鲁棒性图像显著区域提取及描述方法

Keywords: 显著区域,TRS不变矩,不变矩

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对现有的图像显著区域提取及描述方法中存在的计算复杂、鲁棒性差等问题,提出了一种新的显著区域提取和描述方法.首先,通过基于连通区域的方法提取图像中的显著区域,然后,采用不变矩描述子对区域的特征进行描述.实验结果表明,该方法能有效地提取和描述图像中的显著区域,且对平移、旋转和缩放变换具有很高的鲁棒性.

References

[1]  FU Y,WANG M,ZHANG C Q.SAR image targetrecognition based on Hu invariant moments and SVM[C]∥Proceedings of 5th International Conference onInformation Assurance and Security.Xi'an:Springer,2009:585-588.
[2]  FLUSSER J,SUK T,BARBARA Z.Moments andmoment invariants in pattern recognition[M].Chichester:Wiley&Sons Ltd.,2009:15-20.
[3]  MATAS J,CHUM O,URBAN M,et al.Robust wide-baseline stereo from maximally stable extremal regions[C]∥Proceedings of the British Machine Vision Conference.Cardiff:BMVA Press,2002:384-393.
[4]  TUYTELAARS T,VAN GOOL L.Matching widelyseparated views based on affine invariant regions[J].International Journal of Computer Vision,2004,59(1):61-85.
[5]  KADIR T,BRADY M,ZISSERMAN A.An affineinvariant salient region detector[C]∥Proceedings ofEighth European Conference on Computer Vision.Prague:Springer,2004:345-457.
[6]  MIKOLAJCZYK K,TUYTELAARS T,SCHMID C,et al.A comparison of affine region detectors[J].InternationalJournal of Computer Vision,2005,65(1/2):43-72.
[7]  蔡红苹,雷琳,陈涛,等.一种通用的仿射不变特征区域提取方法[J].电子学报,2008,36(4):672-678.CAI Hong-ping,LEI Lin,CHEN Tao,et al.A generalapproach for extracting affine invariant regions[J].Chinese Journal of Electronics,2008,36(4):672-678.(in Chinese)
[8]  张洁玉,陈强,白小晶,等.仿射不变的多尺度自卷积熵提取方法[J].计算机辅助设计与图形学学报,2009,21(9):1328-1332.ZHANG Jie-yu,CHEN Qiang,BAI Xiao-jing,et al.Affine invariant feature extraction based on multi-scaleauto-convolution entropy[J].Journal of Computer-aidedDesign&Computer Graphics,2009,21(9):1328-1332.(in Chinese)
[9]  HU M K.Visual pattern recognition by moment invariants[J].IRE Transactions on Information Theory,1962,8(2):179-187.
[10]  ZUNIC J,HIROTA K,ROSIN P L.A Hu momentinvariant as a shape circularity measure[J].PatternRecognition,2010,43(1):47-57.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133