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...

曲率尺度空间与链码方向统计的角点检测

DOI: 10.11834/jig.20140209

Keywords: 角点检测|曲率尺度空间|Freeman链码|方向统计直方图

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的传统的曲率尺度空间角点检测中,选择的尺度不同会造成角点的漏检测及误检测问题。针对这两个问题,提出一种曲率尺度空间与链码方向统计的角点检测方法。方法提出的角点检测方法是以曲率尺度空间为基础,先在较低的曲率尺度空间上选择候选角点集,再通过自适应阈值及链码方向统计的方法在角点集中剔除错误角点。结果针对不同类型的图像进行了实验,结果表明,该方法比现有角点检测方法检测准确度高5%10%,且漏检测角点少,角点检测错误率低。实验将该方法与CSS算法进行计算时间对比,分别采用256×256简单场景图与935×715复杂场景图,该方法计算时间只比CSS角点检测方法多0.1s与0.9s,相对CSS算法计算时间未有显著增加。结论该方法采用较低的曲率尺度可检测出更多的角点,降低了角点漏检测率;通过计算椭圆角点自适应阈值删除椭圆角点,并采用Freeman链码方向统计方法剔除伪角点,提高了角点检测精度。实验结果表明,本文提出的角点检测方法比其他角点检测算法具有高效性和准确性。

References

[1]  Harris C, Stephens M. A combined corner and edge detector[C]//Proceedings of Fourth Alvey Vision Conf. Manchester. U.K:[s.n.], 1988:147-151.
[2]  Han H Y, Han X, Yang F B. A new stereo matching method based on edges and corners[J]. Journal of Computational Information Systems, 2012, 8(14):6041-6048.
[3]  Velmurugan K, Baboo S S. Image retrieval using harris corners and histogram of oriented gradients[J]. International Journal of Computer Applications, 2011, 24(7):6-10.
[4]  Wang Y T, Chen Y Q, Li J, et al. The harris corner detection method based on three scale invariance spaces[J]. International Journal of Computer Science Issues, 2012, 9(6):18-22.
[5]  Smith S, Brady M. SUSAN-a new approach to low-level image processing[J]. International Journal of Computer Vision, 1997, 23(1):45-48.
[6]  Yang X F, Huang Y M, Li Y. An improved susan corner detection algorithm based on adaptive threshold[C]//Proceedings of the 2nd International Conference on Signal Processing Systems. Dalian: IEEE Press, 2010, 613-616.[DOI:10.1109/ICSPS.2010.55557 30]
[7]  Mokhtatian F, Suomela R J. Robust image corner detection through curvature scale space[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12):1376-1378.[DOI:10.1109/34.735812]
[8]  He X C, Yung N H C. Curvature scale space corner detector with adaptive threshold and dynamic region of support[C]//Proceedings of the 17th International Conference on Pattern Recognition. Cambridge, U.K:IEEE, 2004, 2:791-794.[DOI:10.1109/ICPR.2004.1334377 ]
[9]  He X C, Yung N H C. Corner detector based on global and local curvature properties[J]. Optical Engineering, 2008, 47(5): 1-12.[DOI:10.1117/ 1.2931681]
[10]  Zhang X H, Lei M, Yang D, et al. Multi-scale curvature product for robust image corner detection in curvature scale space[J]. Pattern Recognition Letters, 2007, 28(5):545-554.
[11]  Sun B, Tan J Q. Improved curvature scale space corner detection[J/OL].Computer Engineering and Application, 2013-01-29[2013-08-30].http:[C]//www.cnki.net/kcms/detail/11.2127.TP.20130129.1539.006.html.[孙波, 谭结庆. 改进的曲率尺度空间角点检测[J/OL]. 计算机工程与应用, 2013-01-29[2013-08-30].http:[C]//www.cnki.net/kcms/detail/11.2127.TP.20130129.1539.006.html]
[12]  Hermilo S C, Ernesto B, Ramon M R D. Efficiency of chain codes to represent binary objects[J]. Pattern Recognition, 2007, 40(6):1660-1674.[DOI:10.1016/j.patcog.2006.10.013]
[13]  Yu B, Guo L, Zhao T Y, et al. A curve matching algorithm based on freeman chain Code[C]// Intelligent Computing and Intelligent Systems. Xiamen:IEEE Press, 2010, 3:669-672.[DOI:10. 1109/ICICISYS.2010.5658385]
[14]  Gmati C, Haboubi S, Alaqeeli A, et al. A study of handwritten characters by shape descriptors:doping using the freeman code[C]//Proceedings of 2012 International Conference on Frontiers in Handwriting Recognition. Bari:IEEE Press, 2012:285-290.[DOI:10.1109/ICFHR.2012.170]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133