基于L曲率的尺度空间形状分析技术*

南京大学学报(自然科学版) ›› 2012, Vol. 48 ›› Issue (2): 172–181.

基于L曲率的尺度空间形状分析技术*

郑瑞连¹，钟宝江^2.3**徐东升¹

出版日期:2015-05-21 发布日期:2015-05-21
作者简介: (1.南京航空航天大学理学院，南京，211000;2.苏州大学计算机科学与技术学院，苏州，215006
3.南京大学计算机软件新技术国家重点实验室，南京，210093)
基金资助:
国家自然科学基金(61075040)，江苏省省属高校自然科学研究重大项日(10KJA520047 )，航空科学基金(2009ZH52069)

Scale-space shape analysis based on L curvature

Zheng Rui一Lian¹，Zhong Bao一Jiang ^2.3，Xu Dong-Sheng¹

Online:2015-05-21 Published:2015-05-21
About author: (1. College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing, 211000，China;
2. College of Computer Science and Technology, Soochow University, Suzhou，215006，China;
3. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210093，China)

摘要/Abstract

摘要： 尺度空间技术由于能够很好地模拟人类的视觉机能，己经成为理解和分析图像的一种现代化工具.木文提出了一种基于I曲率的尺度空间形状分析技术.考虑了该技术在形状描述和角点检测中的
应用，并具体地给出了一种检测角点的多尺度曲率积算法.I曲率的尺度空间图表明它的零点和极值点关于尺度参数是稳定的，具有较强的鲁棒性.新的角点检测算法能够增强形状特征点的信息，抑制噪声，
可以得到良好的实验结果，且计算量较少.

Abstract: Scale-space techniques have been considered as modern tools for image understanding and analysis
because they are consistent with the concept of human beings, In this paper, a scale-space technique for shape
analysis based on the L curvature is proposed，and its applications in shape representation and corner detection arc
also studied. Analysis of its relation to planar curvature matched very well with experimental results. So, in
sometimes, L curvature takes place of real curvature. And Lcurvature has more advantage to real curvature.The
compute of L curvature is easy and accurate.Therefore, scale space based on L curvature has more merits. Multi-
scales L curvature products(MSCP) algorithms is introduced in detail.Then a new corner detector is proposed.
Extract zero crossings and the local extreme points of L curvature, and draw them in two plane coordinates, form
Curvature Scal}Space(CSS) maps.The CSS maps constructed with the L curvature indicate that the scale space
trajectories of zero crossings and the local extreme points arc stable with respect to the input parameter.
Experiments arc conducted which show that the new corner detector can enhance the information of shape feature
and suppress noise, and therefore can achieve a good performance in corner detection. Moreover, this method does
not have the undesirable effect of the Uaussian smoothing, need less calculation, have more robustness to noise.The
new corner detector is robust，simple and effective.

郑瑞连¹，钟宝江^2.3**徐东升¹. 基于L曲率的尺度空间形状分析技术*
[J]. 南京大学学报(自然科学版), 2012, 48(2): 172–181.

Zheng Rui一Lian¹，Zhong Bao一Jiang ^2.3，Xu Dong-Sheng¹
. Scale-space shape analysis based on L curvature
[J]. Journal of Nanjing University(Natural Sciences), 2012, 48(2): 172–181.

参考文献

[1]Witkin A P. Scale-space filtering. Proceedings of Eighth international Joint Conference on Ar-tificial lntclligence,Karlsruhe, Germany,1983,1019~1022
[2]Asada H，Brady M.The curvature primal sketch. IEEE Transactions on Pattern Analysis and Machine lntclligence, 1986，8:2一14.
[3]Mokhtarian F, Mackworth A K. Scale-based description and recognition of planar curves and two-dimensional shapes. IEEE Transactions on Pattern Analysis and Machine intelligence，1986，8(1):34一43.
[4]Mokhtarian F, Bober M. Curvature scale space representation: Theory, applications,adn MPEG一7 standardization. Dordrecht. Kluwer Academic Publishers. 2003，450.
[5]Awrangjeb M，Lu G. Robust image corner de tection based on the chord-to-point distance ac cumulation technique. IEEE Transactions on Multimedia, 2008，1059一1072.
[6]Chang C C. Adaptive multiple sets of CSS fea tures for hand posture recognition. Neurocom puting, 2006，69:2017一2025.
[7]Cui M, Wonka P，Razdan A，et al. A new im- age registration scheme based on curvature scale space curve matching. Visual Computer, 2007,23(8):607~618
[8]Mahmoudi S, Daoudi M. A probabilistic ap- proach for 3D shape retrieval by characteristic views. Pattern Recognition Letters, 2007，28 (13):170一1718.
[9]Roh M C, Christmas B, Kittler J，et al. Ro bust player gesture spotting and recognition in low resolution sports video. Lecture Notes in Computer Science, 2006(395):347一358.
[10]Zhang X H，Lei M，Yang D. Robust image corner detection based on multi-scale curvature product. Journal of mage and Graphics, 2007，12(7); 1270-1275.(张小洪，需明，杨月一基于多尺度曲率积的鲁棒图像角点检测.中国图象图形学报，2007,12(7);1270-1275).
[11]Zhang X H，Wang H，Hong M，et al. Robust image corner detection based on scale evolution difference of planar curves. Pattern Recognition Letters，2009，30(4):449一455.
[12]Zhong B J，Liao W H. Direct curvature scale space:theory and corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007，3:508一512.
[13]Zhong B J，Ma K K，Liao W H. Scale-space behavior of planar-curve corners, IEEE Trans- actions on Pattern Analysis and Machine Intelli- gence，2009，31(8):1517一1524.
[14]Zhong B J，Ma K K. On the convergence of pla nar curves under smoothing, IEEE Transactions on Image Processing,2010,19(8):2171~2189
[15]thong B J，Liao W H. Corner detection based on accumulative chord length of refined digital curves. Journal of Computer-Aided Design and Computer Graphics, 2004，16(7):939一9’13.
(钟宝江，廖文和.基于精化曲线累积弦长的角点检测技术.计算机辅助设计与图形学学报，2001，16 (7):939一943).
[16]Han J H，Poston T.Chord-to-point distance accumulation and planar curvature; A new ap- proach to discrete curvature. Pattern Recogni tion Letters, 2001,22:1122~1144.
[17]Rosenfeld A，Johnston E. Angle detection on digital curves, IEEE Transactions on Comput-ers,1973,22:875~878
[18]Rosenfeld A，Weszka J S. An improved method of angle detection on digital curves. IEEE Transactions on Computers，197，24: 940一941.
[19]Rattarangsi A，Chin R T.Scale-based detection of corners of planar curves. IEEE Transactions on Pattern Analysis and Machine intelligence,1992,14:430~449

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed