The Comparison of Two Typical Corner Detection Algorithms

Corners in images represent a lot of important information. Extracting corners accurately is significant to image processing, which can reduce much of the calculations. In this paper, two widely used corner detection algorithms, SUSAN and Harris corner detection algorithms which are both based on intensity, were compared in stability, noise immunity and complexity quantificationally via stability factor eta, anti-noise factor rho and the runtime of each algorithm. It concluded that Harris corner detection algorithm was superior to SUSAN corner detection algorithm on the whole. And the comparison result was applied to an image matching experiment. It was verified that the quantitative evaluations of these two corner detection algorithms were valid through calculating match efficiency, defined as correct matching corner pairs dividing by matching time, which can reflect the performances of a corner detection algorithm comprehensively. The work of this paper can provide a direction to the improvement and the utilization of these two corner detection algorithms.

[1]  Robert Laganière,et al.  Detecting and matching feature points , 2005, J. Vis. Commun. Image Represent..

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Farzin Mokhtarian,et al.  Performance evaluation of corner detectors using consistency and accuracy measures , 2006, Comput. Vis. Image Underst..

[4]  Muhammad Sarfraz,et al.  Corner detection by sliding rectangles along planar curves , 2007, Comput. Graph..

[5]  Nasser Khalili,et al.  Multi-scale free-form 3D object recognition using 3D models , 2001, Image Vis. Comput..

[6]  M. Sarfraz,et al.  Capturing outlines using cubic Bezier curves , 2004, Proceedings. 2004 International Conference on Information and Communication Technologies: From Theory to Applications, 2004..

[7]  Robert Laganiere,et al.  Matching feature points in stereo pairs: a comparative study of some matching strategies , 2001 .

[8]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Moncef Gabbouj,et al.  Wavelet-based corner detection technique using optimal scale , 2002, Pattern Recognit. Lett..

[10]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[11]  Han Wang,et al.  Real-time corner detection algorithm for motion estimation , 1995, Image Vis. Comput..

[12]  Carlos Cabrelli,et al.  Automatic Representation of Binary Images , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Rachid Deriche,et al.  Using geometric corners to build a 2D mosaic from a set of images , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Mingyue Ding,et al.  Corner detection method based on wavelet transform , 2001, International Symposium on Multispectral Image Processing and Pattern Recognition.

[15]  In So Kweon,et al.  COP: a new corner detector , 2002 .

[16]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[17]  Cordelia Schmid,et al.  Evaluation of Interest Point Detectors , 2000, International Journal of Computer Vision.

[18]  Eric W. Rogala,et al.  Corner detection for identification of man-made objects in noisy aerial images , 2002, SPIE Defense + Commercial Sensing.

[19]  Dou Lihua.  Scale Adaptive Canny Edge Detection Method , 2008 .

[20]  R. Laganiere,et al.  Cones: a new approach towards corner detection , 2002, IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373).

[21]  Taejung Kim,et al.  Automatic satellite image registration by combination of matching and random sample consensus , 2003, IEEE Trans. Geosci. Remote. Sens..