Point Detectors
Image Registration and Fusion Systems     
The accuracy of an image registration method heavily depends on the accuracy of the corresponding point landmarks used in
the images to determine the registration parameters. To demonstrate the sensitivity of various point detectors to radiometric
differences between images, results on the red and green bands of a color image are shown below. The color image is shown
in Fig. 1 and its red and green bands are shown in Figs. 2 and 3. Points were detected in the color bands by 11 different
detectors. Points falling within distance of sqrt(2) pixels of each other in the images are considered corresponding points. The
number of corresponding points found in Figs. 2 and 3 is denoted by n and average distance between the n corresponding
points is denoted by A, which characterizes the positional error of detected points.  The smaller the value for A, the more
accurate the correspondences is. Most points were obtained by the Harris detector [4] while highest positional accuracy was
reached by the LoG detector.

One-hundred widely dispersed points are detected by the 11 detectors in Figs. 2 and 3 and the results are overlaid in Figs. 4 –
14 for visual comparison. A point found in the red band is shown by a red `+’, while a point found in the green band is shown by
a green `+’. When detected points in the two bands coincide, the point is shown by a yellow `+’.

Results reported here rate performances of the detectors under radiometric change. There are other factors to consider when
choosing a detector. These include sensitivity to 1) noise, 2) change in image resolution, and 3) change in image geometry.
Fig. 1. A color aerial image of the city of Osaka, Japan
Fig. 1. A color aerial image of the city of Osaka, Japan
Fig. 2. Red band
Fig. 3. Green band
Fig. 4. Winston and Lerman ’72 [1] (n=14, A=0.76)
Fig. 5. Kitchen and Rosenfeld ’82 [2] (n=41, A=0.44)
Fig. 6. The LoG detector (n=39, A=0.28)
Fig. 7. Fortsner and Gulch ’86 [3] (n=66, A=0.64)
Fig. 8.  The Harris detector [4] (n=75, A=0.66)
Fig. 9. Tomasi and Kanade ’91 [5] (n=61, A=0.72)
Fig. 10. Kohlmann ’96 [6] (n=55, A=0.81)
Fig. 11. Rohr ’99 [7] (n=73, A=0.50)
Fig. 12. Ando ’00 [8] (n=4, A=0.71)
Fig. 13. Loy and Zelinski ’02 [9] (n=19, A=0.83)
Fig. 14. Goshtasby ’05 [10] (n=19, A=0.61)
References

  1. P. H. Winston and J. B. Lerman, Circular scan, Vision Flash 23, Artifcial IntelligenceLaboratory,
    Robotics Section, Massachusetts Institute of Technology, March 1972.
  2. L. Kitchen and A. Rosenfeld, Gray Level Corner Detection, Technical Report # 887, Computer Science
    Center, University of Maryland, 1980. Also in Pattern Recognition Letters, vol. 1, Dec. 1982, 95-102.
  3. W. Forstner and E. Gulch, A fast operator for detection and precise location of distinct points, corners
    and centers of circular features, Intercommission Conf. Fast Processing of Photogrammetric Data,
    Interlaken Switzerland, 1987, 281-305.
  4. C. Harris and M. Stephens, A combined corner and edge detector, Proc. 4th Alvey Vision Conf.
    (AVC88), Univ. Manchester, Aug. 31 - Sept. 2, 1988, 147-151.
  5. C. Tomasi and T. Kanade, Shape and Motion from Image Streams: A Factorization Method{Part 3,
    Technical Report CMU-CS-91-132, April 1991.
  6. K. Kohlmann, Corner detection in natural images based on the 2-D Hilbert transform, Signal
    Processing, vol. 48, 1996, 225-234.
  7. K. Rohr, Extraction of 3D anatomical point landmarks based on invariance principles, Pattern
    Recognition, vol. 32, 1999, 3-15.
  8. S. Ando, Image field categorization and edge/corner detection from gradient covariance, IEEE Trans.
    Pattern Analysis and Machine Intelligence, vol. 22, no. 2, 2000, 179-190.
  9. G. Loy and A. Zelinsky, A fast radial symmetry transform for detecting points of interest, 7th Euproean
    Conf. Computer Vision, 2002, 358-368.
  10. A. Goshtasby, 2-D and 3-D Image Registration for Medical, Remote Sensing, and Industrial
    Applications, Wiley Press, 2005.
  11. The LoG detector. See for example, Blostein, D. and Ahuja, N. A multiscale region detector. Computer
    Vision, Graphics and Image Processing, vol. 45, pp. 22-41.
To obtain software modules implementing any of the above detectors, please
contact: cs@imgfsr.com