Abstract
In the past, several approaches for directly determining corners in gray-value images have been introduced. The accuracy of an approach has usually been demonstrated experimentally by comparing its results with those obtained by previous schemes. In this contribution we analyze localization properties of existing direct corner detectors by using an analytical model of gray-value corners. For the different approaches we derive implicit equations constraining the corner points and numerically evaluate their locations. Since a gray-value corner is generally defined as the curvature extremum along the edge line, we also compute this position and take it as the reference location for a comparison of the investigated approaches.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
P.R. Beaudet, “Rotationally invariant image operators,” inProc. International Joint Conference on Pattern Recognition, Kyoto, Japan, 1978, pp. 579–583.
F. Bergholm, “Edge focusing,”IEEE Trans. Patt. Anal. Mach. Intell., vol. PAMI 9, pp. 726–741, 1987.
F. Bergholm and K. Rohr, “A comparison between two approaches applied for estimating diffuseness and height of step edges,” Fraunhofer Institute for Information and Data Processing (IITB), Karlsruhe, Germany, House Rep. 10262, 1991; see also Department of Analysis and Computing Science, Royal Institute of Technology, Stockholm, Tech. Rep. TRITA-NA-P9105, CVAP 83, 1991.
V. Berzins, “Accuracy of Laplacian edge detectors,”Comput. Vis., Graph., Image Process., vol. 27, pp. 195–210, 1984.
J. Blom, B.M. ter Haar Romeny, and J.J. Koenderink, “Affine invariant corner detection,” submitted for publication; see also J. Blom, “Topological and geometrical aspects of image structure,” doctoral dissertation, University of Utrecht, The Netherlands, 1992.
I.N. Bronstein and K.A. Semendjajew,Taschenbuch der Mathematik, 19th ed., Verlag Harri Deutsch: Frankfurt, 1981.
K. Brunnström, T. Lindeberg, and J.-O. Eklundh, “Active detection and classification of junctions by foveation with a head-eye system guided by the scale-space primal sketch,” inProc. 2nd European Conference on Computer Vision, S. Margherita, Italy, 1992; Lecture Notes in Computer Science, vol. 588, G. Sandini, (ed.), Springer-Verlag: Berlin, pp. 701–709, 1992.
F. Canny, “A computational approach to edge detection,”IEEE Trans. Patt. Anal. Mach. Intell., vol. PAMI-8, pp. 679–698, 1986.
R. Deriche and G. Giraudon, “Accurate corner detection: an analytical study,” inProc. 3rd International Conference on Computer Vision, Osaka, Japan, 1990, pp. 66–70.
L. Dreschler, “Zur Reproduzierbarkeit von markanten Bildpunkten bei der Auswertung von Realwelt-Bildfolgen,” inModelle und Strukturen, DAGM Symposium, Hamburg, Germany, 1981, Informatik-Fachberichte 49, B. Radig, ed., Springer-Verlag: Berlin, 1981, pp. 76–82.
L. Dreschler and H.-H. Nagel, “Volumetric model and 3D-trajectory of a moving car derived from monocular TV-frame sequences of a street scene,” inProc. International Joint Conference of Artificial Intelligence, Vancouver, Canada, 1981, pp. 692–697; see alsoComputer Graph. Image Process. vol. 20, pp. 199–228, 1982.
W. Förstner, “On the geometric precision of digital correlation,”Int. Arch. Photogramm. Remote Sensing, vol. 24, pp. 176–189, 1982.
W. Förstner, “A feature based correspondence algorithm for image matching,”Int. Arch. Photogramm. Remote Sensing vol. 26, pp. 150–166, 1986.
G. Giraudon and R. Deriche, “On corner and vertex detection,” inProc. IEEE Conference on Computer Vision and Pattern Recognition Lahaina, Maui, Hawaii, 1991, pp. 650–655.
A. Guiducci, “Corner characterization by differential geometry techniques,”Patt. Recog. Let., vol. 8, pp. 311–318, 1988.
L. Kitchen and A. Rosenfeld, “Gray-level corner detection,”Patt. Recog. Lett., vol. 1, pp. 95–102, 1982.
A. Korn, “Toward a symbolic representation of intensity changes in images,”IEEE Trans. Patt. Anal. Mach. Intell., vol. PAMI-10, pp. 610–625, 1988.
J. Martinet,Singularities of Smooth Functions and Maps, London Mathematical Society Lecture Note Series 58, Cambridge U. Press: Cambridge, England, 1982.
E. De Micheli, B. Caprile, P. Ottonello, and V. Torre, “Localization and noise in edge detection,”IEEE Trans. Patt. Anal. Mach. Intell., vol. PAMI-11, pp. 1106–1117, 1989.
H.-H. Nagel, “Displacement vectors derived from second-order intensity variations in image sequences,”Comput. Vis., Graph., Image Process., vol. 21, pp. 85–117, 1983.
H.-H. Nagel, “Constraints for the estimation of displacement vector fields from image sequences,”Proc. International Joint Conference on Artificial Intelligence, Karlsruhe, Germany, 1983, pp. 945–951.
J.A. Noble, “Finding corners,” inProc. 3rd Alvey Vision Conference, Cambridge, England, 1987, pp. 267–274.
J.H. Rieger, “Generic properties of edges and ‘corners’ on smooth greyvalue surfaces,”Biol. Cybernet. vol. 66, pp. 497–502, 1992.
K. Rohr, “Untersuchung von grauwertabhängigen Transformationen zur Ermittlung des optischen Flusses in Bildfolgen,” Diplomarbeit, Institut für Nachrichtensysteme, Universität Karlsruhe, Germany, 1987.
K. Rohr, “Über die Modellierung und Identifikation charakteristischer Grauwertverläufe in Realweltbildern,” in12th DAGM — Symposium Mustererkennung, Informatik-Fachberichte 254, R.E. Großkopf, ed., Springer-Verlag: Berlin, 1990, pp. 217–224.
K. Rohr, “Modelling and identification of characteristic intensity variations,”Image Vis. Comput., vol. 10, pp. 66–76, 1992.
K. Rohr, “Recognizing corners by fitting parametric models,”Int. J. Comput. Vis., vol. 9, pp. 213–230, 1992.
K. Rohr and C. Schnörr, “An efficient approach to the identification of characteristic intensity variations,”Image Vis. Comput., vol. 11, pp. 273–277, 1993.
M.A. Shah and R. Jain, “Detecting time-varying corners,”Proc. 7th International Conference on Pattern Recognition, Montreal, Canada, 1984, pp. 2–5.
O.A. Zuniga and R.M. Haralick, “Corner detection using the facet model,” inProc. IEEE Conference on Computer Vision and Pattern Recognition, Washington, D.C. 1983, pp. 30–37.
Author information
Authors and Affiliations
Additional information
This work was supported by the Deutsche Forschungsgemeinschaft (DFG) and by the European Union (EU), ESPRIT-Project VIVA (Viewpoint Invariant Visual Acquisition).
Rights and permissions
About this article
Cite this article
Rohr, K. Localization properties of direct corner detectors. J Math Imaging Vis 4, 139–150 (1994). https://doi.org/10.1007/BF01249893
Issue Date:
DOI: https://doi.org/10.1007/BF01249893