Abstract
In this paper, we propose an algorithm to automatically detect regular subcurves in a set of digital curves. The decision criterion is based on Helmholtz Principle introduced by Desolneux, Moisan and Morel and formulated in terms of number of false alarms. We apply our algorithm to low-level computer vision. Following Gestalt Theory, good continuation is indeed, one of the most important grouping laws entering into the early perception of objects. We check this on the level lines of images, which give a contrast invariant representation of images. The result is that most objects are good continuations. This experimentally shows that contrast invariance is a very sound hypothesis for low level vision and that objects can be detected independently of contrast. The parameters of the method may be reduced to a single one – the number of false alarms – and we can show that the detection has a very weak dependency on this number.
Similar content being viewed by others
References
Almansa, A., Desolneux, A., Vamech, S.: Vanishing point detection without any a priori information. IEEE Trans. Pattern Anal. Mach. Intell. 25(4), 502–507 (2003)
Alvarez, L., Morales, F.: Affine morphological multiscale analysis of corners and multiple junctions. Int. J. of Computer Vision 25(2), 95–107 (1997)
Attneave, F.: Some informational aspects of visual perception. Psychological Review 61(3), 183–193 (1954)
Bergen, Julesz: Textons, the fundamental elements in preattentive vision and perception of textures. Bell-Syst. Techn. J. 62(6), 1619–1645 (1983)
Canny, J.: A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8(6), 679–698 (1986)
Cao, F.: Contrast invariant, parameterless detection of good continuations, corners and terminators. Technical Report PI-1487, IRISA, 2002
Caselles, V., Coll, B., Morel, J.M.: A Kanizsa program. In Progress in Nonlinear Differential Equations and their Applications, Vol. 25, 1996, pp. 35–55
Deriche, R., Giraudon, G.: A computational approach for corner and vertex detection. Int. J. of Computer Vision 10(2), 101–124 (1993)
Desolneux, A.: Événements significatifs et applications à l’analyse d’image. PhD thesis, ENS-Cachan, 2000
Desolneux, A., Moisan, L., Morel, J.M.: Maximal meaningful events and application to image analysis. Technical Report Preprint 2000-22, CMLA, ENS-Cachan, 2000
Desolneux, A., Moisan, L., Morel, J.M.: Meaningful alignments. Int. J. of Computer Vision 40(1), 7–23 (2000)
Desolneux, A., Moisan, L., Morel, J.M.: Edge detection by Helmholtz principle. J. Math. Imag. Vision 14(3), 271–284 (2001)
Desolneux, A., Moisan, L., Morel, J.M.: Partial gestalts. http://www.cmla.ens-cachan.fr. To appear in IEEE. Trans. on PAMI, 2001
Desolneux, A., Moisan, L., Morel, J.M.: A grouping principle and four applications. IEEE Trans. Pattern Anal. Mach. Intell. 25(4), 508–513 (2003)
Gousseau, Y., Morel, J.M.: Are natural images of bounded variation? SIAM J. of Math. Anal. 33(3), 634–648 (2001)
Guichard, F., Morel, J.M.: Iterative Image Filtering. To appear, 2003
Guy, G., Medioni, G.: Inferring global perceptual contours from local features. Int. J. of Computer Vision 20(1), 113–133 (1996)
Harris, C.G., Stephens, M.: A combined corner and edge detector. In 4th Alvey Vision Conference, Manchester, 1988, pp. 189–192
Helmholtz, H.: Handbuch der Physiologischen Optik. Allgemeine Encyklopdie der Physik, 1867
Jacobs, D.W.: Robust and efficient detection of salient convex groups. IEEE Trans. Pattern Anal. Mach. Intell. 18(1), 23–37 (1996)
Kanizsa, G.: Vedere e Pensare. Bologna: Il Mulino, 1991
Kanizsa, G.: La Grammaire du Voir. Diderot, 1996. Original title: Grammatica del vedere. French translation from Italian
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Int. J. of Computer Vision 1, 321–331 (1987)
Lindeberg, T., Li, M.X.: Segmentation and classification of edges using minimum description length approximation and complementary junction cues. Computer Vision and Image Understanding 67(1), 88–98 (1997)
Lisani, J.L., Monasse, P., Rudin, L.: Fast shape extraction and application. Preprint 16, CMLA, ENS-Cachan. Available at http://www.cmla.ens-cachan.fr, 2001
Lowe, D.: Perceptual Organization and Visual Recognition. PhD thesis, Stanford University, 1984
Marr, D.: Vision. N.York: W.H. and Co, 1982
Monasse, P., Guichard, F.: Fast computation of a contrast invariant representation. IEEE Trans. on Image Processing 9(5), 860–872 (2000)
Montanari, U.: On the optimal detection of curves in noisy pictures. Communications of the ACM 14(5), 335–345 (1971)
Mumford, D., Shah, J.: Optimal approximation by piecewise smooth functions and associated variational problems. Communication on Pure and Applied Mathematics, XLII(4) (1989)
Musé, P., Sur, F., Morel, J.M.: Recherche dans les grandes bases de formes. Technical Report 2002-02, ENS Cachan, 2002, In French
Nitzberg, M., Shiota, T.: Nonlinear image filtering with edge and corner enhancement. IEEE Trans. Pattern Anal. Mach. Intell. 14(8), 826–833 (1992)
Pao, H., Geiger, D., Rubin, N.: Measuring convexity for figure/ground separation. In International Conference of Computer Vision, ICCV 99. Vol. 2, 1999, pp. 948–955
Sojka, E.: A new algorithm for detecting corners in digital images. In 18th Spring Conference on Computer Graphics, 2001
Wertheimer, M.: Untersuchungen zur Lehre der Gestalt, II. Psychologische Forschung 4, 301–350 (1923)
Zhu, S.C.: Embedding Gestalt laws in markow random fields. IEEE Trans. Pattern Anal. Mach. Intell. 21(11), 1170–1187 (1999)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by
K. Mikula
Rights and permissions
About this article
Cite this article
Cao , F. Application of the Gestalt principles to the detection of good continuations and corners in image level lines. Comput. Visual Sci. 7, 3–13 (2004). https://doi.org/10.1007/s00791-004-0123-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00791-004-0123-6