In this note, we propose a general definition of shape which is both compatible with the one proposed in phenomenology (gestaltism) and with a computer vision implementation. We reverse the usual order in Computer Vision. We do not define “shape recognition” as a task which requires a “model” pattern which is searched in all images of a certain kind. We give instead a “blind” definition of shapes relying only on invariance and repetition arguments. Given a set of images $\mathcal{I}$, we call shape of this set any spatial pattern which can be found at several locations of some image, or in several different images of $\mathcal{I}$. (This means that the shapes of a set of images are defined without any a priori assumption or knowledge.) The definition is powerful when it is invariant and we prove that the following invariance requirements can be matched in theory and in practice: local contrast invariance, robustness to blur, noise and sampling, affine deformations. We display experiments with single images and image pairs. In each case, we display the detected shapes. Surprisingly enough, but in accordance with Gestalt theory, the repetition of shapes is so frequent in human environment, that many shapes can even be learned from single images.

Keywords: image analysis, basic shape elements, contrast invariance, level lines, scale space

@article{COCV_2002__8__863_0, author = {Lisani, J. L. and Morel, J. M. and Rudin, L.}, title = {A blind definition of shape}, journal = {ESAIM: Control, Optimisation and Calculus of Variations}, pages = {863--872}, publisher = {EDP-Sciences}, volume = {8}, year = {2002}, doi = {10.1051/cocv:2002022}, mrnumber = {1932976}, zbl = {1092.68679}, language = {en}, url = {http://www.numdam.org/articles/10.1051/cocv:2002022/} }

TY - JOUR AU - Lisani, J. L. AU - Morel, J. M. AU - Rudin, L. TI - A blind definition of shape JO - ESAIM: Control, Optimisation and Calculus of Variations PY - 2002 SP - 863 EP - 872 VL - 8 PB - EDP-Sciences UR - http://www.numdam.org/articles/10.1051/cocv:2002022/ DO - 10.1051/cocv:2002022 LA - en ID - COCV_2002__8__863_0 ER -

%0 Journal Article %A Lisani, J. L. %A Morel, J. M. %A Rudin, L. %T A blind definition of shape %J ESAIM: Control, Optimisation and Calculus of Variations %D 2002 %P 863-872 %V 8 %I EDP-Sciences %U http://www.numdam.org/articles/10.1051/cocv:2002022/ %R 10.1051/cocv:2002022 %G en %F COCV_2002__8__863_0

Lisani, J. L.; Morel, J. M.; Rudin, L. A blind definition of shape. ESAIM: Control, Optimisation and Calculus of Variations, Volume 8 (2002), pp. 863-872. doi : 10.1051/cocv:2002022. http://www.numdam.org/articles/10.1051/cocv:2002022/

[1] Retrieval of similar shapes under affine transformation, in Proc. International Conference on Visual Information Systems. Amsterdam, The Netherlands (1999) 566-574.

and ,[2] Axioms and fundamental equations of image processing: Multiscale analysis and P.D.E. Arch. Rational Mech. Anal. 16 (1993) 200-257. | MR | Zbl

, , and ,[3] On the affine heat flow for nonconvex curves. J. Amer. Math. Soc. (1998). | MR | Zbl

, and ,[4] The curvature primal sketch. PAMI 8 (1986) 2-14.

and ,[5] A survey of image registration techniques. ACM Comput. Surveys 24 (1992) 325-376.

,[6] Topographic maps and local contrast changes in natural images. Int. J. Comput. Vision 33 (1999) 5-27.

, and ,[7] Geometry and color in natural images. J. Math. Imaging Vision (2002). | MR | Zbl

, and ,[8] Integral and local affine invariant parameter and application to shape recognition, in ICPR94 (1994) A164-A168.

, and ,[9] Edge detection by Helmholtz principle. J. Math. Imaging Vision (to appear). | Zbl

, and ,[10] From the projective group to the registration group: A new model. Preprint (2000). | MR | Zbl

,[11] Pattern Classification and Scene Analysis. Wiley (1973). | Zbl

and ,[12] Shape representation and recognition from multiscale curvature. CVIU 2 (1997) 170-189.

and ,[13] Some recent results on the projective evolution of 2d curves, in Proc. IEEE International Conference on Image Processing. Washington DC (1995) 13-16.

and ,[14] Image iterative smoothing and P.D.E.'s (in preparation).

and ,[15] Visual pattern recognition by moments invariants. IEEE Trans. Inform. Theor. (1962) 179-187. | Zbl

,[16] Organization in vision: Essays on gestalt perception, in Praeger (1979).

,[17] Reconstruction of two-dimensional patterns from Fourier descriptors. MVA 2 (1989) 123-140.

, and ,[18] Classification of partial 2-d shapes using fourier descriptors, in CVPR86 (1986) 344-350.

and ,[19] Comparaison automatique d'images par leurs formes, Ph.D. Dissertation. Université Paris-Dauphine (2001).

,[20] Planar shapes in digital images. MAMS (submitted).

, , and ,[21] Fast shape extraction and applications. PAMI (submitted).

, and ,[22] Theory of edge detection. Proc. Roy. Soc. London Ser. A 207 (1980) 187-217.

and ,[23] Random Sets and Integral Geometry. John Wiley, NY (1975). | MR | Zbl

,[24] Gesetze des Sehens. Waldemar Kramer (1975).

,[25] Affine plane curve evolution: A fully consistent scheme. IEEE Trans. Image Process. 7 (1998) 411-420. | MR | Zbl

,[26] A theory of multiscale, curvature-based shape representation for planar curves. PAMI 14 (1992) 789-805.

and ,[27] Contrast invariant image registration, in Proc. of International Conference on Acoustics, Speech and Signal Process., Vol. 6. Phoenix, Arizona (1999) 3221-3224.

,[28] Fast computation of a contrast-invariant image representation. IEEE Trans. Image Processing 9 (2000) 860-872.

and ,[29] A locally adaptive window for signal matching. Int. J. Computer Vision 7 (1992) 143-162.

and ,[30] Shape discrimination using fourier descriptors. SMC 7 (1977) 170-179. | MR

and ,[31] Recognizing Planar Objects Using Invariant Image Features. Springer Verlag, Lecture Notes in Comput. Sci. 676 (1993). | MR | Zbl

,[32] Efficiently locating objects using the Hausdorff distance. Int. J. Computer Vision 24 (1997) 251-270.

,[33] Affine invariant scale-space. Int. J. Computer Vision 11 (1993) 25-44.

and ,[34] Image Analysis and Mathematical Morphology. Academic Press, New York (1982). | MR | Zbl

,[35] On image analysis by the method of moments. IEEE Trans. Pattern Anal. Machine Intelligence 10 (1998). | Zbl

and ,*Cited by Sources: *