Abstract
Two models for visual pattern recognition are described; the one based on application of internal compensatory transformations to pattern representations, the other based on encoding of patterns in terms of local features and spatial relations between these local features. These transformation and relational-structure models are each endowed with the same experimentally observed invariance properties, which include independence to pattern translation and pattern jitter, and, depending on the particular versions of the models, independence to pattern reflection and inversion (180° rotation). Each model is tested by comparing the predicted recognition performance with experimentally determined recognition performance using as stimuli random-dot patterns that were variously rotated in the plane. The level of visual recognition of such patterns is known to depend strongly on rotation angle. It is shown that the relational-structure model equipped with an invariance to pattern inversion gives responses which are in close agreement with the experimental data over all pattern rotation angles. In contrast, the transformation model equipped with the same invariances gives poor agreement to the experimental data. Some implications of these results are considered.
Similar content being viewed by others
References
Amari, S.: Invariant structures of signal and feature spaces in pattern recognition problems. RAAG Memoirs 4, 553–566 (1968)
Amari, S.: Feature spaces which admit and detect invariant signal transformations. 4th Int. Joint Conf. on Pattern Recognition, Kyoto, Japan (1978)
Aulhorn, O.: Die Lesegeschwindigkeit als Funktion von Buchstaben und Zeilenlage. Pflügers Arch. 250, 12–25 (1948)
Barlow, H. B., Narasimhan, R. Rosenfeld, A.: Visual pattern analysis in machines and animals. Science 177, 567–575 (1972)
Cooper, L. A. Mental rotation of random two-dimensional shapes. Cognit. Psychol. 7, 20–43 (1975)
Dearborn, G. V. N.: Recognition under objective reversal. Psychol. Rev. 6, 395–406 (1899)
Foster, D. H.: A method for the investigation of those transformations under which the visual recognition of a given object is invariant. I. The theory. Kybernetik 11, 217–222 (1972a)
Foster, D. H.: A method for the investigation of those transformations under which the visual recognition of a given object is invariant. II. An example experiment: The group of rotations SO(2) acting on a Landolt ring. Kybernetik 11, 223–229 (1972b)
Foster, D. H.: A hypothesis connecting visual pattern recognition and apparent motion. Kybernetik 13, 151–154 (1973a)
Foster, D. H.: An experimental examination of a hypothesis connecting visual pattern recognition and apparent motion. Kybernetik 14, 63–70 (1973b)
Foster, D. H.: Visual pattern recognition by assignment of invariant features and feature-relations. Opt. Acta 24, 147–157 (1977)
Foster, D. H.: Visual apparent motion and the calculus of variations. In: Formal theories of visual perception, pp. 67–82. Leeuwenberg E. L. J., Buffart, H. F. J. M., eds. Chichester: Wiley 1978a
Foster, D. H.: Visual comparison of random-dot patterns: Evidence concerning a fixed visual association between features and feature-relations. Quart. J. exp. Psychol. In press (1978b)
Frisby, J. P.: The effect of stimulus orientation on the phi phenomenon. Vision Res. 12, 1145–1166 (1972)
Fu, K. S., Rosenfeld, A.: Pattern recognition and image processing. IEEE Trans. Comput. C-25, 1336–1346 (1976)
Gourevitch, V., Galanter, E.: A significance test for one parameter isosensitivity functions. Psychometrika 32, 25–33 (1967)
Green, D. M., Swets, J. A.: Signal detection theory and psychophysics. New York: Wiley 1966
Hoffman, W. C.: Higher visual perception as prolongation of the basic Lie transformation group. Math. Biosci. 6, 437–471 (1970)
Kolers, P. A.: Aspects of motion perception. Oxford: Pergamon Press 1972
Leeuwenberg, E. L. J., Buffart, H. F. J. M., eds. Formal theories of visual perception. Chichester, Wiley 1978
Marko, H.: Space distortion and decomposition theory: A new approach to pattern recognition by vision. Kybernetik 13, 132–143 (1973)
Nickerson, R. S.: Binary-classification reaction time: A review of some studies of human information-processing capabilities. Psychon. Monogr. 65, Suppl. 4, 275–318 (1972)
Pitts, W., McCulloch, W.S.: How we know universals. The perception of auditory and visual forms. Bull. Math. Biophys. 9, 127–147 (1947)
Reed, S.K.: Psychological processes in pattern recognition. New York: Academic Press 1973
Rock, I.: Orientation and form. New York: Academic Press 1973
Sekuler, R. W., Rosenblith, J. F.: Discrimination of direction of line and the effect of stimulus alignment. Psychon. Sci. 1, 143–144 (1964)
Shepard, R. N., Metzler, J.: Mental rotation of three-dimensional objects. Science 171, 701–703 (1971)
Sutherland, N. S.: Outlines of a theory of visual pattern recognition in animals and man. Proc. Roy. Soc. B171, 297–317 (1968)
Sutherland, N. S.: Object recognition. In: Handbook of perception. Vol. III, pp. 157–185. Carterette, E. C., Friedman, M. P. eds. New York: Academic Press 1973
Tanner, W. P. Jr., Swets, J. A.: A decision-making theory of visual detection. Psychol. Rev. 61, 401–409 (1954)
Ullmann, J. R.: A review of optical pattern recognition techniques. Optoelectron, 6, 319–332 (1974)
Ullmann, J. R., Rosenfeld, A.: Picture recognition and analysis. Radio Electron. Eng 47, 33–48 (1977)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Foster, D.H., Mason, R.J. Transformation and relational-structure schemes for visual pattern recognition. Biol. Cybernetics 32, 85–93 (1979). https://doi.org/10.1007/BF00337439
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF00337439