A model for size- and rotation-invariant pattern processing in the visual system

The mapping of retinal space onto the striate cortex of some mammals can be approximated by a log-polar function. It has been proposed that this mapping is of functional importance for scale-and rotation-invariant pattern recognition in the visual system. An exact log-polar transform converts centered scaling and rotation into translations. A subsequent translation-invariant transform, such as the absolute value of the Fourier transform, thus generates overall size-and rotation-invariance. In our model, the translation-invariance is realized via the R-transform. This transform can be executed by simple neural networks, and it does not require the complex computations of the Fourier transform, used in Mellin-transform size-invariance models. The logarithmic space distortion and differentiation in the first processing stage of the model is realized via “Mexican hat” filters whose diameter increases linearly with eccentricity, similar to the characteristics of the receptive fields of retinal ganglion cells. Except for some special cases, the model can explain object recognition independent of size, orientation and position. Some general problems of Mellin-type size-invariance models-that also apply to our model-are discussed.

[1]  F. Campbell,et al.  Spatial-frequency discrimination in human vision. , 1970, Journal of the Optical Society of America.

[2]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[3]  C Blakemore,et al.  On the existence of neurones in the human visual system selectively sensitive to the orientation and size of retinal images , 1969, The Journal of physiology.

[4]  Herbert J. Reitböck,et al.  Zur ähnlichkeitsinvarianten Mustererkennung mittels der Fourier-Mellin-Transformation , 1979, J. Inf. Process. Cybern..

[5]  L. I. Epstein.  An attempt to explain the differences between the upper and lower halves of the striate cortical map of the cat's field of view , 2004, Biological Cybernetics.

[6]  J. Kaas,et al.  Representation of the visual field in striate and adjoining cortex of the owl monkey (Aotus trivirgatus). , 1971, Brain research.

[7]  David R. Smith,et al.  A Threshold Logic Network for Shape Invariance , 1967, IEEE Trans. Electron. Comput..

[8]  E. Schwartz.  Cortical mapping and perceptual invariance: A reply to cavanagh , 1983, Vision Research.

[9]  L. Maffei,et al.  The visual cortex as a spatial frequency analyser. , 1973, Vision research.

[10]  Eric L. Schwartz,et al.  Computational anatomy and functional architecture of striate cortex: A spatial mapping approach to perceptual coding , 1980, Vision Research.

[11]  R. Altes.  The Fourier-Mellin transform and mammalian hearing. , 1978, The Journal of the Acoustical Society of America.

[12]  E. L. Schwartz,et al.  Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception , 1977, Biological Cybernetics.

[13]  P Cavanagh,et al.  Size and Position Invariance in the Visual System , 1978, Perception.

[14]  Meghanad D. Wagh,et al.  A multiplexing theorem and generalisation of R-transform , 1975 .

[15]  L. Palmer,et al.  The retinotopic organization of area 17 (striate cortex) in the cat , 1978, The Journal of comparative neurology.

[16]  P. Cavanagh.  Size Invariance: Reply to Schwartz , 1981, Perception.

[17]  J. Cowan,et al.  A mathematical theory of visual hallucination patterns , 1979, Biological Cybernetics.

[18]  Meghanad D. Wagh,et al.  A class of translation invariant transforms , 1977 .

[19]  D. Whitteridge,et al.  The representation of the visual field on the cerebral cortex in monkeys , 1961, The Journal of physiology.

[20]  J D Delius,et al.  Rotational invariance in visual pattern recognition by pigeons and humans. , 1982, Science.

[21]  G. F. Cooper,et al.  The angular selectivity of visual cortical cells to moving gratings , 1968, The Journal of physiology.

[22]  C. Bundesen,et al.  Visual transformation of size. , 1975, Journal of experimental psychology. Human perception and performance.

[23]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[24]  Herbert J. Reitboeck,et al.  A Transformation with Invariance Under Cyclic Permutation for Applications in Pattern Recognition , 1969, Inf. Control..

[25]  Xaver Müller.  Schnelle, translationsinvariante Transformationen zur Bearbeitung digitaler Grauwertbilder , 1982 .

[26]  E. Schwartz.  A quantitative model of the functional architecture of human striate cortex with application to visual illusion and cortical texture analysis , 1980, Biological Cybernetics.

[27]  Jürgen Altmann,et al.  A Fast Correlation Method for Scale-and Translation-Invariant Pattern Recognition , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  E L Schwartz,et al.  Cortical Anatomy, Size Invariance, and Spatial Frequency Analysis , 1981, Perception.

[29]  Hans Burkhardt,et al.  On invariant sets of a certain class of fast translation-invariant transforms , 1980 .

[30]  L. Maffei,et al.  Spatial frequency rows in the striate visual cortex , 1977, Vision Research.

[31]  R. Vautin,et al.  Magnification factor and receptive field size in foveal striate cortex of the monkey , 2004, Experimental Brain Research.

[32]  A. Cowey.  PROJECTION OF THE RETINA ON TO STRIATE AND PRESTRIATE CORTEX IN THE SQUIRREL MONKEY, SAIMIRI SCIUREUS. , 1964, Journal of neurophysiology.

[33]  V. Tagliasco,et al.  A model of the early stages of the human visual system: Functional and topological transformations performed in the peripheral visual field , 1982, Biological Cybernetics.

[34]  E. L. Schwartz,et al.  Afferent geometry in the primate visual cortex and the generation of neuronal trigger features , 1977, Biological Cybernetics.

[35]  D. G. Albrecht,et al.  Spatial frequency selectivity of cells in macaque visual cortex , 1982, Vision Research.

[36]  P. Cavanagh.  Functional size invariance is not provided by the cortical magnification factor , 1982, Vision Research.

[37]  H. J. Reitboeck,et al.  A Multi-Electrode Matrix for Studies of Temporal Signal Correlations Within Neural Assemblies , 1983 .

[38]  B. Fischer.  Overlap of receptive field centers and representation of the visual field in the cat's optic tract. , 1973, Vision research.

[39]  Carl F. R. Weiman,et al.  Logarithmic spiral grids for image-processing and display , 1979 .