Theory of edge detection

A theory of edge detection is presented. The analysis proceeds in two parts. (1) Intensity changes, which occur in a natural image over a wide range of scales, are detected separately at different scales. An appropriate filter for this purpose at a given scale is found to be the second derivative of a Gaussian, and it is shown that, provided some simple conditions are satisfied, these primary filters need not be orientation-dependent. Thus, intensity changes at a given scale are best detected by finding the zero values of ∇2G(x, y)* I(x, y) for image I, where G(x, y) is a two-dimensional Gaussian distribution and ∇2 is the Laplacian. The intensity changes thus discovered in each of the channels are then represented by oriented primitives called zero-crossing segments, and evidence is given that this representation is complete. (2) Intensity changes in images arise from surface discontinuities or from reflectance or illumination boundaries, and these all have the property that they are spatially localized. Because of this, the zero-crossing segments from the different channels are not independent, and rules are deduced for combining them into a description of the image. This description is called the raw primal sketch. The theory explains several basic psychophysical findings, and the operation of forming oriented zero-crossing segments from the output of centre-surround ∇2G filters acting on the image forms the basis for a physiological model of simple cells (see Marr & Ullman 1979).

[1]  Roy Leipnik The Extended Entropy Uncertainty Principle , 1960, Inf. Control..

[2]  D. Hubel,et al.  Integrative action in the cat's lateral geniculate body , 1961, The Journal of physiology.

[3]  D. Hubel,et al.  Receptive fields, binocular interaction and functional architecture in the cat's visual cortex , 1962, The Journal of physiology.

[4]  D. Jameson,et al.  Mach bands : quantitative studies on neural networks in the retina , 1966 .

[5]  R. Bracewell The Fourier Transform and Its Applications , 1966 .

[6]  R. W. Rodieck,et al.  Analysis of receptive fields of cat retinal ganglion cells. , 1965, Journal of neurophysiology.

[7]  C. Enroth-Cugell,et al.  The contrast sensitivity of retinal ganglion cells of the cat , 1966, The Journal of physiology.

[8]  C. Blakemore,et al.  The neural mechanism of binocular depth discrimination , 1967, The Journal of physiology.

[9]  D. Hubel,et al.  Receptive fields and functional architecture of monkey striate cortex , 1968, The Journal of physiology.

[10]  J. Robson,et al.  Application of fourier analysis to the visibility of gratings , 1968, The Journal of physiology.

[11]  H B Barlow,et al.  PATTERN RECOGNITION AND THE RESPONSES OF SENSORY NEURONS * , 1969, Annals of the New York Academy of Sciences.

[12]  M. Alpern,et al.  The size of rod signals , 1970, The Journal of physiology.

[13]  D. Marr A theory for cerebral neocortex , 1970, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[14]  J. Robson,et al.  Spatial-frequency channels in human vision. , 1971, Journal of the Optical Society of America.

[15]  W. Levick,et al.  Sustained and transient neurones in the cat's retina and lateral geniculate nucleus , 1971, The Journal of physiology.

[16]  J. R. Lee,et al.  How Does the Striate Cortex Begin the Reconstruction of the Visual World? , 1971, Science.

[17]  L. Maffei,et al.  Processes of Synthesis in Visual Perception , 1972, Nature.

[18]  L Maffei,et al.  Retinogeniculate convergence and analysis of contrast. , 1972, Journal of neurophysiology.

[19]  K. Nakayama,et al.  Line length detectors in the human visual system: evidence from selective adaptation. , 1972, Vision research.

[20]  J. Kulikowski,et al.  Spatial arrangement of line, edge and grating detectors revealed by subthreshold summation. , 1973, Vision research.

[21]  R. M. Shapley,et al.  Edge detectors in human vision , 1973, The Journal of physiology.

[22]  B Julesz,et al.  Masking in Visual Recognition: Effects of Two-Dimensional Filtered Noise , 1973, Science.

[23]  F. Campbell,et al.  The effect of phase on the perception of compound gratings. , 1974, Vision research.

[24]  I. D. Macleod,et al.  The visibility of gratings: spatial frequency channels or bar-detecting units? , 1974, Vision research.

[25]  D. Hubel,et al.  Uniformity of monkey striate cortex: A parallel relationship between field size, scatter, and magnification factor , 1974, The Journal of comparative neurology.

[26]  P. Schiller,et al.  Quantitative studies of single-cell properties in monkey striate cortex. I. Spatiotemporal organization of receptive fields. , 1976, Journal of neurophysiology.

[27]  P. Schiller,et al.  Quantitative studies of single-cell properties in monkey striate cortex. II. Orientation specificity and ocular dominance. , 1976, Journal of neurophysiology.

[28]  D. Marr Analyzing natural images: a computational theory of texture vision. , 1976, Cold Spring Harbor symposia on quantitative biology.

[29]  Azriel Rosenfeld,et al.  Digital picture analysis , 1976 .

[30]  D Marr,et al.  Early processing of visual information. , 1976, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[31]  H. Wilson,et al.  Threshold visibility of frequency gradient patterns , 1977, Vision Research.

[32]  G. Poggio,et al.  Binocular interaction and depth sensitivity in striate and prestriate cortex of behaving rhesus monkey. , 1977, Journal of neurophysiology.

[33]  K. D. De Valois,et al.  Spatial frequency adaptation can enhance contrast sensitivity. , 1977, Vision research.

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

[35]  K. D. Valois Independence of black and white: Phase-specific adaptation , 1977, Vision Research.

[36]  S. McKee,et al.  Spatial configurations for visual hyperacuity , 1977, Vision Research.

[37]  N. Graham Visual detection of aperiodic spatial stimuli by probability summation among narrowband channels , 1977, Vision Research.

[38]  David Marr,et al.  Representing Visual Information , 1977 .

[39]  K. D. De Valois Independence of black and white: phase-specific adaptation. , 1977, Vision research.

[40]  B. Logan Information in the zero crossings of bandpass signals , 1977, The Bell System Technical Journal.

[41]  G. J. Burton,et al.  Visual adaptation to patterns containing two-dimensional spatial structure , 1978, Vision Research.

[42]  J. Mayhew,et al.  Suprathreshold contrast perception and complex random textures , 1978, Vision Research.

[43]  H. B. Barlow,et al.  Reconstructing the visual image in space and time , 1979, Nature.

[44]  H. Wässle,et al.  Size, scatter and coverage of ganglion cell receptive field centres in the cat retina. , 1979, The Journal of physiology.

[45]  D Marr,et al.  A computational theory of human stereo vision. , 1979, Proceedings of the Royal Society of London. Series B, Biological sciences.

[46]  J. Bergen,et al.  A four mechanism model for threshold spatial vision , 1979, Vision Research.

[47]  D Marr,et al.  Bandpass channels, zero-crossings, and early visual information processing. , 1979, Journal of the Optical Society of America.

[48]  D. Marr,et al.  An Information Processing Approach to Understanding the Visual Cortex , 1980 .

[49]  D Marr,et al.  Directional selectivity and its use in early visual processing , 1981, Proceedings of the Royal Society of London. Series B. Biological Sciences.