Theory of edge detection

The Royal Society - Tập 207 Số 1167 - Trang 187-217 - 1980
David Marr1, Ellen C. Hildreth1
1M. I. T. Psychology Department and Artificial Intelligence Laboratory, 79 Amherst Street, Cambridge, Massachusetts 02139, U. S. A.

Tóm tắt

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 ∇ 2 G(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 ∇ 2 G filters acting on the image forms the basis for a physiological model of simple cells (see Marr & Ullman 1979).

Từ khóa


Tài liệu tham khảo

Alpern M., 1970, The size of rod signals, Lond., 206, 193

10.1016/0042-6989(74)90096-0

10.1111/j.1749-6632.1969.tb14019.x

10.1038/279189a0

Barlow H. B., 1967, The neural mechanism of binocular depth discrimination. J . Physiol, Lond., 193, 327

Bracewell R. 1965 The Fourier transform and its applications. New York: MacGraw-Hill.

Burton G. J., 1977, Processing by the human visual system of the light and dark contrast components of the retinal image, Biol. Cybernetics, 28, 1

10.1016/0042-6989(78)90082-2

10.1113/jphysiol.1968.sp008574

10.1113/jphysiol.1971.sp009581

Cowan J. D., 1977, Some remarks on channel bandwidths for visual contrast detection. Neurosci, Res. Prog. Bull., 15, 492

Crick F. H. C. Marr D. & Poggio T. 1980 An information processing approach to understanding the visual cortex. To appear in the N.R.P. symposium The cerebral cortex (ed. F. O. Schmidt & F. G. Worden).

De Valois K. K. 1977 Res. 17 1057-1065. aSpatial frequency adaptation can enhance contrast sensitivity. Vision

10.1016/0042-6989(77)90084-0

Enroth-Cugell C., 1966, The contrast sensitivity of retinal ganglion cells of the cat. J.Physiol, Lond., 187, 517

10.1016/0042-6989(77)90140-7

Harmon L. D. & Julesz B. 1973 Masking in visual recognition: effects of two-dimensional filtered noise. Science N .Y . 180 1194-1197.

10.1007/BF00239810

10.1113/jphysiol.1961.sp006635

10.1113/jphysiol.1962.sp006837

10.1113/jphysiol.1968.sp008455

Hubei D. H., 1974, Uniformity of monkey striate cortex: a parallel relationship between field size, scatter, and magnification factor. J. comp, Neurol., 158, 295

10.1016/0042-6989(73)90006-0

Leipnik R. i960 The extended entropy uncertainty principle. Inf. Control 3 18-25.

Logan B. F. Jr 1977 Information in the zero-crossings of bandpass signals. Bell Syst. tech. J. 56. 487-510.

10.1016/0042-6989(74)90157-6

Maffei L. & Fiorentini A. 1972 240 479-481. aProcess of synthesis in visual perception. Nature Lond.

10.1152/jn.1972.35.1.65

Maffei L. & Fiorentini A. 1077 Spatial frequency rows in the striate visual cortex. Vision Res. 17 257-264.

10.1098/rspb.1970.0040

Marr D., 1976, Analyzing natural images: a computational theory of texture vision. Cold Spring Harbor Symp. quant, Biol., 40, 647

10.1098/rstb.1976.0090

Marr D. 1978 Representing visual information. A.A.A.S. 143rd Annual Meeting Symposium o n : Some mathematical questions in biology February 1977. Published in Lectures on mathematics in the life sciences 10 101-180. Also available as M.I.T. A .I. Lab. Memo 415.

10.1098/rspb.1979.0029

10.1364/JOSA.69.000914

Marr D. & Ullman S. 1979 Directional selectivity and its use in early visual processing. (In preparation.)

10.1016/0042-6989(78)90138-4

10.1016/0042-6989(72)90041-7

Peichl L., 1979, Size, scatter and coverage of ganglion cell receptive field centres in the cat retina. J . Physiol, Lond., 291, 117

10.1152/jn.1977.40.6.1392

Pollen D. A., 1971, How does the striate cortex begin the reconstruction of the visual world? Science N, Y ., 173, 74

Ratliff F. 1965 Mach bands: quantitative studies on neural networks in the retina. San Francisco: Holden-Day.

Rodieck R. W. & Stone J. 1965 Analysis of receptive fields of cat retinal ganglion cells. J .Neurophysiol. 28 833-849.

Rosenfeld A. & Kak A. C. 1976 Digital picture processing. New York: Academic Press.

Sachs M. B. Nachmias J. & Robson J. G. 1971 Spatial-frequency channels in human vision. J. opt. Soc. A m .61 1176-1186.

10.1113/jphysiol.1973.sp010133

10.1152/jn.1976.39.6.1288

10.1152/jn.1976.39.6.1320

10.1007/BF00344165

10.1016/0042-6989(77)90069-4

10.1016/0042-6989(79)90117-2

10.1016/0042-6989(77)90152-3