Abstract
It is a common practice in computer vision and image processing to convolve rectangular constant coefficient windows with digital images to perform local smoothing and derivative estimation for edge detection and other purposes. If all data points in each image window belong to the same statistical population, this practice is reasonable and fast. But, as is well known, constant coefficient window operators produce incorrect results if more than one statistical population is present within a window, for example, if a gray-level or gradient discontinuity is present. This paper shows one way to apply the theory of robust statistics to the data smoothing and derivative estimation problem. A robust window operator is demonstrated that preserves gray-level and gradient discontinuities in digital images as it smooths and estimates derivatives.
Similar content being viewed by others
References
Abdelmalek NN (1980)L 1 solution of overdetermined systems of linear equations. ACM Transactions on Mathematical Software 6:220–227
Allan FE (1935) The general form of the orthogonal polynomials for simple series with proofs of their simple properties. Proceedings on Royal Society of Edinburgh 50:310–320
Anderson RL, Houseman EE (1942) Tables of orthogonal polynomial values extended toN= 104. Research Bulletin 297, Iowa State College of Agriculture and Mechanic Arts, Ames, Iowa (April)
Bartels RH, Jezioranski JJ (1985) Least-squares fitting using orthogonal multinomials. ACM Transactions Mathematical Software 11(3) (September):201–217
Beaton AE, Tukey JW (1974) The fitting of power series, meaning polynomials, illustrated on band-spectroscopic data. Technometrics 16:147–185
Beaudet PR (1978) Rotationally invariant image operators. In: Proceedings of 4th International Conference Pattern Recognition, Kyoto, Japan, November 7–10. pp 579–583
Besl PJ, Jain RC (1986) Invariant surface characteristics for three-dimensional object recognition in range images. Computer Vision, Graphics, Image Processing 33(1) (January):33–80
Besl PJ, Jain RC (1988) Segmentation via viable-order surface fitting. IEEE Transactions on Pattern Analysis Machine Intelligence PAMI-10, 2 (March):167–192
Birch JB (1980) Some convergence properties of iteratively reweighted least squares in the location model. Communication Stat. B9:359–369
Blake A, Zisserman A (1987) Visual reconstruction. MIT Press, Cambridge, Massachusetts
Bolle RM, Cooper DB (1984) Bayesian recognition of local 3-D shape by approximating image intensity functions with quadratic polynomials. IEEE Transactions on Pattern Analysis Machine Intelligence PAMI-6(4)(July):418–429
Bolles RC, Fischler MA (1981) A RANSAC-based approach to model fitting and its application to finding cylinders in range data.In: Proceedings of 7th International Joint Conference on Artificial Intelligence, Vancouver, BC, Canada, August 24–28. pp 637–643
Box GEP (1953) Non-normality and tests on variance. Biometrika 40:318–335
Chen DS (1989) A data-driven intermediate level feature extraction algorithm. IEEE Transactions on Pattern Analysis Machine Intelligence, PAMI-11 (7)(July):749–758
Daniel W (1978) Applied Nonparametric Statistics. Houghton Mifflin, Boston, Massachusetts
Davis LS, Rosenfeld A (1978) Noise cleaning by iterated local averaging. IEEE Transactions on Systems, Man, Cybernetics SMC-8(9)(September):705–710
Davis PJ (1963) Interpolation and approximation. Chapter 10: Orthogonal polynomials. Dover, New York
Dierckx P (1977) An algorithm for least-squares fitting of cubic spline surfaces to functions on a rectilinear mesh over a rectangle. Journal of Computational and Applied Mathematics 3(2):113–129
Duda RO, Hart PE (1972) The use of Hough transform to detect lines and curves in pictures. Communication of the ACM 15:11–15
Eddington AS (1914) Stellar movements and the structure of the universe. Macmillan, London
Edgeworth FY (1887) On observations relating to several quantities. Hermathena 6:279–285
Forstner W (1987) Reliability analysis of parameter estimation in linear models with applications to mensuration problems in computer vision. Computer Vision Graphics Image Processing 40:273–310
Gallagher NL, Wise GL (1981) A theoretical analysis of the properties of median filters. IEEE Transactions on Acoustics, Speech, Signal Processing ASSP-29 (December):1136–1141
Golub GH, Van Loan CF (1983) Matrix computations. Johns Hopkins University Press, Baltimore, Maryland
Grimson WEL, Pavlidis T (1985) Discontinuity detection for visual surface reconstruction. Computer Vision, Graphics, and Image Processing 30:316–330
Hampel FR (1968) Contributions to the theory of robust estimation. Ph.D. thesis, University of California, Berkeley
Hampel FR (1973) Robust estimation: A condensed partial survey. Z. Wahrsch. verw. Geb. 27:87–104
Hampel FR, Ronchetti EM, Rousseeuw PJ (1981) The change of variance curve and optimal redescending Mestimators. Journal of Statistical Association 76:643–648
Hampel FR, Ronchetti EM, Rousseeuw PJ, Stahel WA (1986) Robust statistics: The approach based on influence functions. Wiley, New York
Hansen RR, Chellappa R (1988) Two-dimensional robust spectrum estimation. IEEE Transactions ASSP 36(7):1051–1066
Haralick RM (1988) Pose estimation. Machine Vision Workshop, Center for Computer Aids to Industrial Productivity, Rutgers University, New Brunswick, New Jersey, April 25–26 (to be published by Academic Press, (1989)
Haralick RM, Watson L (1981) A facet model for image data. Computer Graphics Image Processing 15:113–129
Haralick RM, Watson LT, Laffey TJ (1983) The topographic primal sketch. International Journal of Robotics Research 2 (1)(Spring):50–72
Harwood D, Subbarao M, Hakalahti H, Davis L(1987) A new class of edge-preserving smoothing filters. Pattern Recognition Letters 6(August):155–162
Hoffman R, Jain AK (1987) Segmentation and classification of range images. IEEE Transactions on Pattern Analysis Machine Intelligence PAMI-9, 5 (September):608–620
Hogg RV (1979) Statistical robustness: One view of its use in applications today. American Statistician 33(3)(August):108–115
Huang TS, Yang GJ, Tang GY (1979) A fast two-dimensional median filtering algorithm. IEEE Transactions on Acoustics, Speech, Signal Processing ASSP-27 (February):13–18
Huber PJ (1964) Robust estimation of a location parameter. Annals of Mathematical Statistics 35:73–101
Huber PJ (1972) Robust statistics: A review. Annals of Statistics 1:799–821
Huber PJ (1977) Robust statistical procedures. Society of Industrial and Applied Mathematics. 56 pgs
Huber PJ (1981) Robust statistics. Wiley, New York
Hueckel M (1973) A local operator which recognizes edges and lines. Journal of Association of Computer Machines 20:634–647
Hurt SL, Rosenfeld A (1984) Noise reduction in three-dimensional digital images. Pattern Recognition 17(4):407–421
Kashyap RL, Eom K (1988) Robust image modeling techniques with image restoration application. IEEE Transaction ASSP 36(8):1313–1325
Lawson CL, Hanson RJ (1974) Solving least squares problems. Prentice-Hall, Englewood Cliffs, New Jersey
Medioni G (1987) Smoothing by diffusion. DARPA Image Understanding Workshop. Also USC Technical Report
Mitiche A, Aggarwal JK (1983) Detection of edges using range information. IEEE Transaction Pattern Analysis Machine Intelligence PAMI-5(2)(March):174–178
Nieminen A, Heinonen P, Neuvo Y (1987) A new class of detail preserving filters for image processing. IEEE Transactions on Pattern Analysis Machine Intelligence PAMI-9(1)(January):74–90
Montgomery DC, Peck EA (1982) Introduction to Linear Regression Analysis. Wiley, 1980. See Chapter 9
Powell MJD (1981) Approximation theory and methods. Cambridge University Press, Cambridge, England
Prewitt J (1970) Object enhancement and extraction. In: Lipkin B, Rosenfeld A (eds) Picture processing and psychopictorics. Academic Press, New York, pp 75–149
Roberts LG (1965) Machine perception of three-dimensional solids. In: Tippett JT et al. (eds) Optical and Electro-Optical Information Processing. MIT Press, Cambridge, Massachusetts, pp 159–197
Rousseuw PJ (1984) Least median of squares regression. Journal of American Statistical Association 79(388):871–880
Rousseuw PJ, Leroy AM (1987) Robust regression and outlier detection. Wiley, New York
Sharma G, Chellappa R (1984) An iterative algorithm for 2-D robust spectral estimation. In: Proceedings of International Conference of ASSP, San Diego, California
Stigler SM (1973) Simon Newcomb, Percy Daniell, and the history of robust estimation 1885–1920. J American Statistical Association 68:872–879
Terzopoulos D (1983) Multilevel computational processes for visual surface reconstruction. Comput. Vision, Graphics, Image Processing 24:52–96
Terzopoulos D (1984) Multiresolution computation of visible surface representations. Ph.D. dissertation, MIT, Cambridge, Massachusetts
Tukey JW (1960) A survey of sampling from contaminated distributions. In: Oklin I (ed) Contributions to probability and statistics. Stanford University Press, Stanford, California
Tukey JW (1962) The future of data analysis. Annals of Mathematical Statistics 33:1–67
Tukey JW (1977) Exploratory data analysis. AddisonWesley, Reading, Massachusetts
Zhou YT, Venkateswar V, Chellappa R (1989) Edge detection and linear feature extraction using a 2-D random field model. IEEE Transactions on Pattern Analysis Machine Intelligence PAMI-11(1):84–95
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Besl, P.J., Birch, J.B. & Watson, L.T. Robust window operators. Machine Vis. Apps. 2, 179–191 (1989). https://doi.org/10.1007/BF01215874
Issue Date:
DOI: https://doi.org/10.1007/BF01215874