This Article 
 Bibliographic References 
 Add to: 
Image Filtering Using Multiresolution Representations
May 1991 (vol. 13 no. 5)
pp. 426-440

It is shown how multiresolution representations can be used for filter design and implementation. These representations provide a coarse frequency decomposition of the image, which forms the basis for two filtering techniques. The first method, based on image pyramids, is used for approximating the convolution of an image with a given mask. In this technique, a filter is designed using a least-squares procedure based on filters synthesized from the basic pyramid equivalent filters. The second method is an adaptive noise reduction algorithm. An optimally filtered image is synthesized from the multiresolution levels, which in this case are maintained at the original sampling density. Individual pixels of the image representation are linearly combined under a minimum mean square error criterion. This uses a local signal-to-noise ratio estimate to provide the best compromise between noise removal and resolution loss.

[1] W. K. Pratt, "An intelligent image processing display terminal," inProc. SPIE Tech. Symp., vol. 27, San Diego, CA, Aug. 1979.
[2] J. F. Abramatic and O. D. Faugeras, "Sequential convolution techniques for image filtering,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-30, no. 1, pp. 1-10, Feb. 1982.
[3] W. K. Prattet al., "Method and apparatus for improved digital image processing," US Patent 4 330 833, 1982.
[4] D. P. O'Leary, "Some algorithms for approximating convolutions,"Comput. Vision, Graphics, Image. Processing, vol. 41, no. 3, pp. 333-345, Mar. 1988.
[5] W. M. Wells, "Efficient synthesis of Gaussian filters by cascaded uniform filters,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-8, pp. 234-239, Mar. 1986.
[6] P. J. Burt and E.H. Adelson, "The Laplacian pyramid as a compact image code,"IEEE Trans. Commun., vol. COM-31, pp. 532-540, Apr. 1983.
[7] P. J. Burt, "Fast filter transforms for image processing,"Comput. Graphics Image Processing, no. 16, pp. 20-51, 1981.
[8] P. J. Burt, "Fast algorithms for estimating local image properties,"Comput. Graphics Image Processing, no. 21, pp. 368-382, 1983.
[9] J. L. Crowley and R. M. Stern, "Fast computation of the difference of low pass transform,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-6, pp. 212-222, 1984.
[10] A. B. Watson, "The cortex transform: Rapid computation of simulated neural images,"Comput. Vision, Graphics, Image Processing, vol. 39, pp. 311-327, 1987.
[11] M. Vetterli, "Multidimensional sub-band coding: Some theory and algorithms,"Signal Processing, vol. 6, pp. 97-112, Apr. 1984.
[12] J. W. Woods and S. D. O'Neill, "Subband coding of images,"IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-34, no. 5, pp. 1278-1288, Oct. 1986.
[13] E. Adelsonet al., "Orthogonal pyramid transforms for image coding," inProc. SPIE Conf. Visual Communications and Image Processing II, vol. SPIE-845, 1987, pp. 50-58.
[14] A. Rosenfeld, Ed.,Multiresolution Image Processing and Analysis.New York: Springer-Verlag, 1984.
[15] D. Marr,Vision. New York: Freeman, 1982.
[16] A. P. Witkin, "Scale space filtering," inProc. 7th Int. Joint Conf. Artificial Intell., pp. 1019-1021, Palo Alto, CA, 1983, pp. 1019-1021.
[17] P. Meer, E. S. Baugher, and A. Rosenfeld, "Frequency domain analysis and synthesis of image pyramid generating kernels,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 512-522, 1987.
[18] R. E. Crochiereet al., "Digital coding of speech in subbands,"Bell Syst. Tech. J., vol. 55, pp. 1069-1085, Oct. 1976.
[19] S. G. Mallat, "A theory for multiresolution signal decomposition: The wavelet representation," Dep. Comput. Inform. Sci., Univ. Pennsylvania, GRASP Lab. Tech. Memo MS-CIS-87-22, 1987.
[20] J. D. Johnston, "A filter family designed for use in quadrature mirror filter bank," inProc. Int. Conf. Audio, Acoustics, Speech, Signal. Processing, Apr. 1980, pp. 291-294.
[21] R. Chellappa and A. A. Sawchuk, Eds.,Digital Image Processing and Analysis, Volume 1: Digital Image Processing. Washington, DC: IEEE Computer Society Press, 1985.
[22] Pixar, Inc., San Rafael, CA.
[23] R. W. Schafer and L. R. Rabiner, "A digital signal processing approach to interpolation,"Proc. IEEE, vol. 61, no. 6, pp. 692-702, June 1973.

Index Terms:
image filtering; picture processing; least squares approximations; multiresolution representations; image pyramids; convolution; adaptive noise reduction algorithm; minimum mean square error criterion; filtering and prediction theory; information theory; least squares approximations; picture processing
S. Ranganath, "Image Filtering Using Multiresolution Representations," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 5, pp. 426-440, May 1991, doi:10.1109/34.134042
Usage of this product signifies your acceptance of the Terms of Use.