×

Projection filter, Wiener filter, and Karhunen-Loève subspaces in digital image restoration. (English) Zbl 0588.94005

In image processing by computer, the transformation from the original continuous-domain image to the degraded and sampled discrete observation image is usually modelled as a linear transformation with additive noise. The relation between two types of filters, the Wiener filter (WF) and the projection filter (PF), for the restoration of the original image from the observation is discussed. The latter is based on the same principle as pseudoinverse filtering but also suppresses the additive noise. The PF and the WF are shown to be closely related under a condition depending on the degradation-sampling operator and the Karhunen-Loève expansion for the family of original images. The relation between the PF and the Gauss-Markov estimator is also clarified.

MSC:

94A08 Image processing (compression, reconstruction, etc.) in information and communication theory
68T10 Pattern recognition, speech recognition
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Albert, A., Regression and the Moore-Penrose Pseudoinverse (1972), Academic Press: Academic Press New York/London · Zbl 0253.62030
[2] Andrews, H. C.; Hunt, B. R., Digital Image Restoration (1977), Prentice-Hall: Prentice-Hall Englewood Cliffs, N.J · Zbl 0379.62098
[3] Campbell, S. L.; Meyer, C. D., Generalized Inverses of Linear Transformations (1979), Pitman: Pitman London/San Francisco · Zbl 0417.15002
[4] Freiberger, W.; Grenander, U., A method in pattern theory, (Proc. 2nd Scand. Conf. on Image Analysis. Proc. 2nd Scand. Conf. on Image Analysis, Helsinki, Finland (June 15-17, 1981)), 11-17 · Zbl 0234.62002
[5] Groetsch, C. W., Generalized Inverses of Linear Operators (1977), Dekker: Dekker New York/Basel · Zbl 0358.47001
[6] Nakamura, N.; Ogawa, H., Optimum digital image restoration under additive noises, Trans. IECE Japan, J67-D, No. 5, 563-570 (1984), [Japanese]
[7] Ogawa, H., Optimum digital image restoration, (Proc. Int. Conf. on Advances in Information Science and Technology. Proc. Int. Conf. on Advances in Information Science and Technology, Calcutta, India (Jan. 11-14, 1982)), 8.1-8.7
[8] Ogawa, H.; Nakamura, N., Projection Filter restoration of degraded images, (Proc. 7th Int. Conf. on Pattern Recognition. Proc. 7th Int. Conf. on Pattern Recognition, Montreal, Canada (July 30-Aug. 2, 1984))
[9] Oja, E., Subspace Methods of Pattern Recognition, (Research Stud., Letchworth (1983), Wiley: Wiley New York)
[10] Oja, E.; Ogawa, H., Parametric projection filter for image and signal restoration (1984), submitted for publication
[11] Zyskind, G., On canonical forms, nonnegative covariance matrices, and best and simple least squares estimators in linear models, Ann. of Math. Statist., 38, 1092-1109 (1967) · Zbl 0171.17103
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.