CHAPTER
7:
POLYNOMIAL
AND
RATIONAL
OPERATORS
221
Figure
7.9:
(a) Original test image and
(b)
result of the rational unsharp masking algorithm.
(Reproduced with permission from [Ram98].
O
1998
SPIE.)
7.5
Conclusions and Remaining Issues
Polynomial and rational operators have been introduced in ths chapter for a wide
spectrum of applications in image processing and analysis. Various simulation
results have been included. These results demonstrate that even simple operators
can yield effective results.
However, ths description clearly indicates that to exploit the possibilities of
this family of tools completely a stronger link is needed between theory and prac-
tice. It is necessary to formulate design techniques that can overcome the limita-
tions of the heuristic approaches often used as discussed above. To this purpose,
mixed competencies are required that should cross-fertilize the research in the
mathematics and signal processing worlds; ths is presently the most important
challenge
in
this field.
References
[Car961 S. Carrato, G. Ramponi, and S. Marsi. A simple edge-sensitive image inter-
polation filter. In
Proc. Third IEEE Intl. Conf: on Image Processing,
Vol. 111, pp.
71 1-714 (Lausanne, September 1996).
[Coc97] F. Cocchia, S. Carrato, and G. Ramponi. Design and real-time irnplementa-
tion of a 3-D rational filter for edge preserving smoothing.
IEEE Trans. Consum.
Electron.
43(4), 1291-1 300 (November 1997).
[Gab941
M.
Gabbouj and
L.
Tabus.
TUT
noisy image database. Tech. Report No. 13,
Tampere University of Technology, Finland (December 1994).
[Key811 R. G. Keys. Cubic convolution interpolation for digital image processing.
IEEE Trans. Acoust. Speech Signal Process.
ASSP-29(6), 11
53-1
160 (December
1981).
[Khr98] L. Khriji,
F.
A. Cheikh,
M.
Gabbouj, and
G.
Ramponi. Color image inter-
polation using vector rational filters.
In
Proc. SPIE Conf on Nonlinear Image
Processing IX,
Vol. 3304, pp. 26-29 (1998).
[Khr99a] L. Khriji and M. Gabbouj. Vector median-rational hybrid filters for multi-
channel image processing.
IEEESignal Process. Lett.
6(7), 186-190 (July 1999).
[Khr99b] L. Khriji,
M.
Gabbouj, G. Ramponi, and
E.
D.
Ferrandiere. Old movie
restoration using rational spatial interpolators. In
Proc. 6th
IEEE
Intl. Conf
on Electronics, Circuits and Systems
(Cyprus, September 1999).
[Lee941
J.
Lee and
V.
J.
Mathews. A stability theorem for bilinear systems.
IEEE
Trans. Signal Process.
41(7), 1871-1873 (July 1994).
[Leu941 H. Leung and
S.
Haykin. Detection and estimation using an adaptive ratio-
nal function filter.
IEEE
Trans. Signal Process,
42(12), 3366-3376 (December
1994).
[Mak94] A. Makovec and G. Ramponi. Supervised discrimination of noisy textures
using third-order moments. In
Proc, COST-229
WG,1+2
Workshop,
pp. 245-
250 (Ljubljana, Slovenia, April 1994).
[Mar801 D. Marr and
E.
Hildreth. Theory of edge detection.
Proc.
R.
Soc. London
B
207,187-217 (1980).
[Mar981 S. Marsi,
R.
Castagno, and G. Ramponi. A simple algorithm for the re-
duction of
blocking artifacts in images and its implementation.
IEEE
Trans.
Consum. Electron.
44(3), 1062-1070 (August 1998).
[Mat9
11
V. J. Mathews. Adaptive polynomial filters.
IEEE
Sig. Process. Mag.,
pp. 10-
26 (July 1991).
[MatOO]
V.
J.
Mathews and
G.
L.
Sicuranza.
Polynomial Signal Processing,
Wiley, New
York (2000).
[Mitgl] S.
K.
Mitra, H. Li, I.-S. Lin, and T-H. Yu. A new class of nonlinear filters
for image enhancement. In
Proc. Intl. Conf on Acoustics, Speech, and Signal
Processing,
pp.
2
5
2
5-2 5 28 (Toronto, April 199 1).
[Per901
P.
Perona and
J.
Malik. Scale space and edge detection using anisotropic
diffusion.
IEEE
Trans. Putt. Anal, Machine Intell.
12(7), 629-639 (July 1990).
[Ram901 G. Ramponi. Bi-impulse response design of isotropic quadratic filters.
Proc. IEEE
78(4), 665-677 (April 1990).
[Ram941
G.
Ramponi and
S.
Carrato. Performance of the Skewness-of-Gaussian
(SoG) edge extractor. In
Proc. Seventh European Signal Processing Conf:
Vol. I,
pp. 4 54-45 7 (Edinburgh, Scotland, September 1994).

Get Nonlinear Image Processing now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.