© The Institution of Engineering and Technology
This study introduces cognition-based parameter setting of non-linear filters using a face recognition system. The parameter setting problem is generally solved by the maximisation or minimisation of some objective evaluation functions such as correlation and statistical independence. However, the tuned filter output is not always adequate for face recognition systems because filter and system are separately tuned using different criterion. When a single image with noise is considered, it is difficult to employ such objective functions because only a single image exists, and the original image cannot be known. When the authors consider some problems such as contrast adjustment and non-photo-realistic rendering, it is also difficult to set an objective criterion for parameter setting because there are no correct solutions other than humans’ subjectivity. To handle such cases, the authors look to some subjective information such as a face in an image, and directly employ a face recognition system as the evaluation function for parameter setting. Experimental results show that cognition-based evaluation has the potential to handle these types of problems.
References
-
-
1)
-
K. Yoneji ,
M. Tanaka ,
M. Okutomi
.
A human-friendly restoration filter.
IEICE Trans. Inf. Syst.
,
10 ,
2830 -
2839
-
2)
-
http://franck.fleurey.free.fr/FaceDetection/.
-
3)
-
K. Arakawa ,
T. Okada
.
ɛ-Separating nonlinear filter bank and its application to face image beautification.
IEICE Trans. Fundam.
,
4 ,
52 -
62
-
4)
-
Tomasi, C., Manduchi, R.: `Bilateral filtering for gray and color images', Int. Conf. on Computer Vision, 1998, p. 839–846.
-
5)
-
H. Rowley ,
S. Baluja ,
T. Kanade
.
Neural network-based face detection.
IEEE Trans. Pattern Anal. Mach. Intell.
,
1 ,
23 -
38
-
6)
-
P.-Y. Hsiao ,
C.-L. Lu ,
L.-C. Fu
.
Multilayered image processing for multiscale harris corner detection in digital realization.
IEEE Trans. Ind. Electron.
,
5 ,
1799 -
1805
-
7)
-
A.S. Georghiades ,
P.N. Belhumeur ,
D.J. Kriegman
.
From few to many: illumination cone models for face recognition under variable lighting and pose.
IEEE Trans. Pattern Anal. Mach. Intell.
,
6 ,
643 -
660
-
8)
-
J. Sporring ,
J. Weickert
.
Information measures in scale-spaces.
IEEE Trans. Inf. Theory
,
1051 -
1058
-
9)
-
T. Abe ,
M. Matsumoto ,
S. Hashimoto
.
Automatic parameter optimization in ɛ-filter for acoustical signal utilizing correlation coefficient.
J. Acoust. Soc. Am.
,
2 ,
896 -
901
-
10)
-
P. Vadakkepat ,
P. Lim ,
L.C.D. Silva ,
L. Jing ,
L.L. Ling
.
Multimodal approach to human-face detection and tracking.
IEEE Trans. Ind. Electron.
,
3 ,
1385 -
1393
-
11)
-
S. Umeda
.
Blind deconvolution of blurred images by using ICA.
IEICE Trans. Fundam.
,
6 ,
677 -
685
-
12)
-
D.R.K. Brownrigg
.
The weighted median filter.
Commun. ACM
,
807 -
818
-
13)
-
P. Mrazek ,
M. Navara
.
Selection of optimal stopping time for nonlinear diffusion filtering.
Int. J. Comput. Vis.
,
189 -
203
-
14)
-
M. Matsumoto ,
S. Hashimoto
.
Estimation of optimal parameter in ɛ-filter based on signal-noise decorrelation.
IEICE Trans. Inf. Syst.
,
6 ,
1312 -
1315
-
15)
-
D.L. Donoho
.
’ Denoising by soft-thresholding.
IEEE Trans. Inf. Theory.
,
3 ,
613 -
627
-
16)
-
S.J. Ko ,
Y.H. Lee
.
Center weighted median filters and their applications to image enhancement.
IEEE Trans. Circuits Syst.
,
984 -
993
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2011.0301
Related content
content/journals/10.1049/iet-ipr.2011.0301
pub_keyword,iet_inspecKeyword,pub_concept
6
6