Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Bilateral Filter Evaluation Based on Exponential Kernels
Al Ismaeil, Kassem; Aouada, Djamila; Mirbach, Bruno et al.
2012In Pattern Recognition (ICPR), 2012 21st International Conference on
Peer reviewed
 

Files


Full Text
Bilateral Filter Evaluation Based on Exponential Kernels.pdf
Publisher postprint (1.52 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Abstract :
[en] The well-known bilateral filter is used to smooth noisy images while keeping their edges. This filter is commonly used with Gaussian kernel functions without real justification. The choice of the kernel functions has a major effect on the filter behavior. We propose to use exponential kernels with L1 distances instead of Gaussian ones. We derive Stein's Unbiased Risk Estimate to find the optimal parameters of the new filter and compare its performance with the conventional one. We show that this new choice of the kernels has a comparable smoothing effect but with sharper edges due to the faster, smoothly decaying kernels.
Disciplines :
Computer science
Electrical & electronics engineering
Identifiers :
UNILU:UL-CONFERENCE-2012-150
Author, co-author :
Al Ismaeil, Kassem ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Mirbach, Bruno;  IEE S.A.
Ottersten, Björn ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
no
Language :
English
Title :
Bilateral Filter Evaluation Based on Exponential Kernels
Publication date :
2012
Event name :
Pattern Recognition (ICPR), 2012 21st International Conference on
Event place :
Tsukuba, Japan
Event date :
11-15 Nov. 2012
Audience :
International
Main work title :
Pattern Recognition (ICPR), 2012 21st International Conference on
Publisher :
IEEE Xplore
ISBN/EAN :
978-1-4673-2216-4
Pages :
258 - 261
Peer reviewed :
Peer reviewed
Available on ORBilu :
since 03 October 2013

Statistics


Number of views
138 (10 by Unilu)
Number of downloads
188 (8 by Unilu)

WoS citations
 
7

Bibliography


Similar publications



Contact ORBilu