Papers by Pauli Kuosmanen
European Signal Processing Conference, Sep 1, 2000
Bookmarks Related papers MentionsView impact
NSIP, 1999
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
In this paper we use a recently introduced method called output distributional influence function... more In this paper we use a recently introduced method called output distributional influence function (ODIF) in the optimization of filters. The ODIF gives information about the robustness of finite length filters and thus it can be used in real filtering situations to find filters having desired robustness properties. We consider possible optimization criteria based on the ODIFs for the expectation and variance which could be used alone or combined with other types of optimization criteria. We use in this paper L-filters as examples of the filter optimization since that filter class includes filters having wide range of different robustness properties. 1. INFLUENCE FUNCTION Influence function (IF) is a useful heuristic tool of robust statistics introduced by Hampel [1, 2] under the name influence curve (IC) for studying the performance of filters under noisy conditions. Definition 1. The IF of estimatorT at underlying probability distributionF is given by IF(y) = lim t!0+ T ((1 t)F + t...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Mar 5, 1999
Bookmarks Related papers MentionsView impact
Springer eBooks, 1998
A novel nonlinear filtering method for multivariate data is proposed. The algorithm belongs to th... more A novel nonlinear filtering method for multivariate data is proposed. The algorithm belongs to the rank conditioned rank selection (RCRS) filtering framework. A similar algorithm to that of the basic RCRS filter can be applied for finding the optimal filters. Experimental results and comparison to other common filter classes are presented.
Bookmarks Related papers MentionsView impact
Journal of Electronic Imaging, Jul 1, 1996
Soft morphological filters form a large class of nonlinear filters with many desirable properties... more Soft morphological filters form a large class of nonlinear filters with many desirable properties. However, few design methods exist for these filters. This paper demonstrates how optimization schemes, simulated annealing and genetic algorithms, can be employed in the search for soft morphological filters having optimal performance in a given signal processing task. Furthermore, the properties of the achieved optimal soft
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Apr 4, 1997
ABSTRACT
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Mar 25, 1996
ABSTRACT
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Sep 24, 1998
ABSTRACT
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Mar 28, 1995
ABSTRACT
Bookmarks Related papers MentionsView impact
European Signal Processing Conference, Sep 8, 1998
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, May 1, 1994
ABSTRACT
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Apr 6, 1998
A new class of adaptive (alpha)-trimmed filters well suited for processing of images corrupted wi... more A new class of adaptive (alpha)-trimmed filters well suited for processing of images corrupted with non-symmetrical pdf speckle and impulsive noise is proposed. It is shown that in certain cases one can provide a better speckle reduction and impulse removal by non-...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Mar 28, 1995
Soft morphological filters form a large class of nonlinear filters with many desirable properties... more Soft morphological filters form a large class of nonlinear filters with many desirable properties. However, few design methods exist for these filters and in the existing methods the selection of the filter composition tends to be ad-hoc and application specific. This paper demonstrates how optimization schemes, simulated annealing and genetic algorithms, can be employed in the search for optimal soft morphological filter sequences realizing optimal performance in a given signal processing task. This paper describes also the modifications in the optimization schemes required to obtain sufficient convergence.
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Mar 3, 2000
ABSTRACT
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Oct 14, 1997
ABSTRACT Robust adaptive vector filtering algorithms applicable to color and multichannel image p... more ABSTRACT Robust adaptive vector filtering algorithms applicable to color and multichannel image processing are proposed. They are based on the use of Q-parameter that is a vector analog of quasirange. Considered algorithms have a good combination of properties: effective noise reduction, ability to remove spikes, edge and detail preservation, and low computational complexity. Their characteristics are evaluated quantitatively and compared to non-adaptive counterparts. Advantages of proposed algorithms are also demonstrated by simulated image processing results.
Bookmarks Related papers MentionsView impact
Proceedings of SPIE, Jun 30, 1994
ABSTRACT
Bookmarks Related papers MentionsView impact
Uploads
Papers by Pauli Kuosmanen