Adaptive kernel-based image denoising employing semi-parametric regularization

Pantelis Bouboulis, Konstantinos Slavakis, Sergios Theodoridis

Research output: Contribution to journalArticlepeer-review

48 Scopus citations


The main contribution of this paper is the development of a novel approach, based on the theory of Reproducing Kernel Hilbert Spaces (RKHS), for the problem of noise removal in the spatial domain. The proposed methodology has the advantage that it is able to remove any kind of additive noise (impulse, gaussian, uniform, etc.) from any digital image, in contrast to the most commonly used denoising techniques, which are noise dependent. The problem is cast as an optimization task in a RKHS, by taking advantage of the celebrated Representer Theorem in its semi-parametric formulation. The semi-parametric formulation, although known in theory, has so far found limited, to our knowledge, application. However, in the image denoising problem, its use is dictated by the nature of the problem itself. The need for edge preservation naturally leads to such a modeling. Examples verify that in the presence of gaussian noise the proposed methodology performs well compared to wavelet based technics and outperforms them significantly in the presence of impulse or mixed noise.

Original languageEnglish (US)
Article number5430976
Pages (from-to)1465-1479
Number of pages15
JournalIEEE Transactions on Image Processing
Issue number6
StatePublished - Jun 2010


  • Denoising
  • Kernel
  • Reproducing Kernel Hilbert Spaces (RKHS)
  • Semi-parametric representer theorem


Dive into the research topics of 'Adaptive kernel-based image denoising employing semi-parametric regularization'. Together they form a unique fingerprint.

Cite this