Mode Estimation in High-dimensional Spaces with Flat-top Kernels: Application to Image Denoising

De Decker, Arnaud;Lee, John;François, Damien;Verleysen, Michel
(2010) 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning (ESANN 2010) — Location: Bruges (Belgium) (28.April.2010)

Files

ModeEstimationinHigh-dimensionalSpaceswithFlat-topKernels-ApplicationtoImageDenoising.pdf
  • Restricted Access
  • Adobe PDF
  • 590.62 KB
Request a copy

Details

Authors
Abstract
Data denoising can be achieved by approximating the data distribution and replacing each data item with an estimate of its closest mode. This idea has already been successfully applied to image denoising. The data then consists of pixel intensities or image patches, that is, vectorized groups of pixel intensities. The latter case raises the issue of mode estimation in a high-dimensional space, since patches can contain about 10 to more than 100 pixels. This paper shows that the widely used Gaussian kernel is outperformed by flat-top kernels that are specifically tailored in order to fight the curse of dimensionality.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

De Decker, A., Lee, J., François, D., & Verleysen, M. (2010). Mode Estimation in High-dimensional Spaces with Flat-top Kernels: Application to Image Denoising. Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning (ESANN 2010), p. 411-416. https://hdl.handle.net/2078.5/253907