Spatially adaptive Total Variation image denoising under salt and pepper noise

Renán Rojas, Paul Rodriguez

Research output: Contribution to journalConference articlepeer-review

26 Scopus citations


Automated selection of the regularization parameter for Total Variation restoration has shown to give very accurate reconstruction results. Most of the literature is devoted to the ℓ 2-TV case (images corrupted with Gaussian noise), whereas for the ℓ 1-TV case (images corrupted with salt-and-pepper noise) there are only a couple of published algorithms. In this paper we present a computationally efficient algorithm for ℓ 1-TV denoising of grayscale and color images, which spatially adapts its regularization parameter. The proposed algorithm, which is based on the Iteratively Reweighted Norm algorithm, uses an adaptive median filter to initially estimate the outliers of the noisy (observed) image, and then proceeds to solve the ℓ 1-TV problem only for the noisy pixels while spatially adapts the regularization parameter based on local statistics. The experimental results show that the proposed method yields impressive results even when 90% of the image pixels are corrupted.

Original languageEnglish
Pages (from-to)278-282
Number of pages5
JournalEuropean Signal Processing Conference
StatePublished - 2011
Event19th European Signal Processing Conference, EUSIPCO 2011 - Barcelona, Spain
Duration: 29 Aug 20112 Sep 2011


Dive into the research topics of 'Spatially adaptive Total Variation image denoising under salt and pepper noise'. Together they form a unique fingerprint.

Cite this