A new fractional-order variational model for speckled de-noising

Abstract : In this paper, a novel speckled image de-noising algorithm is proposed. A fractional-order multiplicative variational model is included as a multiplicative constraint in the regularization problem thereby the appropriate regularization parameter will be controlled by the optimization process itself. An adaptive selection method based on image regions property is used for the selection of the appropriate fractional-order value. The proposed algorithm not only overcomes the disadvantage of generating artificial edges but also has the advantage of de-noising and edges preservation.Experimental results show that the fractional order multiplicative variational model can improve the Peak Signal to Noise Ratio (PSNR) of image, preserve image structures and overcomes the disadvantage of generating artificial edges in the de-noising process.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01128762
Contributor : Frédéric Davesne <>
Submitted on : Tuesday, March 10, 2015 - 12:45:33 PM
Last modification on : Monday, October 28, 2019 - 10:50:21 AM

Identifiers

Collections

Citation

Meriem Hacini, Fella Hachouf, Khalifa Djemal. A new fractional-order variational model for speckled de-noising. 5th European Workshop on Visual Information Processing (EUVIP 2014), Dec 2014, Paris, France. ⟨10.1109/EUVIP.2014.7018384⟩. ⟨hal-01128762⟩

Share

Metrics

Record views

84