|Table of Contents|

Image Restoration Model Based on Total Variation with Fractional Order Singularity Extraction(PDF)

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2003年04期
Page:
400-404
Research Field:
Publishing date:

Info

Title:
Image Restoration Model Based on Total Variation with Fractional Order Singularity Extraction
Author(s):
WangKaiyu XiaoLiang ① WeiZhihui ②
Department of AppliedMathematics,Nanjing University, Nanjing 210093
①Department of Computer Science and Technology, NUST, Nanjing 210094
② Graduate School,NUST, Nanjing 210094
Keywords:
total variat ion restoration model fractional order derivative residual error correctionimage restoration
PACS:
TP391.41
DOI:
-
Abstract:
Although total variation restoration model is used to de-noise the non-texture image, it is not sufficient for real nature images since it removes small scale texture and noise. The drawbacks of the total variation restoration model are analyzed. The possibility of extracting the texture with fractional order derivatives filter is studied and an improved total variation restoration model combined with fractional order derivatives singularities extract ing proposed. The hybrid model provides a new tool to image decomposition and image modeling. Experiments show the model is suitable to de-noising for natural image which is rich of textures, and the model is more effect ive than the previous model.

References:

1 Rudin L, Osher S, Fatemi E. Nonlinear total variation based noise removel algorithms[ J] . Physica D,1992, 60: 259~ 268.
2 Chan T, Shan Jianhong.Mathematical models for local non-texture inpainting[ J] . SIAM Applied Mathematical,2001, 62( 3) : 1 019~ 1 043.
3 Meyer Y. Oscillating patterns in image processing and nonlinear evolutions. University lecture series, 22[M] . Priston: American Mathematical Society Press, 2002.
4 Shekarforoush H. Super-rosolution in computer vision[ D] . France, Nice: University of Nice, 1996.

Memo

Memo:
-
Last Update: 2013-03-17