Open AccessImage deblurring based on fractional-order total variation and total generalized variation
Author(s) -
Bai-Song Xie,
Hui Huang,
Huang An
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1345/2/022006
Subject(s) - deblurring , image (mathematics) , image restoration , variation (astronomy) , artificial intelligence , computer vision , computer science , mathematics , algorithm , dual (grammatical number) , image processing , pattern recognition (psychology) , art , physics , literature , astrophysics
Considering the problem that the traditional method is easy to cause staircase effect and blur detail when removing image blur, we propose a model combined with fractional-order total variation (FOTV) and total generalized variation (TGV) for image deblurring. Firstly, we use the global gradient extraction method (GGES) to divide a blurred image into a smooth portion containing the image features and a detail portion containing the image details. Secondly, we use the TGV method of image deblurring and the FOTV method of image deblurring to repair the two parts of the image separately. Finally, we reconstruct the two restored images together to get the result image. In order to solve the proposed new model effectively, a new numerical algorithm is designed based on the original dual algorithm. The experimental results show that our method is superior to the traditional method in removing the staircase effect and maintaining the image detail area.