Image deblurring based on fractional-order total variation and total generalized variation
Bin Xie, Hui Fei Huang, Huang An · Journal of Physics Conference Series · 2019
Abstract 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.