Wavelet iterative regularization for image restoration with varying scale parameter
- Resource Type
- Authors
- Min Li; Bin-bin Hao; Xiangchu Feng
- Source
- Signal Processing: Image Communication. 23:433-441
- Subject
- Discrete wavelet transform
Mathematical optimization
Lifting scheme
Stationary wavelet transform
Second-generation wavelet transform
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Wavelet transform
Cascade algorithm
Data_CODINGANDINFORMATIONTHEORY
Wavelet packet decomposition
Wavelet
Signal Processing
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering
Algorithm
Software
Mathematics
- Language
- ISSN
- 0923-5965
We first generalize the wavelet-based iterative regularization method and the wavelet-based inverse scale space to shift invariant wavelet-based cases for image restoration. Then, a method to estimate the scale parameter is proposed from wavelet-based iterative regularization; different parameters with different iterations are obtained. The wavelet-based iterative regularization with the new parameter, which controls the extent of denoising more precisely in the wavelet domain, leads to iterative global wavelet shrinkage. We also obtain a time adaptive wavelet-based inverse scale space from the iterative procedure with the proposed parameter. We provide a proof of the convergence and obtain a stopping criterion for the iterative procedure with the new scale parameter based on wavelet transform. The proposed iterative regularized method obtains quite accurate results on a variety of images. Numerical experiments show that the proposed methods can efficiently remove noise and well preserve the details of images.