Abstract
Mixed noise removal from a natural image is a challenging task since the complex noise distribution usually is inestimable. Many noise removal methods based on the low rank approximation have an excellent image denoising performance and are effective for recovering the images corrupted by Gaussian noise. These methods based on the additive white Gaussian noise(AWGN) model are sensitive to the outliers and non-Gaussian noise, such as the salt-and-pepper impulse noise (SPIN) and random valued impulse noise (RVIN). Such methods for mixed noise removal, however, are less effective in preserving image structures and tend to undesired staircase artifacts. This paper presents a novel Nonconvex Low Rank Model with Phase congruency and overlapping Group sparsity regularization (NLRM-PG) for mixed noise removal. Moreover, an efficient optimization algorithm under the alternating direction method of multipliers and majorization minimization framework is proposed to solve the NLRM-PG model. We demonstrate that the proposed method is effective for preserving local irregular structures and it reduces staircase artifacts with the two types of mixture noise, namely, AWGN+SPIN and AWGN+RVIN. Both qualitative and quantitative experiment results on synthetic noisy images and real noisy images illustrate that the proposed method can remove mixture noise in images more efficiently than the existing methods can do. And the results also outperform those obtained by using the competing state-of-the-art methods, particularly for the removal of high-density impulse noise.
Highlights
Images captured in the real world are usually destroyed by noise, resulting in the degradation of image quality
To cope with the above obstacles of traditional Nonconvex Low Rank Approximation (NLRA) methods for mixed noise removal, in this paper, we propose an effective mixed removal method based on a nonconvex low rank approximation model with phase congruency regularization and overlapping group sparsity
It is not difficult to find that the proposed NLRM-PG with phase congruency regularization has overall better performance in different noise levels than NLRA and RPCA-NRA that are methods with nonconvex low rank approximation
Summary
Images captured in the real world are usually destroyed by noise, resulting in the degradation of image quality. Xuegang et al.: Nonconvex Low Rank Approximation With Phase Congruency Regularization coding and NSS prior in [6] were integrated into a regularization term and introduced into the framework that solved minimization problem These methods are effective and have excellent denoising performance for AWGN. To better preserve the image edges, IN was treated as outliers in [11]–[13], robust fidelity terms based on l1 norm and l0 norm were utilized to estimate the IN by hard or soft thresholding, coupled with an appropriate regularizer These methods have displayed promising denoising performance in removing the IN, which cannot effectively remove the AWGN. An effective mixed removal method based on a nonconvex low rank approximation model with phase congruency regularization and overlapping group sparsity. L, S, and N are with the same size of m × n as Y with overlapped patches, where m and n stand for the width, the height of matrix
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
