PROJECT TITLE :

From Rank Estimation to Rank Approximation Rank Residual Constraint for Image Restoration

ABSTRACT:

Rank residual constraint (RRC) model is a new approach to the problem of rank minimization that we present in this research. Our approach gradually approximations the underlying low-rank matrix by minimising the rank residual differs from existing low-rank based approaches, such as the well-known nuclear norm minimization (NNM) and weighted nuclear norm minimization (WNNM), which estimate the underlying low-rank matrix directly from corrupted observations. We apply the proposed RRC model to image restoration tasks, such as image denoising and image compression artefacts reduction, by integrating the image nonlocal self-similarity (NSS) prior to the model. It's important to get a good estimate of the degraded picture first, and then minimise the rank residual between that and an image NSS prior, in order to get a more accurate estimate of the desired image. As a result, each iteration brings the estimated image and the reference image up to date in unison. We also conduct a theoretical evaluation of the suggested RRC model's viability based on the group-based sparse representation model. Researchers have found that the RRC model beats several current approaches in terms of both objective and subjective quality.