High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity


In recent years, picture restoration has improved significantly thanks to techniques based on nonlocal self-similarity and global structural regularisation. Repetitiveness of small picture patches can be used as a powerful prior in the reconstruction process through nonlocal self-similarity. A similar approach underpins global structure regularisation, in which pixels are used to indicate the structure of objects in the image. Keeping this structural information to a minimum reduces the likelihood of artefacts in the reconstruction process. Most image restoration methods have only evaluated one of these two options up to now, and not both at the same time. Nonlocal self-similarity and global structure sparsity are combined in a single efficient model in this article. A weighted nuclear norm-based adaptive regularisation technique is used to recreate a group of similar patches at the same time. A novel technique that decomposes the image into smooth and sparse residual components, the latter of which is regularised using the l1norm, preserves the image's global structure. For efficient picture recovery, an algorithm that uses the alternating direction approach of multipliers algorithm is used. Image completion and super-resolution tasks are used to test the suggested method's performance. Our solution outperforms current state-of-the-art approaches for these tasks, regardless of the extent of image corruption, according to experimental results.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : Low-Rank Quaternion Approximation for Color Image Processing ABSTRACT: Grayscale image processing has seen tremendous success with methods based on low-rank matrix approximation (LRMA). By default, LRMA restores
PROJECT TITLE : Reconstruction of Binary Shapes From Blurred Images via Hankel-Structured Low-Rank Matrix Recovery ABSTRACT: We are increasingly dealing with discrete-domain samples of analogue images due to the popularity of
PROJECT TITLE : Matrix Completion Based on Non-Convex Low-Rank Approximation ABSTRACT: NNM, a convex relaxation for rank minimization (RM), is a widely used tool for matrix completion and relevant low-rank approximation issues
PROJECT TITLE :Low-Rank Matrix Recovery From Noisy, Quantized, and Erroneous Measurements - 2018ABSTRACT:This Project proposes a communication-reduced, cyber-resilient, and data-preserved data collection framework. Random noise
PROJECT TITLE :Large-Scale Kernel-Based Feature Extraction via Low-Rank Subspace Tracking on a Budget - 2018ABSTRACT:Kernel-primarily based ways get pleasure from powerful generalization capabilities in learning a selection of

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry