PROJECT TITLE :

A Group-Based Image Inpainting Using Patch Refinement in MRF Framework - 2018

ABSTRACT:

This Project presents a Markov random field (MRF)-primarily based image inpainting algorithm using patch selection from teams of comparable patches and optimal patch assignment through joint patch refinement. In patch selection, a unique cluster formation strategy based on subspace clustering is introduced to search the candidate patches in relevant supply region only. This improves patch searching in terms of both quality and time. We have a tendency to conjointly propose an efficient patch refinement scheme using higher order singular price decomposition to capture underlying pattern among the candidate patches. This eliminates random variation and unwanted artifacts moreover. Finally, a weight term is computed, primarily based on the refined patches and is incorporated in the objective operate of the MRF model to boost the optimal patch assignment. Experimental results on a massive number of natural images and comparison with well-known existing methods demonstrate the efficacy and superiority of the proposed method.