A New Trend in Optimization on Multi Overcomplete Dictionary toward Inpainting

TL;DR

This paper introduces a novel overcomplete dictionary-based decomposition method for image inpainting, demonstrating its effectiveness through simulations in reconstructing lost or deteriorated image parts.

Contribution

It proposes a new technique for image decomposition using overcomplete dictionaries specifically for inpainting applications.

Findings

Effective reconstruction of missing image parts demonstrated

Improved inpainting performance over traditional methods shown

Simulation results validate the proposed approach

Abstract

Recently, great attention was intended toward overcomplete dictionaries and the sparse representations they can provide. In a wide variety of signal processing problems, sparsity serves a crucial property leading to high performance. Inpainting, the process of reconstructing lost or deteriorated parts of images or videos, is an interesting application which can be handled by suitably decomposition of an image through combination of overcomplete dictionaries. This paper addresses a novel technique of such a decomposition and investigate that through inpainting of images. Simulations are presented to demonstrate the validation of our approach.