An efficient image inpainting algorithm based on a modified Gray–Scott model

Jian Wang, Xinpei Wu, Heming Xu, Junseok Kim

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

In this paper, we proposes an image inpainting algorithm based on the modified Gray–Scott (GS) model. We have added a fidelity term to control the edge and stability of pixel value evolution during the image inpainting process. We verify the effectiveness and robustness of the proposed model through various experiments. By constructing binary images and complex pixel images with a bit depth of 8, we demonstrate the effectiveness of the model on damaged images with Gaussian noise and locally missing pixels. Additionally, we use metrics such as root mean square error (RMSE) and peak signal-to-noise ratio (PSNR) to evaluate the modified GS model. We compared the model with other methods in terms of both visual and computational metrics, and our proposed model outperforms other methods.

Original languageEnglish
Article number109265
JournalSignal Processing
Volume214
DOIs
Publication statusPublished - 2024 Jan

Bibliographical note

Publisher Copyright:
© 2023 Elsevier B.V.

Keywords

  • Gray–Scott
  • Image inpanting
  • PSNR

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'An efficient image inpainting algorithm based on a modified Gray–Scott model'. Together they form a unique fingerprint.

Cite this