A novel image inpainting framework based on multilevel image pyramids

Authors

  • Md.Salman Md.Riyaz Bombaywala UKA Tarsadia University, Bardoli, Gujarat, India.
  • Chirag Paunwala Sarvajanik College of Engineering and Technology, Surat, Gujarat, India.

Keywords:

Exemplar-based inpainting, Image Inpainting, Multilevel, Pyramid

Abstract

Image inpainting is an art of manipulating an image in a visually undetectable way. A considerable amount of research has been done in this area over the last few years. However, the state of art techniques does suffer from computational complexities and plausible results. This paper proposes a multilevel image pyramid-based image inpainting algorithm. The image inpainting algorithm starts from the coarsest level of the image pyramid and inpainting information is propagated to subsequent levels until the bottom level gets inpainted. The search strategy used in the algorithm is based on hashing the coherent information in an image which makes the search fast and accurate. Also, the search space is constrained based on the propagated information thereby reducing the complexity of the algorithm. Compared to other inpainting methods; the proposed algorithm inpaints the target region with better plausibility and human vision conformation. Experimental results show that the proposed algorithm has better results as compared to other inpainting techniques.

Downloads

Published

2021-10-05