A Tensor-based Technique for Structure-aware Image Inpainting

Adib Akl, Charles Yaacoub

2017

Abstract

Image inpainting is an active area of study in computer graphics, computer vision and image processing. Different image inpainting algorithms have been recently proposed. Most of them have shown their efficiency with different image types. However, failure cases still exist, especially when dealing with local image variations. This paper presents an image inpainting approach based on structure layer modeling, where this latter is represented by the second-moment matrix, also known as the structure tensor. The structure layer of the image is first inpainted using the non-parametric synthesis algorithm of Wei and Levoy, then the inpainted field of second-moment matrices is used to constrain the inpainting of the image itself. Results show that using the structural information, relevant local patterns can be better inpainted comparing to the standard intensity-based approach.

Paper Citation

in Harvard Style

Akl A. and Yaacoub C. (2017). A Tensor-based Technique for Structure-aware Image Inpainting . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 599-605. DOI: 10.5220/0006214605990605

in Bibtex Style

@conference{icpram17,
author={Adib Akl and Charles Yaacoub},
title={A Tensor-based Technique for Structure-aware Image Inpainting},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={599-605},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006214605990605},
isbn={978-989-758-222-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - A Tensor-based Technique for Structure-aware Image Inpainting
SN - 978-989-758-222-6
AU - Akl A.
AU - Yaacoub C.
PY - 2017
SP - 599
EP - 605
DO - 10.5220/0006214605990605