IEICE TRANSACTIONS on Fundamentals
Image Inpainting Based on Adaptive Total Variation Model
Summary :
In this letter, a novel adaptive total variation (ATV) model is proposed for image inpainting. The classical TV model is a partial differential equation (PDE)-based technique. While the TV model can preserve the image edges well, it has some drawbacks, such as staircase effect in the inpainted image and slow convergence rate. By analyzing the diffusion mechanism of TV model and introducing a new edge detection operator named difference curvature, we propose a novel ATV inpainting model. The proposed ATV model can diffuse the image information smoothly and quickly, namely, this model not only eliminates the staircase effect but also accelerates the convergence rate. Experimental results demonstrate the effectiveness of the proposed scheme.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E94-A No.7 pp.1608-1612
- Publication Date
- 2011/07/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E94.A.1608
- Type of Manuscript
- LETTER
- Category
- Image
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Zhaolin LU, Jiansheng QIAN, Leida LI, "Image Inpainting Based on Adaptive Total Variation Model" in IEICE TRANSACTIONS on Fundamentals,
vol. E94-A, no. 7, pp. 1608-1612, July 2011, doi: 10.1587/transfun.E94.A.1608.
Abstract: In this letter, a novel adaptive total variation (ATV) model is proposed for image inpainting. The classical TV model is a partial differential equation (PDE)-based technique. While the TV model can preserve the image edges well, it has some drawbacks, such as staircase effect in the inpainted image and slow convergence rate. By analyzing the diffusion mechanism of TV model and introducing a new edge detection operator named difference curvature, we propose a novel ATV inpainting model. The proposed ATV model can diffuse the image information smoothly and quickly, namely, this model not only eliminates the staircase effect but also accelerates the convergence rate. Experimental results demonstrate the effectiveness of the proposed scheme.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E94.A.1608/_p
Copy
@ARTICLE{e94-a_7_1608,
author={Zhaolin LU, Jiansheng QIAN, Leida LI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Image Inpainting Based on Adaptive Total Variation Model},
year={2011},
volume={E94-A},
number={7},
pages={1608-1612},
abstract={In this letter, a novel adaptive total variation (ATV) model is proposed for image inpainting. The classical TV model is a partial differential equation (PDE)-based technique. While the TV model can preserve the image edges well, it has some drawbacks, such as staircase effect in the inpainted image and slow convergence rate. By analyzing the diffusion mechanism of TV model and introducing a new edge detection operator named difference curvature, we propose a novel ATV inpainting model. The proposed ATV model can diffuse the image information smoothly and quickly, namely, this model not only eliminates the staircase effect but also accelerates the convergence rate. Experimental results demonstrate the effectiveness of the proposed scheme.},
keywords={},
doi={10.1587/transfun.E94.A.1608},
ISSN={1745-1337},
month={July},}
Copy
TY - JOUR
TI - Image Inpainting Based on Adaptive Total Variation Model
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1608
EP - 1612
AU - Zhaolin LU
AU - Jiansheng QIAN
AU - Leida LI
PY - 2011
DO - 10.1587/transfun.E94.A.1608
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E94-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2011
AB - In this letter, a novel adaptive total variation (ATV) model is proposed for image inpainting. The classical TV model is a partial differential equation (PDE)-based technique. While the TV model can preserve the image edges well, it has some drawbacks, such as staircase effect in the inpainted image and slow convergence rate. By analyzing the diffusion mechanism of TV model and introducing a new edge detection operator named difference curvature, we propose a novel ATV inpainting model. The proposed ATV model can diffuse the image information smoothly and quickly, namely, this model not only eliminates the staircase effect but also accelerates the convergence rate. Experimental results demonstrate the effectiveness of the proposed scheme.
ER -
English
