A New Inpainting Method Based on TV

Min Qin Wang

doi:10.4028/www.scientific.net/AMM.263-266.2375

Paper Titles

Auxiliary Problems in Convex Alternating Structure Optimization Algorithm
p.2349

Clustering Boundary Points Detection Algorithm Based on Gradient Binarization
p.2358

The Study of Effective Video Summarization Algorithm
p.2364

Textual Integrity Detection Algorithm Based on Matrix Encoding
p.2369

A New Inpainting Method Based on TV
p.2375

Data Normalization of Single Camera Visual Measurement Network System
p.2381

Visual Tracking Using Combining Motion Constraint Model and Online Multiple Instance Boost Random Ferns
p.2385

3D Model Reconstruction Based on Close-Range Photogrammetry
p.2393

Building a Low-Cost Eye-Tracking System
p.2399

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 263-266A New Inpainting Method Based on TV

A New Inpainting Method Based on TV

Abstract:

Nature image has complex structure and texture. In past years, people copy the pixels, which come from the surrounding neighborhood or selected example, into damaged region along isophate direction. This might cause such result as blur edges, which looks “unreasonable” to human eyes. This paper proposes a novel algorithm which simultaneously inpaints structures and textures of damaged images. This algorithm use TV to decompose the image into two parts. We inpaint the cartoon image part firstly by boundary reconstruction. Then we do texture synthesis to texture image part guided by boundary reconstruction. The method aims at inpainting structure and texture simultaneously and produces good results for texture with complex structure.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 263-266)

Pages:

2375-2380

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.263-266.2375

Citation:

Cite this paper

Online since:

December 2012

Authors:

Min Qin Wang

Keywords:

Image Decomposition, Image Inpainting, Texture Synthesis, TV

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] M.Bertalmio, et.al, Image inpainting, Computer Graphics, SIGGRAPH, pp.417-422, 2000.

Google Scholar

[2] T.F. Chan, J.Shen, Nontexture inpainting by curvature Driven diffusion (CDD), J. Visual Comm, Image Rep, 12(4):436-449, 2001.

DOI: 10.1006/jvci.2001.0487

Google Scholar

[3] A.Efros, et.al, Texture synthesis by nonparametric sampling, IEEE Int. Conf. Computer Vision, 1999, p.1033–1038.

Google Scholar

[4] M.Ashikhmin, Synthesizing natural textures, in Proc. ACM Symp. Interactive 3D Graphics, p.217–226, 2001.

Google Scholar

[5] A. Rares, et.al. Edge-based image restoration[J]. IEEE Trans. Image Processing, 2005, 14(10):1454-1468

DOI: 10.1109/tip.2005.854466

Google Scholar

[6] A.Criminisi, P.Perezand, K.Tyama，Region filling and object remova lby exemplar-based image inpainting, IEEE Trans. Image Proeessing，vol.13，PP.1200-1212，2004.

DOI: 10.1109/tip.2004.833105

Google Scholar

[7] L. Rudin, S. Osher, E. Fatemi, Nonlinear total variation based noise removal algorithms, Phys. D, p.259–268, 1992.

DOI: 10.1016/0167-2789(92)90242-f

Google Scholar

[8] Meyer Y. Oscillating Patterns in Image Processing and Nonlinear Evolution Equation: The Fifteenth Dean Jacqueline B. Lewis Memorial Lectures[C], Vo1.22 of University Lecture Series, AMS, Providence, 2001.

Google Scholar

[9] L.Vese, S.Osher, Modeling Textures with Total Variation Minimization and Oscillating Patterns in Image Processing, vol. 02-19, UCLA CAM Rep., May 2002.

Google Scholar

[10] L. Vese and S. Osher,, "Modeling textures with total variation minimization and oscillating patterns in image processing," J. Sci. Comput., to be published.

Google Scholar

[11] M. Wang ey.al. Edge-based image completing guided by region segmentation, CCCM'08, vol.1: 152-156, 2008.

Google Scholar