A Novel Image Inpainting Method Based on Sparse Decomposition

Xuan Zhu; Xu Feng Zhang; Qiu Ju Li; Ji Yao Tao; Ben Yuan Li

doi:10.4028/www.scientific.net/AMM.738-739.573

Paper Titles

The Micro-Video Label Classification System Design Based on Network Data Acquisition
p.556

Boundary Stitching Method for Block-Based Parallel Error Diffusion
p.560

Research on the Method of Screening the Real Vehicle Data Fragment for Driving Cycle
p.564

Application of Statistical Methods in Experimental Modal Frequency Extraction
p.569

A Novel Image Inpainting Method Based on Sparse Decomposition
p.573

A PVC Identification Method of ECG Signal Based on Improved BPNN
p.578

A Visual Dependency Analysis Method Based on VHDL
p.582

Adaptive Face Gender Recognition Based on NSGA-II and Compressive Sensing
p.586

An Algorithm for Electronic Image Stabilization
p.590

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 738-739A Novel Image Inpainting Method Based on Sparse...

A Novel Image Inpainting Method Based on Sparse Decomposition

Abstract:

Redundant Discrete Wavelet Transform (RDWT) and Wavelet Atomic Transform (WAT) are proposed in this paper as a couple of dictionaries to get the structure and texture basing on morphological component decomposition. Then, basing on the fact that the structure and texture have different characteristics, in this paper we use curvature driven diffusion model and Criminisi texture synthesis method to inpaint the structure and texture respectively. At last, compound the inpainted structure and texture and get the inpainting result. The experiment results show the new method can not only decompose the image very well, but also inpaint the image with strong and fairing edge, complete and clear texture .This method shows better results in image inpainting compared to the classical ones.

You might also be interested in these eBooks

Sensors, Measurement, Intelligent Materials and Technologies III

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 738-739)

Pages:

573-577

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.738-739.573

Citation:

Cite this paper

Online since:

March 2015

Authors:

Xuan Zhu, Xu Feng Zhang*, Qiu Ju Li, Ji Yao Tao, Ben Yuan Li

Keywords:

CDD Model, Criminisi Method, Dictionary, Image Inpainting, Sparse Decomposition

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] M. Elad, J-L. Starck,P. Querre, andD. Donoho, Simultaneous cartoon and texture image inpainting, Appl. Comput. Harmon. Anal., vol. 19, p.340–358, (2005).

DOI: 10.1016/j.acha.2005.03.005

Google Scholar

[2] Kang-Yu Ni. Vatiational PDE-based Image Segmentation and Inpainting with Application in computer Graphics[D]. Los Angeles: University of CaIifornia, (2008).

Google Scholar

[3] Baolong Fang. Image restoration algorithm based on texture synthesis research [D]. Shandong university, 2013(In Chinese).

Google Scholar

[4] Xuan Zhu, Mingquan Zhou. Computer science. 2008(12) (In Chinese).

Google Scholar

[5] A . Criminisi, P. P´erez and K. Toyama . IEEE Trans actions on Image Processing, 2004, 13 (9) 1200—1212.

Google Scholar

[6] Smith L N, Elad M. IEEE Signal Processing Letter，2013. 20 (1) : 79-82.

Google Scholar

[7] Fowler J E, The redundant discrete wavelet transform and additive noise. IEEE Signal Processing Letters, 2005, 12(9): 629-632.

DOI: 10.1109/lsp.2005.853048

Google Scholar

[8] Yimei Song, Chengwu Lu, et al. Application Research of Computers，2010. 27（5）1962-1964. (In Chinese).

Google Scholar