结构测度约束下基于加权分形的图像修复算法

doi:10.3969/j.issn.1001-2400.2012.06.014

Abstract

Abstract:

Aiming at enlarging the searching scope and moderately raising the weights of structure pixels during searching and matching in the process of calculating the best repairing patch for each damaged patch, an image inpainting algorithm based on the weighted fractal under the structure-measurement constraint is presented. First, selected domain blocks are transformed by geometrical transform and isomorphic transform. Using the resulting blocks, the codebook is constructed and serves as the enlarged searching scope. By computing the anisotropic nonlinear structure tensor, the local structure measurement is obtained, in accordance with which the normalized weight map is constructed. The luminance transform is performed, in which we derive its new parameter formulas by minimizing the weighted error between the damaged patch and each domain block in the codebook under the structure-measurement constraint. Lastly, we search in the codebook for the best repairing patch with the minimal weighted error, and then the best repairing patch is used to fill in the damaged patch. Experimental results show that the proposed method can restore damaged structures well and simultaneously make the newly filled region maintain good consistency with the source region. The subjective quality and objective evaluation of the inpainted image are both improved greatly.

Key words: image inpainting, anisotropic, structure tensor, local structure measurement, weighted, fractal

CLC Number:

TP317.4

YANG Xiuhong;GUO Baolong;YAN Chunman. Image inpainting algorithm based on the weighted fractal under the structure-measurement constraint[J].J4, 2012, 39(6): 84-91.

References

［1］ Shih T K, Chang R C. Digital Inpainting-Survey and Multilayer Image Inpainting Algorithm［C］//Third International Conference on Information Technology and Applications. Sydney: IEEE, 2005: 15-24.
［2］ Ma Wenjuan, Ma Qinghua. An Effective Method for Removing Large Object［C］//The 4th International Congress on Image and Signal Processing. Shanghai: IEEE, 2011: 80-84.
［3］ Ling C H, Lin C W, Su C W, et al. Virtual Contour Guided Video Object Inpainting Using Posture Mapping and Retrieval［J］. IEEE Trans on Multimedia, 2011, 13(2): 292-302.
［4］ Xiong Zhiwei, Sun Xiaoyan, Wu Feng. Block-Based Image Compression With Parameter-Assistant Inpainting［J］. IEEE Trans on Image Processing, 2010, 19(6): 1651-1657.
［5］ Wu Guanlin, Chen C Y, Chien S Y. Algorithm and Architecture Design of Image Inpainting Engine for Video Error Concealment Applications［J］. IEEE Trans on Circuits and Systems for Video Technology, 2011, 21(6): 792-803.
［6］郝岩, 冯象初, 许建楼. 一种非局部扩散的图像修复模型［J］. 西安电子科技大学学报, 2010, 37(5): 825-828.
Hao Yan, Feng Xiangchu, Xu Jianlou. Image Inpainting Model of Nonlocal Diffusion［J］. Journal of Xidian University, 2010, 37(5): 825-828.
［7］许建楼, 冯象初, 郝岩. 二阶总广义变分图像修复模型及其算法［J］. 西安电子科技大学学报, 2012, 39(5): 24-32.
Xu Jianlou, Feng Xiangchu, HAO Yan. Second Order Total Generalized Variational Inpainting Model and Its Algorithm［J］. Journal of Xidian University, 2012, 39(5): 24-32.
［8］ Zhang Hongying, Peng Qicong, Wu Yadong. Image Completion Algorithm Based On Texture Synthesis［J］. Journal of Systems Engineering and Electronics, 2007, 18(2): 385-391.
［9］ Wong A, Orchard J. A Nonlocal-means Approach to Exemplar-based Inpainting［C］//IEEE International Conference Image Processing. San Diego: ICIP, 2008: 2600-2603.
［10］ Wohlberg B. Inpainting by Joint Optimization of Linear Combinations of Exemplars［J］. IEEE Signal Processing Letters, 2011, 18(1): 75-78.
［11］ Cerutti S, Marchesi C. Fractal Dimension: From Geometry to Physiology［M］. New Jersey: Wiley-IEEE Press, 2011: 327-346.
［12］ Broxa T, Weickert J, Burgeth B, et al. Nonlinear Structure Tensors［J］. Image and Vision Computing, 2006, 24(1): 41-55.
［13］ Hahn J, Lee C O. A Nonlinear Structure Tensor with the Diffusivity Matrix Composed of the Image Gradient［J］. J Math Imaging Vis, 2009, 34(2): 137-151.
［14］ Wang Z, Bovik A C, Sheikh H R, et al. Image Quality Assessment: from Error Visibility to Structural Similarity［J］. IEEE Trans on Image Processing, 2004, 13(4): 600-612.

[1]	FENG Xiangchu,WANG Ping,HE Ruiqiang. Method for inpainting blind images using the game and L0 constraint [J]. Journal of Xidian University, 2021, 48(4): 103-112.
[2]	HE Yunbin,LENG Xin,WAN Jing. Unbalanced data weighted boundary point integration undersampling method [J]. Journal of Xidian University, 2021, 48(4): 176-183.
[3]	WANG Xin,CHANG Guiqing,CHI Chenchen. Separation and imaging of the anisotropic scattering targets in the wide-angle SAR [J]. Journal of Xidian University, 2021, 48(2): 109-116.
[4]	ZHANG Meng,LI Zhuo,XING Lijuan. Weighted sum codes-aided SCL decoding of polar codes [J]. Journal of Xidian University, 2020, 47(6): 66-71.
[5]	YANG Hongyu,ZHANG Xugao. Network security situation adaptive prediction model [J]. Journal of Xidian University, 2020, 47(3): 14-22.
[6]	WANG Haobo,DA Xinyu,XU Ruiyang,LIANG Yuan,NI Lei,ZHANG Hongwei. Constellation splitting security transmission technology based on the multi-parameter weighted-type fractional Fourier transform for dual-polarized satellites [J]. Journal of Xidian University, 2020, 47(3): 121-127.
[7]	LI Li,YAN Li,ZHOU Lei,LI Dong,LIU Hongqing. l_p-norm regularization optimization of impulsive disturbance removal [J]. Journal of Xidian University, 2020, 47(1): 30-36.
[8]	TIAN Qiang,FENG Dazheng,HU Haoshuang. Constrained weighted least squares algorithm for TOA-based joint synchronization and localization [J]. Journal of Xidian University, 2019, 46(5): 1-7.
[9]	WANG Boyuan,LIU Xuelin,YU Baoguo,JIA Ruicai,GAN Xingli,HUANG Lu. Improved weighted k-nearest neighbor algorithm for WiFi fingerprint positioning [J]. Journal of Xidian University, 2019, 46(5): 41-47.
[10]	TIAN Qiang,FENG Dazheng,LI Jin,HU Haoshuang. New two-step semidefinite relaxation method for acoustic energy-based localization [J]. Journal of Xidian University, 2019, 46(4): 16-21.
[11]	QI Xiaogang,HU Qiuqiu,YAO Xuqing,LIU Lifang. Efficient alarm analysis approach for communication networks [J]. Journal of Xidian University, 2019, 46(4): 1-8.
[12]	QI Xiaogang, YUAN Lieping, LIU Lifang. Hybrid location algorithm for the acoustic source based on error correction [J]. Journal of Xidian University, 2019, 46(1): 1-7.
[13]	ZHOU Cheng,MAN Xin,ZHOU Zhiwen. Constrained weighted least squares algorithm based on the MIMO radar system for target localization [J]. Journal of Xidian University, 2019, 46(1): 124-129.
[14]	WEI Juan;JI Yongxiang;NIU Junru. Novel algorithm for DOA estimation based on the sparse reconstruction [J]. Journal of Xidian University, 2018, 45(5): 13-18.
[15]	FENG Xiangchu;LI Xiaohui;WANG Weiwei;JIA Xixi. Modified BM3D algorithm for image denoising using the directed diffusion equation [J]. Journal of Xidian University, 2017, 44(5): 102-108.

Image inpainting algorithm based on the weighted fractal under the structure-measurement constraint

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 10