Dual optimization image repair algorithm based on linear structure and optimal texture

Abstract

The performances of repaired image depend on the local information in the repaired area and the consistency between the repair directions with structural content. Image repair algorithm with texture information performs well in repairing seriously damaged images, but it has bad performances when the images have the abundant structure information. The dual optimization image repair algorithm based on the linear structure and the optimal texture is proposed. The algorithm uses the double-constraint sparse model to reconstruct the missed information in large area in order to improve the clarity of repaired images. After adopting the preference of Criminisi priority, the image repair algorithm of self-similarity characteristics is proposed to improve the fault and fuzzy distortion phenomena in the repaired image. The results show that the proposed algorithm has more clarity in the image texture and structure and better effectiveness, and the peak signal-to-noise ratio of the repaired images by proposed algorithm is superior to that by other algorithms.

Keywords

image restoration / linear structure / texture information / iteration / sparse representation

References

[1] BertalmioM, SapiroG, CasellesV. Image inpainting [C]. Proceedings of International Conference on Computer Graphics and Interactive Techniques. New Orleans, Louisiana, USA, 2000417-424

[2] ChanT F, ShenJ H. Non-texture inpainting by curvature-driven diffusions (CDD) [J]. Journal of Visual Communication and Image Representation, 2001, 12(4): 436-449

[3] ChanT F, ShenJ H. Mathematical models for local non-texture inpainting [J]. SIAM Journal of Applied Mathematics, 2001, 62(3): 1019-1043

[4] CriminisiA, PerezP, ToyamaK. Region filling and object removal by exemplar-based image inpainting [J]. IEEE Transactions on Image Processing, 2004, 13(9): 1200-1212

[5] RaneS D, SapiroG, BertalmioM. Structure and texture filling-inof missing image blocks in wireless transmission and compression applications [J]. IEEE Transactions on Image Processing, 2003, 12(3): 296-303

[6] YamauchiH, HaberJ, SeidelH P. Image restoration using multiresolution texture synthesis [C]. Proceedings of Computer Graphics International Conference (CGI. 2003). Tokyo, Japan, 20031530-1552

[7] KangJ-l, TangX-h, RenShu. Image inpainting by structural constraints and sample sparse representation [J]. Journal of Image Graphics, 2013, 18(11): 1425-1434

[8] LiS T, ZhaoM. Image inpainting with salient structure completion and texture propagation [J]. Pattern Recognition Letters, 2011, 32(9): 1256-1266

[9] FanG-p, HeH-j, ChenF, ZhaiD-h, RenQ, NuoBu. An image inpainting algorithm based on local properties [J]. Journal of Optoelectronics Laser, 2012, 23(12): 2410-2417

[10] FlorinabelD J, JulietS E, SadasivamV. Combined frequency and spatial domain-based patch propagation for image completion [J]. Computers and Graphics, 2011, 35(6): 1051-1058

[11] CriminisiA, PerezP, ToyamaK. Object removal by exemplar-based inpainting [C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003, Wisconsin, USA, Monona Terrace Convention Center Madison: 18-20

[12] XuZ-b, SunJian. Image inpainting by patch propagation using patch sparsity [J]. IEEE Transactions on Image Processing, 2010, 19(5): 1153-1165

[13] WuX-j, LiG-qing. Large scale image inpainting based on exemplar and structure information [J]. Acta Electronica Sinica, 2012, 40(8): 1509-1514

[14] ShiJ-g, QiChun. An image inpainting algorithm based on sparse modeling with double constraints [J]. Journal of Xi’an Jiaotong University, 2011, 46(2): 6-10

[15] EsedogluS, ShenJ H. Digital inpainting based on the Mumford-Shah-Euler image model [J]. European Journal on Applied Mathematics, 2002, 13(4): 353-370

[16] HuZ-p, LiuW, XuC-qian. Iterative image inpainting using sparse constraint with local adaptive learned dictionary and informational priority selected diffusion [J]. Chinese Journal of Scientific Instrument, 2010, 31(3): 600-605

[17] YangX-l, HuangF, WangJ-ming. Modified image analytical solutions for ground displacement using [J]. Journal of Central South University of Technology, 2011, 18(3): 859-865

[18] LiuL-x, TanG-z, SolimanM S. Color image segmentation using mean shift and improved ant clustering [J]. Journal of Central South University, 2012, 19(4): 1040-1048

[19] ZhangY, SunZ-x, YaoWei. Image completion based on direction empirical mode decomposition [J]. Acta Electronica Sinica, 2010, 38(2): 257-262

[20] ChenX-d, ZhuX-lin. A weighted matching image restoration algorithm based on modified priority [J]. Journal of Hefei University of Technology, 2013, 36(1): 113-118