改进的块匹配五台山壁画修复算法
|
摘要
针对五台山壁画破损区域形状不规则、大小不均匀,采用Criminisi算法修复时易出现错误填充的问题,提出一种改进的块匹配五台山壁画数字化修复算法.首先在计算优先权,除置信度与数据项之外引入分散度项,确保信息最丰富的块被优先修复;然后结合图像块结构的整体性将协方差因子引入相似度计算中,以减少错误填充率.对五台山破损壁画进行数字化修复的实验结果表明,该算法较好地解决了Criminisi算法的错误填充问题.
In order to avoid the error filling problem caused by irregular shape and uneven size of damaged areas in Wutai Mountain murals, a novel block matching algorithm was proposed. First, a dispersion item was introduced in the priority calculation process except for a confidence coefficient and a data item originally, which might guarantee that the most informative block would be inpainted primarily. Then, the covariance factor denoting structural integrity among image blocks was adopted in similarity calculation to reduce error filling rate. Experimental results on Wutai Mountain murals illustrate that the proposed algorithm can solve the error filling problem of the original Criminisi algorithm effectively.
In order to avoid the error filling problem caused by irregular shape and uneven size of damaged areas in Wutai Mountain murals, a novel block matching algorithm was proposed. First, a dispersion item was introduced in the priority calculation process except for a confidence coefficient and a data item originally, which might guarantee that the most informative block would be inpainted primarily. Then, the covariance factor denoting structural integrity among image blocks was adopted in similarity calculation to reduce error filling rate. Experimental results on Wutai Mountain murals illustrate that the proposed algorithm can solve the error filling problem of the original Criminisi algorithm effectively.
引文
[1]Pan Yunhe,Lu Dongming.Digital protection and restoration of Dunhuang mural[J].Journal of System Simulation,2003,15(3):310-314(in Chinese)(潘云鹤,鲁东明.古代敦煌壁画的数字化保护与修复[J].系统仿真学报,2003,15(3):310-314)
[2]Yang Xiaoping,Wang Shuwen.Dunhuang mural inpainting in intricate disrepaired region based on improvement of priority algorithm[J].Journal of Computer-Aided Design&Computer Graphics,2011,23(2):284-289(in Chinese)(杨筱平,王书文.基于优先权改进算法的敦煌壁画复杂破损区域修复[J].计算机辅助设计与图形学学报,2011,23(2):284-289)
[3]Yang Xiaoping,Wang Shuwen.Dunhuang mural inpainting based on Markov random field sampling[J].Journal of Computer Applications,2010,30(7):1835-1837+1840(in Chinese)(杨筱平,王书文.基于马尔可夫采样的敦煌壁画修复[J].计算机应用,2010,30(7):1835-1837+1840)
[4]Shen Jingni,Wang Huiqin,Wu Meng,et al.Tang dynasty tomb murals inpainting algorithm of MCA decomposition[J].Journal of Frontiers of Computer Science&Technology,2017,11(11):1826-1836(in Chinese)(申婧妮,王慧琴,吴萌,等.MCA分解的唐墓室壁画修复算法[J].计算机科学与探索,2017,11(11):1826-1836)
[5]Bertalmio M,Vese L,Sapiro G,et al.Simultaneous structure and texture image inpainting[J].IEEE Transactions on Image Processing,2003,12(8):882-889
[6]Smith L N,Elad M.Improve dictionary learning:multiple dictionary updates and coefficient reuse[J].IEEE Signal Processing Letters,2013,20(1):79-82
[7]Chan T F,Shen J H.Nontexture inpainting by curvature-driven diffusions[J].Journal of Visual Communication and Image Representation,2001,12(4):436-449
[8]Shen J H,Chan T F.Mathematical models for local nontexture inpaintings[J].SIAM Journal on Applied Mathematics,2002,62(3):1019-1043
[9]Bertalmio M,Sapiro G,Caselles V,et al.Image inpainting[C]//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM Press,2000:417-424
[10]Criminisi A,Perez P,Toyama K.Object removal by exemplar-based inpainting[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2003,2:721-728
[11]Criminisi A,Perez P,Toyama K.Region filling and object removal by exemplar-based inpainting[J].IEEE Transactions on Image Processing,2004,13(9):1200-1212
[12]Starck J L,Elad M,Donoho D.Image decomposition via the combination of sparse representation and a variational approach[J].IEEE Transactions on Image Processing,2005,14(10):1570-1582
[13]Zhu Xuan,Zhang Xufeng,Li Qiuju,et al.Image inpainting method based on sparse descomposition[J].Computer Science,2016,43(1):294-297(in Chinese)(祝轩,张旭峰,李秋菊,等.基于稀疏分解的图像修复方法[J].计算机科学,2016,43(1):294-297)
[14]Bertalmio M,Bertozzi A L,Sapiro G.Navier-stokes,fluid dynamics,and image and video inpainting[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2001,1:355-362
[15]Li Xufeng,Wang Jing,Liu Hongmin,et al.Image inpainting using feature precedence and patch matching[J].Journal of Computer-Aided Design&Computer Graphics,2016,28(7):1131-1137(in Chinese)(李旭峰,王静,刘红敏,等.特征优先块匹配图像修复算法[J].计算机辅助设计与图形学学报,2016,28(7):1131-1137)
[16]Wang J,Lu K,Pan D R,et al.Robust object removal with an exemplar-based image inpainting approach[J].Neurocomputing,2014,123(10):150-155
[17]Zeng Jiexian,Wang Can.Image completion based on redefined priority and image division[J].Journal of Image and Graphics,2017,22(9):1183-1193(in Chinese)(曾接贤,王璨.基于优先权改进和块划分的图像修复[J].中国图象图形学报,2017,22(9):1183-1193)
[18]He K M,Sun J.Image completion approaches using the statistics of similar patches[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(12):2423-2435
[19]Zhou H L,Zheng J M.Adaptive patch size determination for patch-based image completion[C]//Proceedings of the 17th IEEE International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2010:421-424
[20]Ruzic T,Pizurica A.Context-aware patch-based image inpainting using Markov random field modeling[J].IEEE Transactions on Image Processing,2014,24(1):444-456
[21]Li Mengxue,Zhai Donghai,Meng Hongyue,et al.Image inpainting algorithm for partitioning feature subregions[J].Journal of Computer Applications,2017,37(12):3541-3546(in Chinese)(李梦雪,翟东海,孟红月,等.划分特征子区域的图像修复算法[J].计算机应用,2017,37(12):3541-3546)
[22]Yang C,Lu X,Lin Z,et al.High-resolution image inpainting using multi-scale neural patch synthesis[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2017:4076-4084
[23]Iizuka S,Simo-Serra E,Ishikawa H.Globally and locally consistent image completion[J].ACM Transactions on Graphics,2017,36(4):1-14
[2]Yang Xiaoping,Wang Shuwen.Dunhuang mural inpainting in intricate disrepaired region based on improvement of priority algorithm[J].Journal of Computer-Aided Design&Computer Graphics,2011,23(2):284-289(in Chinese)(杨筱平,王书文.基于优先权改进算法的敦煌壁画复杂破损区域修复[J].计算机辅助设计与图形学学报,2011,23(2):284-289)
[3]Yang Xiaoping,Wang Shuwen.Dunhuang mural inpainting based on Markov random field sampling[J].Journal of Computer Applications,2010,30(7):1835-1837+1840(in Chinese)(杨筱平,王书文.基于马尔可夫采样的敦煌壁画修复[J].计算机应用,2010,30(7):1835-1837+1840)
[4]Shen Jingni,Wang Huiqin,Wu Meng,et al.Tang dynasty tomb murals inpainting algorithm of MCA decomposition[J].Journal of Frontiers of Computer Science&Technology,2017,11(11):1826-1836(in Chinese)(申婧妮,王慧琴,吴萌,等.MCA分解的唐墓室壁画修复算法[J].计算机科学与探索,2017,11(11):1826-1836)
[5]Bertalmio M,Vese L,Sapiro G,et al.Simultaneous structure and texture image inpainting[J].IEEE Transactions on Image Processing,2003,12(8):882-889
[6]Smith L N,Elad M.Improve dictionary learning:multiple dictionary updates and coefficient reuse[J].IEEE Signal Processing Letters,2013,20(1):79-82
[7]Chan T F,Shen J H.Nontexture inpainting by curvature-driven diffusions[J].Journal of Visual Communication and Image Representation,2001,12(4):436-449
[8]Shen J H,Chan T F.Mathematical models for local nontexture inpaintings[J].SIAM Journal on Applied Mathematics,2002,62(3):1019-1043
[9]Bertalmio M,Sapiro G,Caselles V,et al.Image inpainting[C]//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques.New York:ACM Press,2000:417-424
[10]Criminisi A,Perez P,Toyama K.Object removal by exemplar-based inpainting[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2003,2:721-728
[11]Criminisi A,Perez P,Toyama K.Region filling and object removal by exemplar-based inpainting[J].IEEE Transactions on Image Processing,2004,13(9):1200-1212
[12]Starck J L,Elad M,Donoho D.Image decomposition via the combination of sparse representation and a variational approach[J].IEEE Transactions on Image Processing,2005,14(10):1570-1582
[13]Zhu Xuan,Zhang Xufeng,Li Qiuju,et al.Image inpainting method based on sparse descomposition[J].Computer Science,2016,43(1):294-297(in Chinese)(祝轩,张旭峰,李秋菊,等.基于稀疏分解的图像修复方法[J].计算机科学,2016,43(1):294-297)
[14]Bertalmio M,Bertozzi A L,Sapiro G.Navier-stokes,fluid dynamics,and image and video inpainting[C]//Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2001,1:355-362
[15]Li Xufeng,Wang Jing,Liu Hongmin,et al.Image inpainting using feature precedence and patch matching[J].Journal of Computer-Aided Design&Computer Graphics,2016,28(7):1131-1137(in Chinese)(李旭峰,王静,刘红敏,等.特征优先块匹配图像修复算法[J].计算机辅助设计与图形学学报,2016,28(7):1131-1137)
[16]Wang J,Lu K,Pan D R,et al.Robust object removal with an exemplar-based image inpainting approach[J].Neurocomputing,2014,123(10):150-155
[17]Zeng Jiexian,Wang Can.Image completion based on redefined priority and image division[J].Journal of Image and Graphics,2017,22(9):1183-1193(in Chinese)(曾接贤,王璨.基于优先权改进和块划分的图像修复[J].中国图象图形学报,2017,22(9):1183-1193)
[18]He K M,Sun J.Image completion approaches using the statistics of similar patches[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(12):2423-2435
[19]Zhou H L,Zheng J M.Adaptive patch size determination for patch-based image completion[C]//Proceedings of the 17th IEEE International Conference on Image Processing.Los Alamitos:IEEE Computer Society Press,2010:421-424
[20]Ruzic T,Pizurica A.Context-aware patch-based image inpainting using Markov random field modeling[J].IEEE Transactions on Image Processing,2014,24(1):444-456
[21]Li Mengxue,Zhai Donghai,Meng Hongyue,et al.Image inpainting algorithm for partitioning feature subregions[J].Journal of Computer Applications,2017,37(12):3541-3546(in Chinese)(李梦雪,翟东海,孟红月,等.划分特征子区域的图像修复算法[J].计算机应用,2017,37(12):3541-3546)
[22]Yang C,Lu X,Lin Z,et al.High-resolution image inpainting using multi-scale neural patch synthesis[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2017:4076-4084
[23]Iizuka S,Simo-Serra E,Ishikawa H.Globally and locally consistent image completion[J].ACM Transactions on Graphics,2017,36(4):1-14