首页 > 论文 > 激光与光电子学进展 > 57卷 > 22期(pp:221015--1)

基于Gabor变换和组稀疏表示的敦煌壁画修复算法

Algorithm for Dunhuang Mural Inpainting Based on Gabor Transform and Group Sparse Representation

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

在敦煌壁画修复过程中,初始字典的随机选取易陷入局部最优,仅以颜色欧氏距离作为图像块分组标准会导致图像修复后易出现结构模糊和线条不连续等问题。针对以上问题,提出了一种基于Gabor变换和组稀疏表示的敦煌壁画修复算法。首先,采用互信息作为图像块分组准则,并建立相似结构组,这使得组稀疏表示更加合理;然后,通过Gabor小波变换对相似结构组进行特征信息提取,并结合PCA降维的方式得到初始化结构组的特征字典,避免了字典初始化随机选取的不足;最后,采用奇异值SVD分解和分裂Bregman迭代优化方法对结构组字典和稀疏系数进行学习并完成壁画图像的修复。实验结果表明,相比于其他对比算法,所提方法取得了较好的主客观修复效果。

Abstract

In the process of Dunhuang mural restoration, dictionary initialized random selection falls into local optimum easily and only the color Euclidean distance is used as the standard for image block grouping, which leads to the problems such as structure blur and line discontinuity after image restoration. An algorithm for Dunhuang mural inpainting based on Gabor transform and group sparse representation is proposed in this paper. First, the similar structure group is established using mutual information as the criterion of image block grouping, which makes group sparse representation more reasonable. Second, the Gabor wavelet transform is used to extract the feature information of similar structure groups, and the feature dictionary of the structure group is initialized by means of PCA dimension reduction, which can avoid the disadvantage of dictionary initialized random selection. Finally, the SVD decomposition and the split Bregman iteration method are used to learn the structure group dictionary and the sparse coefficients to complete the mural image restoration. The experimental results show that, compared with the other algorithms, the algorithm proposed in this paper has achieved good subjective and objective restoration effects.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP391.4

DOI:10.3788/LOP57.221015

所属栏目:图像处理

基金项目:教育部人文社会科学研究青年基金;

收稿日期:2020-03-19

修改稿日期:2020-04-20

网络出版日期:2020-11-01

作者单位    点击查看

陈永:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070甘肃省人工智能与图形图像处理工程研究中心, 甘肃 兰州 730070
陶美风:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
艾亚鹏:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
陈锦:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070

联系人作者:陈永(edukeylab@126.com)

备注:教育部人文社会科学研究青年基金;

【1】Wang J Y. The investigation on the current condition of mogao grottoes and the classification of diseases in exist Dunhuang Research[J]. 0, 2005(6): 113-117.
王进玉. 敦煌莫高窟洞窟现状调查与病害分类 敦煌研究[J]. 0, 2005(6): 113-117.

【2】Li L, Gao R W, Mei S L, et al. Mural image de-noising based on Shannon-Cosine wavelet precise integration method [J]. Journal of Zhejiang University (Sciences Edition). 2019, 46(3): 279-287.
李丽, 高若婉, 梅树立, 等. 基于Shannon-Cosine小波精细积分法的壁画降噪修复方法 [J]. 浙江大学学报(理学版). 2019, 46(3): 279-287.
Li L, Gao R W, Mei S L, et al. Mural image de-noising based on Shannon-Cosine wavelet precise integration method [J]. Journal of Zhejiang University (Sciences Edition). 2019, 46(3): 279-287.
李丽, 高若婉, 梅树立, 等. 基于Shannon-Cosine小波精细积分法的壁画降噪修复方法 [J]. 浙江大学学报(理学版). 2019, 46(3): 279-287.

【3】Bertalmio M, Sapiro G, Caselles V, et al. Image inpainting[C]//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques , July 23-28, 2000, New Orleans, LA, USA. New York: , 2000, 417-424.

【4】Shen J H, Chan T F. Mathematical models for local nontexture inpaintings [J]. SIAM Journal on Applied Mathematics. 2002, 62(3): 1019-1043.

【5】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.

【6】Criminisi A, Pérez P, Toyama K. Region filling and object removal by exemplar-based image inpainting [J]. IEEE Transactions on Image Processing. 2004, 13(9): 1200-1212.

【7】Chen Y, Ai Y P, Chen J. Dunhuang mural inpainting algorithm based on information entropy and structural characteristics [J]. Laser & Optoelectronics Progress. 2020, 57(12): 121020.
陈永, 艾亚鹏, 陈锦. 基于信息熵和结构特性的敦煌壁画修复算法 [J]. 激光与光电子学进展. 2020, 57(12): 121020.

【8】Bittens S, Plonka G. Real sparse fast DCT for vectors with short support [J]. Linear Algebra and Its Applications. 2019, 582: 359-390.Bittens S, Plonka G. Real sparse fast DCT for vectors with short support [J]. Linear Algebra and Its Applications. 2019, 582: 359-390.

【9】Wang H C, Tao C H, Chen S C, et al. High-precision seismic data reconstruction with multi-domain sparsity constraints based on curvelet and high-resolution Radon transforms [J]. Journal of Applied Geophysics. 2019, 162: 128-137.Wang H C, Tao C H, Chen S C, et al. High-precision seismic data reconstruction with multi-domain sparsity constraints based on curvelet and high-resolution Radon transforms [J]. Journal of Applied Geophysics. 2019, 162: 128-137.

【10】Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation [J]. IEEE Transactions on Signal Processing. 2006, 54(11): 4311-4322.

【11】Dong W S, Zhang L, Shi G M, et al. Nonlocally centralized sparse representation for image restoration [J]. IEEE Transactions on Image Processing. 2013, 22(4): 1620-1630.

【12】Zhang J, Zhao D B, Gao W. Group-based sparse representation for image restoration [J]. IEEE Transactions on Image Processing. 2014, 23(8): 3336-3351.

【13】Li J, et al. Hyperspectral image classification via multiple-feature-based improved sparse representation [J]. Acta Optica Sinica. 2019, 39(5): 0528004.
李非燕, 霍宏涛, 李静, 等. 基于多特征和改进稀疏表示的高光谱图像分类 [J]. 光学学报. 2019, 39(5): 0528004.

【14】Lou X X, Tang X H, Zhang Y. Sparsity image inpainting algorithm based on similar patch group [J]. Journal of Image and Graphics. 2019, 24(7): 1055-1066.
楼幸欣, 唐向宏, 张越. 相似匹配块组的稀疏表示图像修复 [J]. 中国图象图形学报. 2019, 24(7): 1055-1066.
Lou X X, Tang X H, Zhang Y. Sparsity image inpainting algorithm based on similar patch group [J]. Journal of Image and Graphics. 2019, 24(7): 1055-1066.
楼幸欣, 唐向宏, 张越. 相似匹配块组的稀疏表示图像修复 [J]. 中国图象图形学报. 2019, 24(7): 1055-1066.

【15】Research advances on dictionary learning models, algorithms and applications [J]. Acta Automatica Sinica. 2015, 41(2): 240-260.
练秋生, 石保顺, 陈书贞. 字典学习模型、算法及其应用研究进展 [J]. 自动化学报. 2015, 41(2): 240-260.

【16】Gao C Y, Xu X E, Luo Y M, et al. Object image inpainting based on sparse representation [J]. Chinese Journal of Computers. 2019, 42(9): 1953-1965.
高成英, 徐仙儿, 罗燕媚, 等. 基于稀疏表示的物体图像修复 [J]. 计算机学报. 2019, 42(9): 1953-1965.

【17】Cheng C, Da F P, Wang C X, et al. Pose invariant face recognition using maximum Gabor similarity based on Lucas-Kanade algorithm [J]. Acta Optica Sinica. 2019, 39(7): 0715005.
程超, 达飞鹏, 王辰星, 等. 基于Lucas-Kanade算法的最大Gabor相似度大姿态人脸识别 [J]. 光学学报. 2019, 39(7): 0715005.

引用该论文

Chen Yong,Tao Meifeng,Ai Yapeng,Chen Jin. Algorithm for Dunhuang Mural Inpainting Based on Gabor Transform and Group Sparse Representation[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221015

陈永,陶美风,艾亚鹏,陈锦. 基于Gabor变换和组稀疏表示的敦煌壁画修复算法[J]. 激光与光电子学进展, 2020, 57(22): 221015

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF