基于低秩表示的图像修复方法
PDF下载 (662)刘慧青,赵杰煜 *,常俊生.基于低秩表示的图像修复方法[J].宁波大学学报(理工版),2017,30(3):24-29.DOI:
LIU Hui-qing,ZHAO Jie-yu *,CHANG Jun-sheng.Image inpainting method based on low-rank representation[J].Journal of Ningbo University(Natural Science & Engineering Edition),2017,30(3):24-29.DOI:
| Title: | Image inpainting method based on low-rank representation |
| 作者: | 刘慧青, 赵杰煜 *, 常俊生 |
| Author(s): | LIU Hui-qing, ZHAO Jie-yu *, CHANG Jun-sheng |
| 关键词: | 低秩表示; 稀疏表示; 图像修复; 强制校正 |
| Keywords: | low-rank representation; sparse representation; image inpainting; mandatory revising |
| 分类号: | TP391.4 |
| 文献标识码: | A |
| 摘要: | 现实场景中, 存在很多原因导致所获图像信息并不完整, 其中会存在少许的破损, 这对基于此数据进行下一步的研究造成了障碍. 针对图像存在的破损问题, 提出一种基于低秩表示的图像修复方法. 通过图像的矩阵存储方式, 由稀疏理论获取其低秩表示, 提取到图像的全局特征. 根据所获的低秩表示, 结合缺损区域与其相邻区域的相似性, 将缺损区域逐步缩小, 并对缩小区域进行强制校正, 从而完成修复图像任务, 最后得到补全后的最终图像. 在二维图像上设计对比实验进行验证, 结果证明该方法在结构简单图修复、破损老照片修复、去除叠加文字以及大块物体移除等方面都具有良好的性能. 实验结果表明, 低秩表示在图像修复方面具有获取全局信息的优势, 修复效果良好. |
| Abstract: | The acquired images in reality may be incomplete or have some damages for one reason or other. The loss of information in these images makes these images less valuable or completely useless. To tackle these issues, an image inpainting method based on low rank representation is proposed. Image inpainting is implemented by extracting the global features through the image low-rank representation using the sparse theory. Several experiments are conducted on some images damaged by word, scratches and shade, which validate the efficiency of the proposed method. |
| 参考文献 /References: | [1] BERTALMIO M, SAPIRO G, CASELLES V, et al. Image inpainting[C]//Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, ACM Press/Addison Wesley Publishing Company, 2000:417- 424. [2] FIDANER I B. A Survey on variational image inpainting, texture synthesis and image completion[D]. Istanbul: Bogazici University, 2008. [3] 张红英, 彭启琮. 数字图像修复技术综述[J]. 中国图象图形学报, 2007, 12(1):1-10. [4] ELAD M. Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing[M]. New York: Springer Publishing Company, 2010:58-66. [5] 李志丹, 和红杰, 尹忠科, 等. 基于块结构稀疏度的自适应图像修复算法[J]. 电子学报, 2012, 41(3):549-554. [6] ELDAR Y, KUTYNIOK G. Compressed sensing: Theory and applications [J]. IEEE Transactions on Information Theory, 2012, 52(4):1289-1306. [7] MALLAT S G, ZHANG Z. Matching pursuits with time-frequency dictionaries[J]. IEEE Transactions on Signal Processing, 1993, 41(12):3397-3415. [8] UDELL M, HORN C, ZADEH R, et al. Generalized low rank models[J]. Foundations and Trends in Machine Learning, 2016, 9(1):1-118. [9] PENG X, YAN R, ZHAO B, et al. Fast low rank representation based spatial pyramid matching for image classification[J]. Knowledge Based Systems, 2015, 90: 14-22. [10] ZHANG H, LIN Z, ZHANG C, et al. Robust latent low rank representation for subspace clustering[J]. Neuro- computing, 2014, 145:369-373. [11] CAI T T, ZHANG A. Sparse representation of a polytope and recovery of sparse signals and low-rank matrices[J]. IEEE Transactions on Information Theory, 2014, 60(1): 122-132. [12] LIU G, LIN Z, YU Y. Robust subspace segmentation by low-rank representation[C]//Proceedings of the 27th International Conference on Machine Learning (ICML- 10), 2010: 663-670. [13] LIU G, LIN Z, YAN S, et al. Robust recovery of subspace structures by low-rank representation[J]. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2013, 35(1):171-184. [14] LU X, WANG Y, YUAN Y. Graph-regularized low-rank representation for destriping of hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(7):4009-4018. [15] CRIMINISI A, PEREZ P, TOYAMA K. Region filling and object removal by exemplar-based image inpainting [J]. IEEE Transactions on Image Processing, 2004, 13(9): 1200-1212 [16] 朱为, 李国辉. 基于自动结构延伸的图像修补方法[J]. 自动化学报, 2009, 35(8):1041-1047. [17] 张岩, 孙正兴, 姚伟. 基于方向经验模型分解的图像修复方法[J]. 电子学报, 2010, 38(2):257-262. [18] BUGEAU A, BERTALM?O M, CASELLES V, et al. A comprehensive framework for image inpainting[J]. IEEE Transactions on Image Processing, 2010, 19(10):2634- 2645. [19] SHEN B, HU W, ZHANG Y, et al. Image inpainting via sparse representation[C]//2009 IEEE International Confe- rence on Acoustics, Speech and Signal Processing, 2009: 697-700. [20] WANG Y X, ZHANG Y J. Image inpainting via weighted sparse non-negative matrix factorization[C]//18th IEEE International Conference on Image Processing, 2011:3409-3412. [21] XU Z, SUN J. Image inpainting by patch propagation using patch sparsity[J]. IEEE Transactions on Image Processing, 2010, 19(5):1153-1165. [22] ELHAMIFAR E, VIDAL R. Sparse subspace clustering [C]//IEEE Conference on Computer Vision & Pattern Recognition, 2009:2790-2797. [23] CAND?S E J, LI X, MA Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011, 58(3): 11. [24] FAZEL M. Matrix rank minimization with applications [D]. Palo Alto: Stanford University, 2002. [25] LIN Z, CHEN M, MA Y. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices[EB/OL]. [2016-08-15]. http://core.ac. uk/download/pdf/2148530.pdf. [26] CAI J F, CAND?S E J, SHEN Z. A singular value thresholding algorithm for matrix completion[J]. SIAM Journal on Optimization, 2010, 20(4):1956-1982. |
| 备注/Memo: | 收稿日期: 2016-12-13. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 国家自然科学基金（61571247）; 浙江省自然科学基金重点项目（LZ16F030001）; 浙江省国际科技合作专项（2013C24027）. 第一作者: 刘慧青（1991-）, 女, 安徽安庆人, 在读硕士研究生, 主要研究方向: 计算机视觉和图像处理. E-mail: hqing2010@163.com *通信作者: 赵杰煜（1965-）, 男, 浙江宁波人, 博士/教授, 主要研究方向: 图像图形、计算机视觉与机器学习. E-mail: zhao_jieyu@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
