Wavelet Inpainting Based on Tensor Diffusion
-
摘要: 在JPEG2000图像压缩标准中,有损传输过程中的小波系数的丢失将严重影响接收端图像的质量.为了修复丢失的或被损坏的小波系数,本文提出了一种基于张量扩散的小波域修复模型(TDWI),该混合模型将结构自适应各向异性正则与小波表示结合起来.同时推导该模型对应的Euler-Lagrange方程,并据此来分析它在像素域的几何正则性能.由于在正则项中采用了矩阵值的结构张量,该模型的扩散核的形状随着图像的局部结构特征(包括尖锐边缘、角点和各向同性区域)自适应地变化.与已有的小波域修复模型相比,本文所提模型能更自适应地、更准确地控制像素域的几何正则性,并对噪声有更强的鲁棒性.另外,本文采用了一个更加有效且适合的数值实现方法来进一步改善所提模型的修复性能.最后,给出了各种丢失情形下的实验结果来表明该模型在小波域修复性能和抗噪性能等方面的优越性.Abstract: Due to the lossy transmission in the JPEG2000 image compression standard, the loss of wavelet coefficients heavily affects the quality of the received image. In this paper, we propose a novel wavelet inpainting model based on tensor diffusion (TDWI) to restore the missing or damaged wavelet coefficients. A hybrid model is built by combining structure-adaptive anisotropic regularization with wavelet representation. Its associated Euler-Lagrange equation is also given for analyzing its regularity performance. Owing to the matrix representation of the structure tensor in the regularization term, the shape of diffusion kernel changes adaptively according to the image features, including sharp edges, corners and homogeneous regions. Compared with existing wavelet inpainting models, the proposed one can control more adaptively and accurately the geometric regularity in the image and exhibits better robustness to noise. In addition, an effective and proper numerical scheme is adopted to improve the computation. Experimental results on a variety of loss scenarios are given to demonstrate the advantages of our proposed model.
-
Key words:
- Wavelet /
- inpainting /
- structure tensor /
- diffusion /
- anisotropic /
- regularization
-
[1] Xiong X S, Zhao H, Tang C J. Image inpainting used in specific target replacement. In: Proceedings of the 2008 IEEE International Conference on Information and Automation. Changsha, China: IEEE, 2008. 354-356 [2] Tauber Z, Li Z N, Drew M S. Review and preview: disocclusion by inpainting for image-based rendering. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2007, 37(4): 527-540 [3] Wighton P, Lee T K, Atkins M S. Dermascopic hair disocclusion using inpainting. In: Proceedings of the 2008 International Society for Optics and Photonics. San Diego, CA, USA: SPIE, 2008. 691427-1-8 [4] Ma M Y, Au O C, Chan S H G, Sun M T. Edge-directed error concealment. IEEE Transactions on Circuits and Systems for Video Technology, 2010, 20(3): 382-395 [5] Lakshman H, Ndjiki-Nya P, Koppel M, Doshkov D, Wiegand T. An automatic structure-aware image extrapolation applied to error concealment. In: Proceedings of the 16th IEEE International Conference on Image Processing. Cairo, Egypt: IEEE, 2009. 913-916 [6] Wu G L, Chen C Y, Chien S Y. Algorithm and architecture design of image inpainting engine for video error concealment applications. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(6): 792-803 [7] Chan T F, Shen J H, Zhou H M. Total variation wavelet inpainting. Journal of Mathematical Imaging and Vision, 2006, 25(1): 107-125 [8] Sakurai M, Kiriyama S, Goto T, Hirano S. Fast algorithm for total variation minimization. In: Proceedings of the 18th IEEE International Conference on Image Processing. Brussels, Belgium: IEEE, 2011. 1461-1464 [9] Li S L, Wang H Q. Image inpainting using curvature-driven diffusions based on p-Laplace operator. In: Proceedings of the 4th International Conference on Innovative Computing, Information and Control. Kaohsiung, Taiwan, China: IEEE, 2009. 323-325 [10] Zhang H Y, Peng Q C, Wu Y D. Wavelet inpainting based on p-Laplace operator. Acta Automatica Sinica, 2007, 33(5): 546-549 [11] Yau A C, Tai X C, Ng M K. L0-norm and total variation for wavelet inpainting. In: Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision. Voss, Norway: Springer, 2009. 539-551 [12] Hadji M L, Maouni M, Nouri F Z. A wavelet inpainting by a Tixotrop model. In: Proceedings of the 14th International conference on information visualization. London, United Kingdom: IEEE, 2010. 559-563 [13] Zhang X Q, Chan T F. Wavelet inpainting by nonlocal total variation. Inverse Problems and Imaging, 2010, 4(1): 191- 210 [14] Brox T, Weickert J, Burgeth B, Mrázek P. Nonlinear structure tensors. Image and Vision Computing, 2006, 24(1): 41- 55 [15] Yoo H, Kim B, Sohn K. Coherence enhancing diffusion filtering based on connected component analysis structure tensor. In: Proceedings of the 6th IEEE Conference on Industrial Electronics and Applications. Beijing, China: IEEE, 2011. 271-274 [16] Hahn J, Lee C O. A nonlinear structure tensor with the diffusivity matrix composed of the image gradient. Journal of Mathematical Imaging and Vision, 2009, 34(2): 137-151 [17] Wang Y K, Lu B B, Miao C L. Image fusion based on nonlinear structure tensor. In: Proceedings of the 2011 International Conference on Multimedia Technology. Hangzhou, China: IEEE, 2011. 6390-6393 [18] Gao C Q, Tian J W, Wang P. Generalised-structure-tensor-based infrared small target detection. Electronics Letters, 2008, 44(23): 1349-1351 [19] Rane S D, Sapiro G, Bertalmio M. Structure and texture filling-in of missing image blocks in wireless transmission and compression applications. IEEE Transactions on Image Processing, 2003, 12(3): 296-303 [20] Chan R H, Wen Y W, Yip A M. A fast optimization transfer algorithm for image inpainting in wavelet domains. IEEE Transactions on Image Processing, 2009, 18(7): 1467-1476 [21] Zhang Wen-Juan, Feng Xiang-Chu, Wang Xu-Dong. Mumford-Shah model based on weighted total generalized variation. Acta Automatica Sinica, 2012, 38(12): 1913-1922 (in Chinese)
点击查看大图
计量
- 文章访问数: 1675
- HTML全文浏览量: 55
- PDF下载量: 1414
- 被引次数: 0