A Coupled Non-local Total Variation Algorithm for Image Colorization
-
摘要: 基于局部算子的全变差(TV)模型在对纹理图像着色时，会出现颜色扩散不均匀，着色范围区域较小等问题。为了解决上述问题，该文提出基于非局部算子的耦合全变差图像着色模型，结合交替方向乘子法(ADMM)，设计出相应的数值求解算法，并给出该算法的收敛性结果。该模型充分利用像素邻域亮度之间的相似性进行颜色扩散，能有效避免仅利用亮度边缘信息进行局部扩散导致颜色扩散不均匀的问题。数值实验结果表明，该模型在快速着色的同时，能有效解决颜色在纹理等细节处扩散不均匀的问题。Abstract: The traditional Total Variation (TV) model based on local operators for texture image colorization has some problems, such as inhomogeneous color diffusion, small coloring ranges and so on. In order to solve these problems, a coupled total variation model based on nonlocal operators is presented for image colorization, and the correspond numerical algorithm is designed to solve the model by incorporating the Alternating Direction Method of Multipliers (ADMM), and the convergence result of the algorithm is given. The proposed model makes full use of the similarity between the brightness of the pixel areas to perform color diffusion, which can effectively avoid the problem of inhomogeneous color diffusion due to local diffusion only using the brightness edge information. The experimental results are given to show that the model can effectively solve the problem of inhomogeneous color diffusion at textures and other details while fast colorizing.
-
表 2 图3图像着色后的PSNR值及MSE值的比较
图像 模型 PSNR值 MSE值 第1排 Levin模型[4] 23.69 0.0043 Kang模型[8] 22.74 0.0053 金模型[9] 25.46 0.0028 本文模型 25.82 0.0026 第2排 Levin模型[4] 24.63 0.0034 Kang模型[8] 22.10 0.0062 金模型[9] 27.52 0.0018 本文模型 26.91 0.0020 第3排 Levin模型[4] 24.87 0.0033 Kang模型[8] 21.71 0.0067 金模型[9] 25.21 0.0030 本文模型 26.04 0.0025 第4排 Levin模型[4] 24.85 0.0033 Kang模型[8] 21.04 0.0079 金模型[9] 25.66 0.0027 本文模型 25.87 0.0026 
下载: 导出CSV
-
PAUL S, BHATTACHARYA S, and GUPTA S. Spatiotemporal colorization of video using 3D steerable pyramids[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(8): 1605–1619 doi: 10.1109/TCSVT.2016.2539539 METE S P and DHAIT A S. A colorization algorithm with artifacts suppression on real time video[J]. International Journal of Science and Research, 2016, 5(4): 1126–1131 doi: 10.21275/v5i4.nov162748 HORIUCHI T. Colorization algorithm using probabilistic relaxation[J]. Image and Vision Computing, 2004, 22(3): 197–202 doi: 10.1016/j.imavis.2003.08.004 LEVIN A, LISCHINSKI D, and WEISS Y. Colorization using optimization[C]. Proceedings of ACM SIGGRAPH 2004, New York, USA, 2004: 689–694. SAPIRO G. Inpainting the colors[C]. IEEE International Conference on Image Processing, Genova, Italy, 2005: 6987–701. YATZIV L and SAPIRO G. Fast image and video colorization using chrominance blending[J]. IEEE Transactions on Image Processing, 2006, 15(5): 1120–1129 doi: 10.1109/tip.2005.864231 TENG Shenghua, CHEN An’jun and ZOU Mouyan. Colorization using Laplace equation[J].Journal of Image and Graphics, 2006, 11(4): 103–106 doi: 10.1002/qua.560410608 KANG S H and MARCH R. Variation models for image colorization via chromaticity and brightness decomposition[J]. IEEE Transactions on Image Processing, 2007, 16(9): 2251–2261 doi: 10.1109/tip.2007.903257 金正猛, 周晨. 基于耦合全变差的快速图像着色算法[J]. 电子学报, 2016, 44(10): 2364–2369 doi: 10.3969/j.issn.0372-2112.2016.10.012JIN Zhengmeng and ZHOU Chen. A fast coupled total variation algorithm for image colorization[J]. Acta Electronica Sinica, 2016, 44(10): 2364–2369 doi: 10.3969/j.issn.0372-2112.2016.10.012 GILBOA G and OSHER S. Nonlocal operators with applications to image processing[J]. Multiscale Model&Simul, 2009, 7(3): 1005–1028 doi: 10.1137/070698592 ZHU Wei, CHAYES V, TIARD A, et al. Unsupervised classification in hyperspectral imagery with nonlocal total variation and primal dual hybrid gradient algorithm[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(5): 2786–2798 doi: 10.1109/tgrs.2017.2654486 陆文琪, 端金鸣, 魏伟波, 等. 基于非局部CTV-L1模型的大破损彩色纹理图像修复[J]. 计算机应用研究, 2016, 33(8): 2524–2529 doi: 10.3969/j.issn.1001-3965.2016.08.063LU Wenqi, DUAN Jinming, WEI Weibo, et al. Large broken color texture image inpainting using non-local CTV-L1 model[J]. Application Research of Computers, 2016, 33(8): 2524–2529 doi: 10.3969/j.issn.1001-3965.2016.08.063 LI Zhi, MALGOUYRES F, and ZENG Tieyong. Regularized non-local total variation and application in image restoration[J]. Journal of Mathematical Imaging and Vision, 2017, 59(2): 296–317 doi: 10.1007/s10851-017-0732-6 BUADES A, COLL B, and MOREL J M. A review of image denoising algorithms, with a new one[J]. Multiscale Model&Simul, 2005, 4(2): 490–530 doi: 10.1137/040616024 KOJU R and JOSHI S R. Comparative analysis of color image watermarking technique in RGB, YUV, and YCbCr Color Channels[J]. Nepal Journal of Science and Technology, 2015, 15(2): 133–140 doi: 10.3126/njst.v15i2.12130 CHELALI F Z, CHERABIT N, and DJERADI A. Face recognition system using skin detection in RGB and YCbCr color space[C]. World Symposium on Web Application & Networking, Sousse, Tunisia, 2015: 1–7. BOYD S, PARINKH N, CHU E, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers[J]. Foundations and Trends in Machine Learning, 2010, 3(1): 1–122 doi: 10.1561/ 2200000016 GLOWINSKI R and MARROCCO A. Sur lapproximation parele-ments finis dordreun, et la resolution par penalisation-du-alite dune classe de problemes de Dirichlet nonlineaires[J]. Revue Francaise D’Automatique,Informatique,Re-cherch Operationnel, 1975, 9(R2): 41–76 doi: 10.1051/m2an/197509r200411 -
下载:
图(3) / 表(2)
计量
- 文章访问数: 1702
- HTML全文浏览量: 529
- PDF下载量: 56
- 被引次数: 0
