计算机科学 ›› 2015, Vol. 42 ›› Issue (3): 271-273.doi: 10.11896/j.issn.1002-137X.2015.03.056
李秋菊,祝 轩,张旭峰,王 宁
LI Qiu-ju, ZHU Xuan, ZHANG Xu-feng and WANG Ning
摘要： 提出了一对新的冗余离散小波变换(RDWT)和波原子变换(WAT)字典,并将其应用于图像稀疏形态成分分解以获得图像的卡通与纹理成分。并针对卡通和纹理所具有的不同形态学特征,对卡通成分采用具有曲率运动、边缘冲击特性和平滑去噪性能的非线性self-snake模型来放大；对纹理成分采用双三次插值方法来放大,最后通过叠加就可获得放大图像。实验结果表明,这种基于新字典对的稀疏形态成分分解的图像放大方法相比于传统的基于整幅图像的放大方法能够有效地保护小曲率和大梯度,强化图像边缘,保证纹理细节清晰完整。
| [1] 程光权,成礼智.基于小波的方向自适应图像插值[J].电子与信息学报,2009,2:265-269 [2] 祝轩,张申华,王蕾,等.基于self-snake模型的图像放大[J].西北大学学报:自然科学版,2010,0(1):73-75 [3] Starck J L,Elad M,Donoho D L.Redundant multiscale transforms and their application for morphological component separation[J].Advances in Imaging and Electron Physics,2004,132(35):287-348 [4] Meyer Y.Oscillating patterns in image processing and nonlinear evolution equations [M].Boston:American Mathematical Society,2002 [5] Chan T F,Shen J H.Mathematical models for local non-texture inpainting[J].SIAM J.Appl.Math,2001,62(6):1019-1043 [6] Zhu Xuan,Wang Ning,En-biao,et al.Image decomposition modelcombined with sparse representation and total variation[C]∥Proceeding of the IEEE International Conference on Information and Automation.Yinchuan,China,2013:86-91 [7] 李德强,吴永国,罗海波.基于冗余离散小波变换的信号配准及分类[J].自动化学报,2011,37(1):61-66 [8] 刘国军,冯象初,张选德.波原子纹理图像阈值算法[J].电子与信息学报,2009,(8):1791-1795 [9] Mallat S G,Jaggi S,Karl W,et al.High resolution pursuit forfeature extraction[J].Applied and Computational Harmonic Analysis,1998,5(7):428-449 [10] Osher S,Burger M,Goldfarb D,et al.An iterated regularization method for total variation-based image restoration[J].SIAM Journal on Multiscale Modeling and Simulation,2005,4(5):460-489 [11] Daubechies I,Defrise M,Mol C D.An iterative thresholding algorithm for linear inverse problems with a sparsity constraint[J].Commun.Pure Appl.Math.,2004,57(11):1413-1457 [12] Stack J L,Elad M,Donoho D L.Image decomposition via thecombination of Sparse representation and a variational approach[J].IEEE Transaction on Image Proeessing,2005,4(10):1570-158 |
| No related articles found! |
|
||
首页