多通道图像EMD及应用
|
摘要
针对现有的经验模态分解方法(Empirical Mode Decomposition,EMD)对多通道图像(如彩色图像)进行分解时通常忽略各通道图像之间相关性的问题,提出了一种多通道图像EMD方法。该方法采用双拉普拉斯算子插值得到图像上下包络,并建立一个整体筛分停止准则进行筛分来考虑各通道图像相关性,能够将多通道图像自适应分解为数目不多的内蕴模态函数(Intrinsic Mode Function,IMF)分量和一个余量,其中内蕴模态函数分量体现了原始图像不同尺度的特征信息,余量体现了图像的整体变化趋势。该方法可以应用在图像锐化、夜景图像增强等图像分析和处理领域。实验结果显示该方法能够取得较好的效果。
The existing Empirical Mode Decomposition(EMD)methods usually ignore the correlation of each channel image when decomposing a multi-channel image(e.g. a color image). To ameliorate, this paper presents a novel EMD method for multi-channel images. It computes the upper and lower envelopes of multi-channel images by an interpolation approach based on bi-Laplacian operator, and sets up a whole stopping criterion of the sifting process to consider the correlation of all channel images. The novel EMD method can decompose a multi-channel image into a finite number of Intrinsic Mode Functions(IMFs)with different scale features and a residue representing the whole change trend of the image.According to the novel EMD method, a suite of challenging application tasks in image analysis and processing can be undertook, such as image sharpening and night image enhancement. Experimental results demonstrateal this method and its applications can generate good results.
The existing Empirical Mode Decomposition(EMD)methods usually ignore the correlation of each channel image when decomposing a multi-channel image(e.g. a color image). To ameliorate, this paper presents a novel EMD method for multi-channel images. It computes the upper and lower envelopes of multi-channel images by an interpolation approach based on bi-Laplacian operator, and sets up a whole stopping criterion of the sifting process to consider the correlation of all channel images. The novel EMD method can decompose a multi-channel image into a finite number of Intrinsic Mode Functions(IMFs)with different scale features and a residue representing the whole change trend of the image.According to the novel EMD method, a suite of challenging application tasks in image analysis and processing can be undertook, such as image sharpening and night image enhancement. Experimental results demonstrateal this method and its applications can generate good results.
引文
[1] Huang N E,Shen Z,Long S R,et al.The empirical modedecomposition and the Hilbert spectrum for nonlinearand non-stationary time series analysis[J].Proceedings ofthe Royal Society A Mathematical Physical&EngineeringSciences,1998,454(1971):903-995.
[2] Battista B M,Knapp C,Mcgee T,et al.Application of theempirical mode decomposition and Hilbert-Huang trans-form to seismic reflection data[J].Geophysics,2007,72(2):H29-H37.
[3] Chen C,Chiang W,Liu T,et al.Detecting the sensitivityof structural damage based on the Hilbert-Huang trans-form approach[J].Engineering Computations,2010,27(7):799-818.
[4] Schneider E K,Fennessy M J,Kinter J L.A statistical-dynamical estimate of winter ENSO teleconnections ina future climate[J].Journal of Climate,2009,22(22):6624-6638.
[5] Gemmrich J R,Farmer D M.Near-surface turbulence inthe presence of breaking waves[J].Journal of PhysicalOceanography,2004,34(5):1067-1086.
[6]周小龙,杨龚勇,梁秀霞,等.基于EMD重构和SVM的滚动轴承故障诊断方法研究[J].东北电力大学学报,2016,36(6):71-76.
[7]尚海昆,王坤,李峰.基于集合经验模态分解法的局部放电信号去噪[J].东北电力大学学报,2016,36(4):32-38.
[8]姜万录,刘云杰,朱勇.小波脊线解调与两次EMD分解相结合的故障识别方法及应用研究[J].仪器仪表学报,2013,34(5):1131-1138.
[9]胡钢,郑皎月,秦新强.结合局部邻域特性和C-BEMD的图像融合方法[J].计算机辅助设计与图形学学报,2017(4):608-615.
[10] Nunes J C,Guyot S,Del E,et al.Texture analysis basedon local analysis of the bidimensional empirical modedecomposition[J].Machine Vision and Applications,2005,16(3):177-188.
[11] Linderhed A.Compression by image empirical mode decom-position[C]//Proceedings of IEEE International Confer-ence on Image Processing,2005:553-556.
[12] Damerval C,Meignen S,Perrier V.A fast algorithm forbidimensional EMD[J].IEEE Signal Processing Letters,2005,12(10):701-704.
[13]张合勇,任德明,赵卫疆,等.图像处理中二维经验模式分解的改进算法[J].光学学报,2009,29(5):1248-1253.
[14] Bhuiyan S M A,Adhami R R,Khan J F.Fast and adap-tive bidimensional empirical mode decomposition usingorder-statistics filter based envelope estimation[J].EURASIPJournal on Advances in Signal Processing,2008(1):1-18.
[15] Chen C Y,Guo S M,Chang W S,et al.An improvedbidimensional empirical mode decomposition:a meanapproach for fast decomposition[J].Signal Processing,2014,98(5):344-358.
[16] Bhuiyan S M A,Khan J F,Alam M S.Color imagetrend adjustment using a color bidimensional empiricalmode decomposition method[J].Journal of Electronic Im-aging,2012,21(3):234-242.
[17] Subr K,Soler C,Durand F.Edge-preserving multiscaleimage decomposition based on local extrema[J].ACMTransactions on Graphics,2009,28(5):147.
[18] Wang H,Cao J,Liu X,et al.Least-squares images foredge-preserving smoothing[J].Computational Visual Media,2015,1(1):27-35.
[19] He K,Sun J,Tang X.Guided image filtering[J].IEEETransactions on Pattern Analysis&Machine Intelli-gence,2013,35(6):1397-1409.
[20] Paris S,Hasinoff S W,Kautz J.Local Laplacian filters:edge-aware image processing with a Laplacian pyramid[J].ACM Transactions on Graphics,2011,30(4):1244-1259.
[21] Majumder A.Contrast enhancement of multi-displays usinghuman contrast sensitivity[C]//Proceedings of IEEE Com-puter Society Conference on Computer Vision and Pat-tern Recognition,2005:377-382.
[22] Lee S.An efficient content-based image enhancementin the compressed domain using Retinex theory[J].IEEETransactions on Circuits&Systems for Video Technol-ogy,2007,17(2):199-213.
[23] Elad M.Retinex by two bilateral filters[M]//Scale spaceand PDE methods in computer vision.Berlin,Heidelberg:Springer,2005:217-229.
[24] Zhao H X,Xiao C B,Yu J.Night color image enhance-ment via statistical law and retinex[M]//Emerging trendsin image processing,computer vision and pattern recog-nition.San Francisco:Morgan Kaufmann,2015:249-261.
[25] Rahman Z U,Jobson D J,Woodell G A.Retinex pro-cessing for automatic image enhancement[J].Proceed-ings of SPIE,2004,13(1):100-110.
[26]戴岩.夜间彩色图像增强技术研究[D].北京:北京工业大学,2014.
[2] Battista B M,Knapp C,Mcgee T,et al.Application of theempirical mode decomposition and Hilbert-Huang trans-form to seismic reflection data[J].Geophysics,2007,72(2):H29-H37.
[3] Chen C,Chiang W,Liu T,et al.Detecting the sensitivityof structural damage based on the Hilbert-Huang trans-form approach[J].Engineering Computations,2010,27(7):799-818.
[4] Schneider E K,Fennessy M J,Kinter J L.A statistical-dynamical estimate of winter ENSO teleconnections ina future climate[J].Journal of Climate,2009,22(22):6624-6638.
[5] Gemmrich J R,Farmer D M.Near-surface turbulence inthe presence of breaking waves[J].Journal of PhysicalOceanography,2004,34(5):1067-1086.
[6]周小龙,杨龚勇,梁秀霞,等.基于EMD重构和SVM的滚动轴承故障诊断方法研究[J].东北电力大学学报,2016,36(6):71-76.
[7]尚海昆,王坤,李峰.基于集合经验模态分解法的局部放电信号去噪[J].东北电力大学学报,2016,36(4):32-38.
[8]姜万录,刘云杰,朱勇.小波脊线解调与两次EMD分解相结合的故障识别方法及应用研究[J].仪器仪表学报,2013,34(5):1131-1138.
[9]胡钢,郑皎月,秦新强.结合局部邻域特性和C-BEMD的图像融合方法[J].计算机辅助设计与图形学学报,2017(4):608-615.
[10] Nunes J C,Guyot S,Del E,et al.Texture analysis basedon local analysis of the bidimensional empirical modedecomposition[J].Machine Vision and Applications,2005,16(3):177-188.
[11] Linderhed A.Compression by image empirical mode decom-position[C]//Proceedings of IEEE International Confer-ence on Image Processing,2005:553-556.
[12] Damerval C,Meignen S,Perrier V.A fast algorithm forbidimensional EMD[J].IEEE Signal Processing Letters,2005,12(10):701-704.
[13]张合勇,任德明,赵卫疆,等.图像处理中二维经验模式分解的改进算法[J].光学学报,2009,29(5):1248-1253.
[14] Bhuiyan S M A,Adhami R R,Khan J F.Fast and adap-tive bidimensional empirical mode decomposition usingorder-statistics filter based envelope estimation[J].EURASIPJournal on Advances in Signal Processing,2008(1):1-18.
[15] Chen C Y,Guo S M,Chang W S,et al.An improvedbidimensional empirical mode decomposition:a meanapproach for fast decomposition[J].Signal Processing,2014,98(5):344-358.
[16] Bhuiyan S M A,Khan J F,Alam M S.Color imagetrend adjustment using a color bidimensional empiricalmode decomposition method[J].Journal of Electronic Im-aging,2012,21(3):234-242.
[17] Subr K,Soler C,Durand F.Edge-preserving multiscaleimage decomposition based on local extrema[J].ACMTransactions on Graphics,2009,28(5):147.
[18] Wang H,Cao J,Liu X,et al.Least-squares images foredge-preserving smoothing[J].Computational Visual Media,2015,1(1):27-35.
[19] He K,Sun J,Tang X.Guided image filtering[J].IEEETransactions on Pattern Analysis&Machine Intelli-gence,2013,35(6):1397-1409.
[20] Paris S,Hasinoff S W,Kautz J.Local Laplacian filters:edge-aware image processing with a Laplacian pyramid[J].ACM Transactions on Graphics,2011,30(4):1244-1259.
[21] Majumder A.Contrast enhancement of multi-displays usinghuman contrast sensitivity[C]//Proceedings of IEEE Com-puter Society Conference on Computer Vision and Pat-tern Recognition,2005:377-382.
[22] Lee S.An efficient content-based image enhancementin the compressed domain using Retinex theory[J].IEEETransactions on Circuits&Systems for Video Technol-ogy,2007,17(2):199-213.
[23] Elad M.Retinex by two bilateral filters[M]//Scale spaceand PDE methods in computer vision.Berlin,Heidelberg:Springer,2005:217-229.
[24] Zhao H X,Xiao C B,Yu J.Night color image enhance-ment via statistical law and retinex[M]//Emerging trendsin image processing,computer vision and pattern recog-nition.San Francisco:Morgan Kaufmann,2015:249-261.
[25] Rahman Z U,Jobson D J,Woodell G A.Retinex pro-cessing for automatic image enhancement[J].Proceed-ings of SPIE,2004,13(1):100-110.
[26]戴岩.夜间彩色图像增强技术研究[D].北京:北京工业大学,2014.