摘要
数码相机的时代已经到来,其革命无处不在,数字图像也是。然而,相机对图像质量的提高并非总能跟得上人类的苛求。图像质量的降低称为图像降质,有许多原因导致,最主要是由于模糊和噪声。随着相机镜头的小型化和廉价化,受限于拍摄水平,如果没有拍摄时没有拿稳相机或者对焦不准,都会减少图像清晰度,让人很难分辨细节。一些其它的随机因素也会给相机带来不可避免的噪声。美好的瞬间一去不回,难以复制。人们迫切希望找到一些简单有效的方法来恢复图像,提高质量。我们的工作就是围绕着各种形式的图像模糊展开。
我们的主要工作和创新点如下：
一、首先回顾了相关背景知识和研究现状,指出了图像恢复和图像增强之间的区别,介绍了图像式恢复相对于其它恢复方式的优点,展望了其广泛的应用领域；就什么是图像恢复技术这个问题的解释,将图像恢复和图像增强之间作出对比。接着我们对图像恢复技术中的关键技术和难点进行了阐述。
二、搭出基于单幅模糊图像的盲复原框架：模糊图像的盲恢复是一项极富挑战性的工作,导致其病态性的主要原因是已知量少于未知量。针对这个问题,我们试图通过增加辅助信息作为约束条件来限制未知量。具体做法是：用两个包含显著边缘的空间先验的正则代价函数来交替迭代模糊核和清晰图像直至收敛,得到模糊图像的模糊核；之后又利用包含稀疏先验的正则函数来恢复清晰图像,可以保持更多的结构细节。为减少噪声对模糊核的干扰,我们还提出模糊核的修正准则。针对前人相对盲目的人工设置模糊核尺寸,我们首次提出了自适应模糊核尺寸选择机制。
三、根据各自数学模型,对几种特殊模糊作出快速处理：在直线运动模糊的对数频谱中找到其模糊参数：模糊方向和模糊尺度,并且结合误差参数法进一步做出精确估计；在离焦模糊的倒频谱的第一个中心圆环中估计出了离焦半径；用Hough变换先提取出旋转运动模糊图像边缘中的有效圆弧段,接着用最小二乘拟合出圆心位置,然后依据Bresenham画圆算法提取出各个同心圆上的像素,分别对其进行一维复原,最后镶嵌回去得到完整的二维去模糊图像；针对局部模糊,用一系列的形态学方法先分割出模糊区域,接着用盲复原框架算法对模糊区域进行恢复,最后同原清晰区域整合得到完整去模糊图像。
四、针对更加病态的含噪模糊图像,首先利用方向高通滤波器和Radon逆变换来重建模糊核。然后在去噪去卷积阶段,我们建立两个代价函数交替迭代直至收敛,最终收敛得到去噪去卷积的清晰图像。
五、针对模糊图像质量的评价,首次提出了考虑主观感受的客观评价标准。我们不仅考虑了一些客观评价准则诸如饱和度、对比度、边缘信息以及基于自然统计规律的功率谱知识,而且有效地将对人眼视觉敏感的图像纹理考虑进来,组成了一个加权评价函数形式。在如何确定各项评价准则的权重因子时,我们用到了最小二乘非线性回归拟合方法。
The age of digital cameras is dawning, and its revolution is everywhere, so is digital image. However, the advancement of image quality due to camera cannot always keep up with men's expectation. We refer to reducment in image quality as image degradation; there are many reasons for this, which mainly due to blur and noise. With the miniaturization and cheapness of camera lens, and limited to photographers'level, if the camera doesn't be hold steadily or the object get out of focus, all of which can reduce the visibility of image, and make us hard to distinguish the detail. Some other stochastic factors also take in inevitable noise into image. Great moment once go may never come back any more, which is difficult to copy. Simple but effective approach to restore image and improve the quality became urgency. Our research thus center about various forms of image blurs.
Our main work and innovation include the following:
1We look back at background, figure out the difference between image restoration and image enhancement. We introduce the advantage of image restoration methods refer to other restoration methods, and forsee its broad application. Concerning what is image restoration, we compare it with the notion of image enhancement. And then we elaborate the key technology difficulties in image restoration method.
2Blind deconvolution of blur image is a most challenging job, the illness of which was mainly due to the number of known less than that of unknown. We set up a framework to blind deconvolution based on a single burred image, and try to add auxiliary information as condition to restrict unknowns, here comes concrete measures:two regularization cost function which involve salient edges as spatial prior to alternately iterate the blur kernel and latent image until convergence, where we can get the blur kernel. Then sparse prior is used to restore the latent image which can preserve more structure detail. In order to reduce noise in blur kernel, we put forward some revisal principle. We propose adaptive kernel size to avoid blindly manual set.
3Based on respective mathematical model, we make several rapid processes on several special blur. We find blur parameters (which are motion length and motion direction) in logarithmic spectrum in linear motion blur images, and make precise evaluate combine with error-parameter. Defocus radius can be found in first circle- loop of defocus blur image cestrum. We use Hough transform to extract the edge of rotated blur image, and then the least square was applied to fit the location of the center. Thus pixels on each concentric circle were picked up to one-dimensional restoration respectively. A series of morphology methods can segment blur area from latent area in local blur images, then blind deconvolution framework was applied to restore the blur area. Then merge it with latent area can get the last deblurred image.
4For noisy blur images which are more ill, we first utilize directional low-pass filter and inverse Radon transform to restructure the blur kernel. In the denoise and deconvolution stage, we construct two cost functions to denoise and deconvolution alternately, latent image can be obtained when they convergent.
5We put forward a criterion of objective assessment which consider the subjective feelings for blur image evaluation. We not only concern some objective measure criteria like saturation, contrast, edge information and power spectral which based on natural statistical laws, but also effectively take in consider of image texture which sensitive to human vision, and a weighted evaluation function is made up. The least square nonlinear regress method is applied to fit the weight factor of each item.
引文
[11 JOSHI N S. Enhancing photographs using content-specific image priors[M]. ProQuest,2008.
[2]CHO T S. Motion blur removal from photographs [D]; Massachusetts Institute of Technology,2010.
[3]LO I S, MCKERCHER B, LO A, et al. Tourism and online photography [J]. Tourism Management,2011,32(4):725-31.
[4]WANG H-N, ZHONG W, WANG J, et al. Research of measurement for digital image definition [J]. Journal of Image and Graphics,2004,9(7):828-31.
[5]GRAHAM D J, REID I, RICE S P. Automated sizing of coarse-grained sediments:image-processing procedures [J]. Mathematical Geology,2005,37(1):1-28.
[61 PARKER J R. Algorithms for image processing and computer vision [M]. John Wiley & Sons,2010.
[7]李仕,孙辉,张葆.运动模糊图像的实时恢复算法[J].光学精密工程,2007,15(5)：767.
[81 AMUDHA J, PRADEEPA N, SUDHAKAR R. A Survey on Digital Image Restoration [J]. Procedia Engineering,2012,38(2378-82.
[9]NAYAR S K, BEN-EZRA M. Motion-based motion deblurring [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2004,26(6):689-98.
[10]RASKAR R, AGRAWAL A, TUMBLIN J. Coded exposure photography: motion deblurring using fluttered shutter [J]. ACM Trans Graph,2006,25(3):795-804.
[11]LEVIN A, SAND P, CHO T S, et al. Motion-invariant photography [J]. ACM Trans Graph,2008,27(3):1-9.
[12]YU-WING T, HAO D, BROWN M S, et al. Correction of Spatially Varying Image and Video Motion Blur Using a Hybrid Camera [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2010,32(6):1012-28.
[13]WEI-GE C, NANDHAKUMAR N, MARTIN W N. Image motion estimation from motion smear-a new computational model [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1996,18(4):412-25.
[14]JIA J, SUN J, TANG C-K, et al. Bayesian Correction of Image Intensity with Spatial Consideration Computer Vision-ECCV 2004 [M]//PAJDLA T, MATAS J. Springer Berlin/Heidelberg.2004:342-54.
[15]PETSCHNIGG G, SZELISKI R, AGRAWALA M, et al. Digital photography with flash and no-flash image pairs [J]. ACM Trans Graph,2004,23(3):664-72.
[16]RAV-ACHA A, PELEG S. Two motion-blurred images are better than one [J]. Pattern Recogn Lett,2005,26(3):311-7.
[17]YUAN L, SUN J, QUAN L, et al. Image deblurring with blurred/noisy image pairs [J]. ACM Trans Graph,2007,26(3):1.
[18]TELLEEN J, SULLIVAN A, YEE J, et al. Synthetic Shutter Speed Imaging [J]. Computer Graphics Forum,2007,26(3):591-8.
[19]FERGUS R, SINGH B, HERTZMANN A, et al. Removing camera shake from a single photograph [J]. ACM Trans Graph,2006,25(3):787-94.
[20]KRISHNAN D, TAY T, FERGUS R. Blind deconvolution using a normalized sparsity measure; proceedings of the Computer Vision and Pattern Recognition (CVPR),2011 IEEE Conference on, F 20-25 June 2011,2011 [C].
[21]LEVIN A, FERGUS R, FR, et al. Image and depth from a conventional camera with a coded aperture [J]. ACM Trans Graph,2007,26(3):70.
[22]SHAN Q, JIA J, AGARWALA A. High-quality motion deblurring from a single image [J]. ACM Trans Graph,2008,27(3):1-10.
[23]CHO S, LEE S. Fast motion deblurring [J]. ACM Trans Graph,2009,28(5):1-
[24]XU L, JIA J. Two-phase kernel estimation for robust motion deblurring [M]. Proceedings of the 11th European conference on Computer vision:Part Ⅰ. Heraklion, Crete, Greece; Springer-Verlag.2010:157-70.
[25]WANG W, ZHENG J-J, LIU X, et al. Adaptive detection method of degraded parameters in motion blur image; proceedings of the Fuzzy Systems and Knowledge Discovery (FSKD),2011 Eighth International Conference on, F 26-28 July 2011, 2011 [C].
[26]TIKHONOV A N. On the stability of inverse problems [J]. Doklady Akademii Nauk SSSR,1943,39(5):195-8.
[27]WIENER N. Extrapolation, Interpolation, and Smoothing of Stationary Time Series [M]. The MIT Press,1964.
[28]RICHARDSON W H. Bayesian-Based Iterative Method of Image Restoration [J]. J Opt Soc Am,1972,62(1):55-9.
[29]LUCY L. An iterative technique for the rectification of observed distributions [J]. The astronomical journal,1974,79(745.
[30]CARON J N, NAMAZI N M, ROLLINS C J. Noniterative blind data restoration by use of an extracted filter function [J]. Appl Opt,2002,41(32):6884-9.
[31]JALOBEANU A, BLANC-FERAUD L, ZERUBIA J. Estimation of blur and noise parameters in remote sensing; proceedings of the Acoustics, Speech, and Signal Processing (ICASSP),2002 IEEE International Conference on, F 13-17 May 2002, 2002 [C].
[32]NEELAMANI R, HYEOKHO C, BARANIUK R. ForWaRD:Fourier-wavelet regularized deconvolution for ill-conditioned systems [J]. Signal Processing, IEEE Transactions on,2004,52(2):418-33.
[33]GEMAN D, REYNOLDS G. Constrained restoration and the recovery of discontinuities [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1992,14(3):367-83.
[34]DONATELLI M, ESTATICO C, MARTINELLI A, et al. Improved image deblurring with anti-reflective boundary conditions and re-blurring [J]. Inverse Problems,2006,22(6):2035.
[35]KUNDUR D, HATZINAKOS D. Blind image deconvolution [J]. Signal Processing Magazine, IEEE,1996,13(3):43-64.
[36]REEVES S J, MERSEREAU R M. Blur identification by the method of generalized cross-validation [J]. Image Processing, IEEE Transactions on,1992,1(3): 301-11.
[37]SANG KU K, JOON KI P. Out-of-focus blur estimation and restoration for digital auto-focusing system [J]. Electronics Letters,1998,34(12):1217-9.
[38]LIKAS A C, GALATSANOS N P. A variational approach for Bayesian blind image deconvolution [J]. Signal Processing, IEEE Transactions on,2004,52(8): 2222-33.
[39]MISKIN J, MACKAY D J. Ensemble learning for blind image separation and deconvolution [M]. Advances in independent component analysis. Springer.2000: 123-41.
[40]TOMASI C, MANDUCHI R. Bilateral filtering for gray and color images; proceedings of the Computer Vision,1998 Sixth International Conference on, F,1998 [C].IEEE.
[41]YOUNG I T, VAN VLIET L J. Recursive implementation of the Gaussian filter [J]. Signal processing,1995,44(2):139-51.
[42]OSHER S, RUDIN L I. Feature-oriented image enhancement using shock filters [J]. SIAM Journal on Numerical Analysis,1990,27(4):919-40.
[43]WOLD H. Estimation of principal components and related models by iterative least squares [J]. Multivariate analysis,1966,1(391-420.
[44]NOCEDAL J, WRIGHT S J,. Conjugate gradient methods [M]. Springer,2006.
[45J NOCEDAL A V, KRYLOV A S. Scale-space method of image ringing estimation; proceedings ot the ICTP, F,2009 [C].
[46]KAZHDAN M, BOLITHO M, HOPPE H. Poisson surface reconstruction; proceedings of the Proceedings of the fourth Eurographics symposium on Geometry processing, F,2006 [C].
[47]TANAKA M, YONEJI K, OKUTOMI M. Motion blur parameter identification from a linearly blurred image; proceedings of the Consumer Electronics, 2007 ICCE 2007 Digest of Technical Papers International Conference on, F,2007 [C]. IEEE.
[48]B.R.HUNT T M C. Nonstationary Assumptions for Gaussian Models of Images [J]. Systems, Man and Cybernetics, IEEE Transactions on,1976, SMC-6(12): 876-82.
[49]YITZHAKY Y, KOPEIKA N S. Identification of Blur Parameters from Motion Blurred Images [J]. Graphical Models and Image Processing,1997,59(5): 310-20.
[50]王伟,郑津津,刘星,et a1.图像复原中的模糊参数估计[J].智能系统学报,2012,7(4)：315-20.
[51]HOUGH P V C. Machine Analysis Of Bubble Chamber Pictures [J]. ConfProc, 1959, C590914(554-8.
[52]MAINI R, AGGARWAL H. Study and comparison of various image edge detection techniques [J]. International Journal of Image Processing (IJIP),2009,3(1): 1-11.
[53]Y Z M. Deconvolution and Signal Recovery [J]. National defence industrial press,2001,200-2.
[54]SIMMS N. Illuminated line of light using point light source [M]. Google Patents.1997.
[55]MOGHADDAM M E. A mathematical model to estimate out of focus blur; proceedings of the Image and Signal Processing and Analysis,2007 ISPA 2007 5th International Symposium on, F,2007 [C]. IEEE.
[56]CHILDERS D G, SKINNER D P, KEMERAIT R C. The cepstrum:A guide to processing [J]. Proceedings of the IEEE,1977,65(10):1428-43.
[57]ROM R. On the cepstrum of two-dimensional functions (Corresp.) [J]. Information Theory, IEEE Transactions on,1975,21(2):214-7.
[58]TUGNAIT J K. Identification and deconvolution of multichannel linear non-Gaussian processes using higher order statistics and inverse filter criteria [J]. Signal Processing, IEEE Transactions on,1997,45(3):658-72.
[59]沈瑛,吴禄慎.由约束最小二乘方法改进的图像恢复方法[J].数据采集与处理,2002,17(3)：325-7.
[60]ZHANG T, HONG H, YAN L, et al. Restoration of rotational motion blurred image based on Chebyshev polynomial interpolations; proceedings of the Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, F,2009 [C]. International Society for Optics and Photonics.
[61]BRESENHAM J E. Algorithm for computer control of a digital plotter [J]. IBM Systems journal,1965,4(1):25-30.
[62]ALDRICH J. Doing Least Squares:Perspectives from Gauss and Yule [J]. International Statistical Review,1998,66(1):61-81.
[63]杜春,孙即祥.基于峰度和圆拟合的旋转运动模糊参数辨识；proceedings ofthe全国第19届计算机技术与应用(CACIS)学术会议论文集(上册),F,2008[C].
[64]NAGY J G, O'LEARY D P. Restoring images degraded by s blur [J]. SIAM Journal on Scientific Computing,1998,19(4):1063-82.
[65]DAI S, WU Y. Removing partial blur in a single image; proceedings of the Computer Vision and Pattern Recognition,2009 CVPR 2009 IEEE Conference on, F, 2009[C]. IEEE.
[66]BARDSLEY J, JEFFERIES S, NAGY J, et al. A computational method for the restoration of images with an unknown, spatially-varying blur [J]. Optics Express, 2006,14(5):1767-82.
[67]HIRSCH M, SRA S, SCH LKOPF B, et al. Efficient filter flow for space variant multiframe blind deconvolution; proceedings of the CVPR, F,2010 [C].
[68]SOREL M, SROUBEK F. Space-variant deblurring using one blurred and one underexposed image; proceedings of the Image Processing (ICIP),2009 16th IEEE International Conference on, F,2009 [C]. IEEE.
[69]LEVIN A. Blind motion deblurring using image statistics; proceedings of the NIPS, F,2006 [C].
[70]LIU R, LI Z, JIA J. Image partial blur detection and classification; proceedings of the Computer Vision and Pattern Recognition,2008 CVPR 2008 IEEE Conference on, F,2008 [C]. IEEE.
[71]SU B, LU S, TAN C L. Blurred image region detection and classification; proceedings of the Proceedings of the 19th ACM international conference on Multimedia, F,2011 [C]. ACM.
[72]ZHAO J, FENG H, XU Z, et al. Automatic blur region segmentation approach using image matting [J]. Signal, Image and Video Processing,2013,7(6):1173-81.
[73]CHUANG Y-Y, CURLESS B, SALESIN D H, et al. A bayesian approach to digital matting; proceedings of the Computer Vision and Pattern Recognition,2001 CVPR 2001 Proceedings of the 2001 IEEE Computer Society Conference on, F,2001 [C]. IEEE.
[74]MINHAS R, MOHAMMED A A, WU Q J, et al.3D shape from focus and depth map computation using steerable filters [M]. Image Analysis and Recognition. Springer.2009:573-83.
[75]http://www.alphamatting.com/datasets.
[76]ELAD M, FEUER A. Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images [J]. Image Processing, IEEE Transactions on,1997,6(12):1646-58.
[77]RUDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms [J]. Physica D:Nonlinear Phenomena,1992,60(1):259-68.
[78]VOGEL C R, OMAN M E. Fast, robust total variation-based reconstruction of noisy, blurred images [J]. Image Processing, IEEE Transactions on,1998,7(6):813-24.
[79]LEE J-S. Digital image smoothing and the sigma filter [J]. Computer Vision, Graphics, and Image Processing,1983,24(2):255-69.
[80]TAI Y-W, LIN S. Motion-aware noise filtering for deblurring of noisy and blurry images; proceedings of the Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, F,2012 [C]. IEEE.
[81]MOTWANI M C, GADIYA M C, MOTWANI R C, et al. Survey of image denoising techniques; proceedings of the Proceedings of GSPX, F,2004 [C]. Citeseer.
[82]BUADES A, COLL B, MOREL J-M. A non-local algorithm for image denoising; proceedings of the Computer Vision and Pattern Recognition,2005 CVPR 2005 IEEE Computer Society Conference on, F,2005 [C]. IEEE.
[83]DABOV K, FOI A, KATKOVNIK V, et al. Image denoising with block-matching and 3D filtering; proceedings of the Electronic Imaging 2006, F,2006 [C]. International Society for Optics and Photonics.
[84]YU G, SAPIRO G. DCT image denoising:a simple and effective image denoising algorithm [J]. Image Processing On Line,2011,108(
[85]DEANS S R. The Radon transform and some of its applications [M]. Courier Dover Publications,2007.
[86]ZHONG L, CHO S, METAXAS D, et al. Handling noise in single image deblurring using directional filters; proceedings of the Computer Vision and Pattern Recognition (CVPR),2013 IEEE Conference on, F,2013 [C]. IEEE.
[87]LI W, CHEN Y, LEE J, et al. Robust Optical Flow Estimation for Continuous Blurred Scenes using RGB-Motion Imaging and Directional Filtering [J].2014,
[88]OLIVER N M, ROSARIO B, PENTLAND A P. A Bayesian computer vision system for modeling human interactions [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2000,22(8):831-43.
[89]WEBSTER A A, JONES C T, PINSON M H, et al. Objective video quality assessment system based on human perception; proceedings of the IS&T/SPIE's Symposium on Electronic Imaging:Science and Technology, F,1993 [C]. International Society for Optics and Photonics.
[901 http://live.ece.utexas.edu/research/quality/.
[91]宋鹏程.基于HVS的点扩散算法和图像质量评价方法的研究[D]；河南大学,2012.
[92]MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain [J]. Image Processing, IEEE Transactions on,2012, 21(12):4695-708.
[93]CHOI M G, JUNG J H, JEON J W. No-Reference Image Quality Assessment using Blur and Noise [J]. Proceedings of World Academy of Science:Engineering & Technology,2009,50(
[94]VENKATESH BABU R, SURESH S, PERKIS A. No-reference JPEG-image quality assessment using GAP-RBF [J]. Signal processing,2007,87(6):1493-503.
[951 MARZILIANO P, DUFAUX F, WINKLER S, et al. A no-reference perceptual blur metric; proceedings of the Image Processing 2002 Proceedings 2002 International Conference on, F,2002 [C]. IEEE.
[96]TSOY Y R, SPITSYN V G, CHERNYAVSKY A V. No-reference image quality assessment through interactive neuroevolution [J]. Proc of lnt Con/on Compo Graphics (Graphicon-2007), Moscow State University, Moscow, Russia,2007,156-9.
[97]CHEN M-J, BOVIK A C. No-reference image blur assessment using multiscale gradient [J]. EURASIP Journal on Image and Video Processing,2011, 2011(1):1-11.
[981 PERTUZ S, PUIG D, GARCIA M A. Analysis of focus measure operators for shape-from-focus [J]. Pattern Recognition,2013,46(5):1415-32.
[99]ZHU X, MILANFAR P. A no-reference sharpness metric sensitive to blur and noise; proceedings of the Quality of Multimedia Experience,2009 QoMEx 2009 International Workshop on, F,2009 [C]. IEEE.
[100]RANDLES R H, WOLFE D A. Introduction to the theory of nonparametric statistics [J]. Introduction to the theory of nonparametric statistics, by Randles, Ronald H; Wolfe, Douglas A New York:Wiley, c1979 Wiley series in probability and mathematical statistics,1979,1(
[101]HUYNH-THU Q, GHANB ARI M. Scope of validity of PSNR in image/video quality assessment [J]. Electronics Letters,2008,44(13):800-1.
[102]RUBINSTEIN R Y. Optimization of computer simulation models with rare events [J]. European Journal of Operational Research,1997,99(1):89-112.
[103]KOPLOWITZ J, GRECO V. On the edge location error for local maximum and zero-crossing edge detectors [J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,1994,16(12):1207-12.
[104]HORITA A, NAKAYAMA K, HIRANO A, et al. Analysis of signal separation and signal distortion in feedforward and feedback blind source separation based on source spectra; proceedings of the Neural Networks,2005 IJCNN '05 Proceedings 2005 IEEE International Joint Conference on, F 31 July-4 Aug.2005, 2005 [C].
[105]WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment:from error visibility to structural similarity [J]. Image Processing, IEEE Transactions on, 2004,13(4):600-12.
[106]O'NEIL P V. Advanced engineering mathematics [M]. Cengage Learning, 2010.
[107]IHARA S. Information theory for continuous systems [M]. World Scientific, 1993.
[108]IIDAKA T, YAMASHITA K, KASHIKURA K, et al. Spatial frequency of visual image modulates neural responses in the temporo-occipital lobe. An investigation with event-related fMRI [J]. Cognitive Brain Research,2004,18(2): 196-204.
[109]PAN B, LU Z, XIE H. Mean intensity gradient:an effective global parameter for quality assessment of the speckle patterns used in digital image correlation[J]. Optics and Lasers in Engineering,2010, 48(4):469-77.
[110]SAYOOD K. Statistical evaluation of image quality measures [J]. Journal of Electronic imaging,2002,11(2):206-23.
[111]楼斌.基于NSS与HVS的图像质量评价万法研究[D]；浙江大学,2009.
[112]ROTH S, BLACK M J. Fields of experts:A framework for learning image priors; proceedings of the Computer Vision and Pattern Recognition,2005 CVPR 2005 IEEE Computer Society Conference on,F,2005 [C]. IEEE.
[113]TAKIGUCHI H, UDAGAWA Y. Method and apparatus for processing color images having high maximum saturation [M]. Google Patents.1991.
[114]CAMPBELL F W, ROBSON J. Application of Fourier analysis to the visibility of gratings [J]. The Journal of Physiology,1968,197(3):551.
[115]WANG L, HE D-C. Texture classification using texture spectrum [J]. Pattern Recognition,1990,23(8):905-10.
[1161 YE N, CHEN Q. An anomaly detection technique based on a chi-square statistic for detecting intrusions into information systems [J]. Quality and Reliability Engineering International,2001,17(2):105-12.
[117]SYKES A. An introduction to regression analysis [M]. Law School. University of Chicago,1993.