基于照射/反射模型的视觉感知增强算法研究及应用
|
摘要
图像增强技术是指通过特定的方法突显图像中某些想要的信息,抑制或消除无关信息,以改善图像的视觉感知效果。经过处理后的图像更加适合人眼观察或计算机分析处理。图像增强的目标和方法往往与具体应用相关,研究人员通常针对不同采集条件下的图像特性以及不同的的应用任务要求设计对应的图像增强算法,很少有通用的增强算法。近年来由于场景和成像设备的限制,在不均匀光照和低光照条件下拍摄的图像视觉效果较差,人眼难以识别,机器难以处理,急需对其进行增强处理。人类的视觉系统具有高度完善的自适应调节功能,能够在多种不同光照条件下准确地感知外部场景。因此,模拟人眼的处理过程来研究图像增强技术是一个有效的途径。本文对现实场景中的不均匀光照和低光照条件下采集的图像特性进行了深入研究,提出了基于照射/反射模型的图像增强算法。主要工作包括：
1.研究了照射/反射模型,针对现有算法在照射分量估计上的不足,提出了基于分块的照射分量估计算法,并在真实数据集上验证了基于分块估计照射分量的必要性,为后续的图像处理奠定基础；
2.研究和分析了照射/反射模型相关算法在动态范围压缩上存在的不足,提出了基于分段对数函数的动态范围压缩算法。在真实数据集上的实验结果证明算法能够有效地增强亮度较低的区域,抑制过亮的区域,使图像符合人眼的视觉特性；
3.针对传统的照射/反射模型中的色偏和饱和度不够等问题,提出了基于灰度世界假设的色彩校正算法。在真实数据集上的实验结果证明算法能够有效地消除图像增强后由于不良光源引起的色偏现象；
4.将上述算法应用到扣件状态检测系统中,通过在真实数据集上的实验结果证实,本文算法能够提高扣件的定位准确率和识别能力,同时验证了本文算法在去除不均匀光照和低光照影响的有效性。
Image enhancement is a kind of technology about highlighting some information which you want, and removing irrelevant information which you do not need, so that it can improve visual effects and perception. Images are more suitable to the human eyes and computer recognition after the enhancement. The goals and methods of image enhancement are often related to the specific applications. Researchers commonly use a specific algorithm for different images under various conditions. There is few common enhancement methods for enhancement. In recent years, images can not be recognition by the restrictions of the scene and image equipment, even under the uniform illumination and low lights conditions. Human visual system can be able to accurately perceive the external scene in a variety of light conditions with the adaptive adjustment function. Therefore, the way to simulate human eyes is an effective enhancement method. In this paper, the images under uniform illumination and low lights have been researched. An enhancement algorithm based on illuminance/reflectance model is proposed. The main tasks of this paper include:
1. Illuminance/reflectance model has been studied. Estimate illuminance by local of image could more accurately, so illuminance estimation based on image block is proposed in this paper. The necessity of this algorithm has been verified in Database.
2. Image enhancement algorithm on dynamic range adjustment and contrast enhancement has been studied. Dynamic range adjustment in illuminance/reflectance model Based on logarithmic function was proposed. According to the database, the algorithm can effectively enhance the brightness of the lower region; inhibit the brighter region, so that the image will be more suitable for human eyes observation.
3. The algorithm of gray world and white balance has been studied. A method based on white balance was proposed. This algorithm can effectively remove color cast for visual observation of human eyes.
4. The proposed enhancement algorithm is used to fastener detection. It has improved accuracy of fastener position and identification of fastener position.
1.研究了照射/反射模型,针对现有算法在照射分量估计上的不足,提出了基于分块的照射分量估计算法,并在真实数据集上验证了基于分块估计照射分量的必要性,为后续的图像处理奠定基础；
2.研究和分析了照射/反射模型相关算法在动态范围压缩上存在的不足,提出了基于分段对数函数的动态范围压缩算法。在真实数据集上的实验结果证明算法能够有效地增强亮度较低的区域,抑制过亮的区域,使图像符合人眼的视觉特性；
3.针对传统的照射/反射模型中的色偏和饱和度不够等问题,提出了基于灰度世界假设的色彩校正算法。在真实数据集上的实验结果证明算法能够有效地消除图像增强后由于不良光源引起的色偏现象；
4.将上述算法应用到扣件状态检测系统中,通过在真实数据集上的实验结果证实,本文算法能够提高扣件的定位准确率和识别能力,同时验证了本文算法在去除不均匀光照和低光照影响的有效性。
Image enhancement is a kind of technology about highlighting some information which you want, and removing irrelevant information which you do not need, so that it can improve visual effects and perception. Images are more suitable to the human eyes and computer recognition after the enhancement. The goals and methods of image enhancement are often related to the specific applications. Researchers commonly use a specific algorithm for different images under various conditions. There is few common enhancement methods for enhancement. In recent years, images can not be recognition by the restrictions of the scene and image equipment, even under the uniform illumination and low lights conditions. Human visual system can be able to accurately perceive the external scene in a variety of light conditions with the adaptive adjustment function. Therefore, the way to simulate human eyes is an effective enhancement method. In this paper, the images under uniform illumination and low lights have been researched. An enhancement algorithm based on illuminance/reflectance model is proposed. The main tasks of this paper include:
1. Illuminance/reflectance model has been studied. Estimate illuminance by local of image could more accurately, so illuminance estimation based on image block is proposed in this paper. The necessity of this algorithm has been verified in Database.
2. Image enhancement algorithm on dynamic range adjustment and contrast enhancement has been studied. Dynamic range adjustment in illuminance/reflectance model Based on logarithmic function was proposed. According to the database, the algorithm can effectively enhance the brightness of the lower region; inhibit the brighter region, so that the image will be more suitable for human eyes observation.
3. The algorithm of gray world and white balance has been studied. A method based on white balance was proposed. This algorithm can effectively remove color cast for visual observation of human eyes.
4. The proposed enhancement algorithm is used to fastener detection. It has improved accuracy of fastener position and identification of fastener position.
引文
[1]Gonzalez R C. Digital Image Processing[M]. Beijing:Publishing House of Electronics Industry, 2003.
[2]L. Tao, Tompkins r, Asari v. An illuminance-reflectance model for nonlinear enhancement of color images[C] Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: Vol 3, Jan 20-26, 2005, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2005:159.
[3]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001.
[4]Oppenheim A.V.Speech analysis-synthesis system based on homomorphic filtering. JASAournal of the Acoustical Society of America[J],1969,45(2):460-465
[5]Fries R,Modestino J.Image enhancement by stochastic homomorphic filtering[C].IEEE Transactions on Acoustics,Speech,and Signal Processing,1979,27(6):627-637
[6]Polesel,Ramponi,Mathews.Image enhancement via adaptive unsharp masking[C].IEEE Transactions on Image Processing,2000,9(3):505-510
[7]Srinivasa D.R,Image Enhancement Using Integer Sequences Based Windows[C], PICC, Kongu Engineering College, 2010. pp. 498-502
[8]Guillon S,Baylou P,Najim.Adaptive nonlinear filters for 2D and 3D image enhancement.[C] Signal Processing, 1998,67(3):237-254
[9]陈强,纪则轩,孙权森.基于光能分配的遥感图像增强[J].中国图像图形学报,2009,14(11)： 2284-2291
[10]马江林,赵忠明.海量遥感图像频域编辑器软件的设计与实现[M].计算机工程.2007,33(1)
[11]Marini, D. and Rizzi, A., A computational approach to color adaptation effects[C], Image and Vision Computing 2000,18:1005-1014
[12]Morel, J.M. Petro, A.B. Sbert, C. A PDE Formalization of Retinex Theory[C]. IEEE Transactions on Image Processing, Nov.2010,19 Issue:11.pp2825-2837
[13]Kimmel R. Elad M. Shaked D. et al. A variational framework for Retinex[C]. International Journal of Computer Vision. 2003,52(1):8-23
[14]Xiaolin Wu, A Linear Programming Approach for Optimal Contrast-Tone Mapping[C],ECCV,2011.1262-1272
[15]Fattal R,Lischinski D,Werman M.Gradient domain high dynamic range compression[C]. Computer Graphics Proceedings,ACM,2002.249-256
[16]Meylan I Sfisstrunk S. High dynamic range image rendering with a retinex based adaptive filter[C]. IEEE Transactions on Image Processing,2006,15(9):2826-2830
[17]Meylan L.Tone mapping for high dynamic range images[J]. Thesis,Ecole Polytechnique Federale de Lausanne,Lausanne,Switzerland,2Q06.
[18]Krawczyk G,Myszkowski K,Seidel P.Lightness perception in tone reproduction for high dynamic range images[J].Computer G Graphics Forum,2005,24(11):635-645
[19]AGGARWAL, M., AND AHUJA, N. High dynamic range panoramic imaging[C]. In Proc.IEEE ICCV,vol.I,2001.2-9
[20]Raanan Fattal, Dani Lischinski, Michael Werman. Gradient Domain High Dynamic Range Compression full Full[J] ACM SIGGRAPH 2002.
[21]Rafal Mantiuk, Karol Myszkowski, Hans-Peter Seidel. A Perceptual Framework for Contrast Processing of High Dynamic Range Images [C]. In ACM Transactions on Applied Perception, 2006.:286-308
[22]Grzegorz Krawczyk, Karol Myszkowski, Hans-Peter Seidel,Computational Model of Lightness Perception in High Dynamic Range Images [J].In: Proc. of IS&T/SPIE's Human Vision and Electronic Imaging, 2006.
[23]Fredo Durand,Julie Dorsey.A Fast Approximation of the Bilateral Filter using a Signal Processing Approach[J]. MIT technical report 2006 (MIT-CSAIL-TR-2006-073)
[24]E.H. Land,J McCann. Lightness and Retinex theory[J]. Opt SocAmer,1971.61(1):1-11.
[25]S. Shwartz, E. Namer, and Y. Schechner. Blind haze separation[C].CVPR, 2006.
[26]R. Tan. Visibility in bad weather from a single image[C]. CVPR,2008.
[27]Kaiming He Jian Sun Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior[C].CVPR,2009,1956-1963
[28]Akito Yamasaki, Hidenori Takauji, Shun'ichi Kaneko.Denighting:Enhancement of Nighttime Images for a Surveillance Camera[C].ICPR,2008,1-4
[29]曹力,路吉林.基于DSP的夜晚图像增强技术[J].上海：微型电脑应用.2010.
[30]Barnard K,Cardei V,Funt B.A comparison of computational color constancy algorithms-part I;methodology and experiments with synthesized data[C].IEEE Transactions on Image Processing,2002,11(9):972-984
[31]Barnard K,Martin L,Coath A,Funt B.A comparison of computational color constancy algorithms methodology and experiments with synthesized data[C].IEEE Transactions on Image Processing,2002,11(9):985-996
[32]Provenzi E,Fierro M,Rizzi A, Carli L. Gadia D,Marini D.Random spray Retinex:a new Retinex implementation to investigate the local properties of the model[C].IEEE Transactions on Image Processing,2007,16 (1):162-171
[33]Rizzi A,Gatta C,Marin. A new algorithm for unsupervised global and local color correction[J]. Pattern Recognition Letters,2003,24(11):1663-1677
[34]Papoulis, A. Probability, Random Variables, and Stochastic Processes[C].3rd edn. McGraw-Hill: New York, 1991.pp. 345-346
[35]Provenzi E,Gatta C,Fierro M,Rizzi A.A spatially variant white-patch and gray-world method for color image enhancement driven by local contrast[C].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(10):1757-1770
[36]Rahman Z,Jobson D J,Woodell G A. Multi-scale retinex for color image enhancememt[C]. IEEE Image Processing, 1996,3: 1003-1006
[37]Jobson, D.J., Rahman, Z., and Woodell, G.A.. Properties and performance of the center/surround Retinex[C]. IEEE Trans, on Image Proc., 1997a.6:451-462.
[38]Jobson, D.J., Rahman, Z., and Woodell, G.A. A multiscale Retinex for bridging the gap between color imagesand the human observation of scenes[C].IEEE Transactions on Image Processing:Special Issue on Color Processing,1997,6(7):965-976.
[39]L. Tao, V.K. Asari, Modified luminance based MSR for fast and efficient image enhancement[C], Proceedings of the IEEE International Workshop on Applied Imagery and Pattern Recognition (AIPR), 2003, pp.174 - 179.
[40]E.H. Land. The Retinex theory of color visionC]. Sci. Amer.,237:108-128,1977.
[41]E.H. Land. Recent advances in the Retinex theory and some implications for cortical computations:Color vision and the natural image[C]. Proc. Nat. Acad. Sci. USA, 80:5163-5169, 1983.
[42]E.H. Land. An alternative technique for computation of the designator in the Retinex of color vision[C]. Proc. Nat. Acad. Sci. USA, 83:3078-3080, 1986.
[43]E H Land. An alternative technique for the computation of the designator in the Retinex theory of color vision[C]. Proceedings of the National Academy of Science of the United States of America,1986,83(10):3078-3080
[44]Provenzi, E., Rizzi, A., Carli, L. D., and Marini, D, Mathematical definition and analysis of the retinex algorithm[C], J. Opt. Soc. Am. A 22(12), 2613-2621 (2005).
[45]Wenye Ma; Morel, J.-M.; Osher, S.; Chien, A.; An L1-based variational model for Retinex theory and its application to medical imagesComputer Vision and Pattern Recognition[C],2011 IEEE Conference on Issue Date: 20-25 June 2011 On page(s):153 - 160
[46]Frankle, J. and McCann, J., "Method and apparatus for lightness imaging." US Patent (May 1983). Number Patent 4384336.
[47]Funt, B., Ciurea, F., and McCann, J., Retinex in matlab[C],J. of Electronic Imaging 13(1), 48-57 (2004).
[48]McCann, J., Lesson learned from mondrians applied to real images and color gamuts [C],Proc. IST/SID Seventh Color Imaging Conference, 1-8 (1999).
[49]Rahman Z,Jobson D.J,Woodell G. A. Retinex processing for automatic image enhancement[J]. Journal of Electronic Imaging, 2004,13(1):100-110
[50]Tumblin J,Turk G. a boundary hierarchy for detail preserving contrast reduction [C] Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH. Los Angeles, 1999: 83-90
[51]Choudhury P,Tumblin. The trilateral filter for high contrast images and meshes [C] Proceedings of Eurographics Symposium on Rendering,2003: 1-11
[52]H.T. Ngo, K.V. Asari, M.Z. Zhang, L. TaoDesign of a systolic-pipelined architecture for real-time enhancement of color video stream based on an illuminance/reflectance model Integration[J], the VLSI Journal, 41 (2008), pp. 474-488
[53]J. luc Starck, F. Murtagh, E. J. Cands, E. J. C, and D. L. Donoho. Gray and color image contrast enhancement by the curvelet transform[J]. IEEE TIP, 12, 2003.
[54]Anustup Choudhury, Gerard G. Medioni. Perceptually Motivated Automatic Color Contrast Enhancement[J]. IEEE International Conference on Computer Vision, Color and Reflectance in Imaging and Computer Vision Workshop, October 2009
[55]Horn, B. K. P., "Determinig lightness from an image[J]," Computer Graphics and Image Processing 3,277-299 (1974)
[56]Blake, A., "Boundary conditions of lightness computation in mondrian world[J]," Computer Vision Graphics and Image Processing 32,314-327 (1985)
[57]Terzopoulos, D.1986. Image analysis using multigrid relaxationmethods[J]. IEEE Trans. on PAMI,8:129-139.
[58]J. M.Morel, A. B. Petro, and C. Sbert. Fast implementation of color constancy algorithms[J]. Proc. SPIE, 7241, 724106, 2009. DOI:10.1117/12.805474
[59]E. J. Candes, M. Rudelson, T. Tao, and R. Vershynin. Error correction via linear programming[J]. In Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science, 2005
[60]W. Ma, S. Osher, A TV Bregman iterative model of Retinex theory. [J] CAM Report 10-13, 2010
[61]李明.杨艳屏TV—Retinex:一种快速图像增强算法计算机辅助设计与图形学学报[J]VOI.10 2O10.10: 1778-1782
[62]唐亮.谢维信,黄建军,市航空影像中基于模糊Retinex的阴影消除[J].电子学报Vol. 33 No. 3 2005.3: 498-503
[63]唐磊赵春霞.基于各向异性Retinex的路面图像阴影消除[J].中国图象图形学报Vol. 13. No. 2 2008.2: 264-268
[64]徐冠雷,王孝通,基于限邻域EMD的图像增强[J].电子学报Vol. 34 NO. 9 2006.9: 1635-1639
[65]汪荣贵张新龙.基于Retinex理论的压缩域图像增强方法研究计算机研究与发展[J]48(2)：259-270,2011
[66]许欣,陈强.消除光晕现象的快速Retinex图像增强[J].计算机辅助设计与图形学学报o1_20,No.10.2008.10：1325-1331
[67]令雷,周荫清,李景文Retinex理论在航空影像增强中的应用[J].系统工程与电子技术,2008,7(30)：1382一1385
[68]王湘晖,曾明.基于视觉感知的图像增强质量客观评价算法[J].光电子·激光,2008,19(2)：258-262
[69]邵桂芳,李祖枢.基于视觉感知的融合图像质量评价[J].计算机应用,2004,24(5)：69-75
[70]Karanaseka S A, et al. A distortion measure for blocking artifacts in image based onhuman visual sensitivity[C]. IEEE Transactions on Image Processing,1995,4(6): 713-724
[71]Wang Zhou,Bovik A C, et al. Image quality assessment from error visibility to structural similarity[C]. IEEE Transactions on Image Processing,2004,13(4): 600. 612
[72]祁云平,马慧芳,张其善.基于PSNR与SSM联合的图像质量评价模型[J].计算机应用,2007,27(2)：503-506
[73]杨春玲,旷开智,陈冠豪,谢胜利.基于梯度的结构相似度的图像质量评价方[J].计算机应用,2007:507-510
[74]佟雨兵,张其善,常青.基于NN与SVM的图像质量评价模型[J].北京：航空航天大学学报,2006,32(9)：1031-1034
[75]D.Jobson, Z. ur Rahman, and G. A. Woodell. The statistics of visual representation[C]. In Visual Information Processing, page pp., 2002
[76]徐燕.基于多尺度理论改进的分水岭医学图像分割算法[J].中国医学物理学杂志,2007, 24(2)：99-101.
[77]刘金华,龙图景.一种改进的模糊边缘检测快速算法[J].系统仿真学报,2003,2(2)：273-274.
[78]Yang Zhang. Research on Key Technologies of Video Processing System on Railway Handcarts [D]. Beijing: Beijing Jiaotong University. 2008.
[79]Jiang Chang. Research and achievement of key technologies of railway handcarts video processing system. [M] Beijing: Beijing Jiaotong University. 2009.
[80]Jin Huang.An image-based Method for fastener Inspection[C]. International Conference on Railway. Engineering Beijing. 2012.
[2]L. Tao, Tompkins r, Asari v. An illuminance-reflectance model for nonlinear enhancement of color images[C] Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition: Vol 3, Jan 20-26, 2005, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2005:159.
[3]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2001.
[4]Oppenheim A.V.Speech analysis-synthesis system based on homomorphic filtering. JASAournal of the Acoustical Society of America[J],1969,45(2):460-465
[5]Fries R,Modestino J.Image enhancement by stochastic homomorphic filtering[C].IEEE Transactions on Acoustics,Speech,and Signal Processing,1979,27(6):627-637
[6]Polesel,Ramponi,Mathews.Image enhancement via adaptive unsharp masking[C].IEEE Transactions on Image Processing,2000,9(3):505-510
[7]Srinivasa D.R,Image Enhancement Using Integer Sequences Based Windows[C], PICC, Kongu Engineering College, 2010. pp. 498-502
[8]Guillon S,Baylou P,Najim.Adaptive nonlinear filters for 2D and 3D image enhancement.[C] Signal Processing, 1998,67(3):237-254
[9]陈强,纪则轩,孙权森.基于光能分配的遥感图像增强[J].中国图像图形学报,2009,14(11)： 2284-2291
[10]马江林,赵忠明.海量遥感图像频域编辑器软件的设计与实现[M].计算机工程.2007,33(1)
[11]Marini, D. and Rizzi, A., A computational approach to color adaptation effects[C], Image and Vision Computing 2000,18:1005-1014
[12]Morel, J.M. Petro, A.B. Sbert, C. A PDE Formalization of Retinex Theory[C]. IEEE Transactions on Image Processing, Nov.2010,19 Issue:11.pp2825-2837
[13]Kimmel R. Elad M. Shaked D. et al. A variational framework for Retinex[C]. International Journal of Computer Vision. 2003,52(1):8-23
[14]Xiaolin Wu, A Linear Programming Approach for Optimal Contrast-Tone Mapping[C],ECCV,2011.1262-1272
[15]Fattal R,Lischinski D,Werman M.Gradient domain high dynamic range compression[C]. Computer Graphics Proceedings,ACM,2002.249-256
[16]Meylan I Sfisstrunk S. High dynamic range image rendering with a retinex based adaptive filter[C]. IEEE Transactions on Image Processing,2006,15(9):2826-2830
[17]Meylan L.Tone mapping for high dynamic range images[J]. Thesis,Ecole Polytechnique Federale de Lausanne,Lausanne,Switzerland,2Q06.
[18]Krawczyk G,Myszkowski K,Seidel P.Lightness perception in tone reproduction for high dynamic range images[J].Computer G Graphics Forum,2005,24(11):635-645
[19]AGGARWAL, M., AND AHUJA, N. High dynamic range panoramic imaging[C]. In Proc.IEEE ICCV,vol.I,2001.2-9
[20]Raanan Fattal, Dani Lischinski, Michael Werman. Gradient Domain High Dynamic Range Compression full Full[J] ACM SIGGRAPH 2002.
[21]Rafal Mantiuk, Karol Myszkowski, Hans-Peter Seidel. A Perceptual Framework for Contrast Processing of High Dynamic Range Images [C]. In ACM Transactions on Applied Perception, 2006.:286-308
[22]Grzegorz Krawczyk, Karol Myszkowski, Hans-Peter Seidel,Computational Model of Lightness Perception in High Dynamic Range Images [J].In: Proc. of IS&T/SPIE's Human Vision and Electronic Imaging, 2006.
[23]Fredo Durand,Julie Dorsey.A Fast Approximation of the Bilateral Filter using a Signal Processing Approach[J]. MIT technical report 2006 (MIT-CSAIL-TR-2006-073)
[24]E.H. Land,J McCann. Lightness and Retinex theory[J]. Opt SocAmer,1971.61(1):1-11.
[25]S. Shwartz, E. Namer, and Y. Schechner. Blind haze separation[C].CVPR, 2006.
[26]R. Tan. Visibility in bad weather from a single image[C]. CVPR,2008.
[27]Kaiming He Jian Sun Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior[C].CVPR,2009,1956-1963
[28]Akito Yamasaki, Hidenori Takauji, Shun'ichi Kaneko.Denighting:Enhancement of Nighttime Images for a Surveillance Camera[C].ICPR,2008,1-4
[29]曹力,路吉林.基于DSP的夜晚图像增强技术[J].上海：微型电脑应用.2010.
[30]Barnard K,Cardei V,Funt B.A comparison of computational color constancy algorithms-part I;methodology and experiments with synthesized data[C].IEEE Transactions on Image Processing,2002,11(9):972-984
[31]Barnard K,Martin L,Coath A,Funt B.A comparison of computational color constancy algorithms methodology and experiments with synthesized data[C].IEEE Transactions on Image Processing,2002,11(9):985-996
[32]Provenzi E,Fierro M,Rizzi A, Carli L. Gadia D,Marini D.Random spray Retinex:a new Retinex implementation to investigate the local properties of the model[C].IEEE Transactions on Image Processing,2007,16 (1):162-171
[33]Rizzi A,Gatta C,Marin. A new algorithm for unsupervised global and local color correction[J]. Pattern Recognition Letters,2003,24(11):1663-1677
[34]Papoulis, A. Probability, Random Variables, and Stochastic Processes[C].3rd edn. McGraw-Hill: New York, 1991.pp. 345-346
[35]Provenzi E,Gatta C,Fierro M,Rizzi A.A spatially variant white-patch and gray-world method for color image enhancement driven by local contrast[C].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(10):1757-1770
[36]Rahman Z,Jobson D J,Woodell G A. Multi-scale retinex for color image enhancememt[C]. IEEE Image Processing, 1996,3: 1003-1006
[37]Jobson, D.J., Rahman, Z., and Woodell, G.A.. Properties and performance of the center/surround Retinex[C]. IEEE Trans, on Image Proc., 1997a.6:451-462.
[38]Jobson, D.J., Rahman, Z., and Woodell, G.A. A multiscale Retinex for bridging the gap between color imagesand the human observation of scenes[C].IEEE Transactions on Image Processing:Special Issue on Color Processing,1997,6(7):965-976.
[39]L. Tao, V.K. Asari, Modified luminance based MSR for fast and efficient image enhancement[C], Proceedings of the IEEE International Workshop on Applied Imagery and Pattern Recognition (AIPR), 2003, pp.174 - 179.
[40]E.H. Land. The Retinex theory of color visionC]. Sci. Amer.,237:108-128,1977.
[41]E.H. Land. Recent advances in the Retinex theory and some implications for cortical computations:Color vision and the natural image[C]. Proc. Nat. Acad. Sci. USA, 80:5163-5169, 1983.
[42]E.H. Land. An alternative technique for computation of the designator in the Retinex of color vision[C]. Proc. Nat. Acad. Sci. USA, 83:3078-3080, 1986.
[43]E H Land. An alternative technique for the computation of the designator in the Retinex theory of color vision[C]. Proceedings of the National Academy of Science of the United States of America,1986,83(10):3078-3080
[44]Provenzi, E., Rizzi, A., Carli, L. D., and Marini, D, Mathematical definition and analysis of the retinex algorithm[C], J. Opt. Soc. Am. A 22(12), 2613-2621 (2005).
[45]Wenye Ma; Morel, J.-M.; Osher, S.; Chien, A.; An L1-based variational model for Retinex theory and its application to medical imagesComputer Vision and Pattern Recognition[C],2011 IEEE Conference on Issue Date: 20-25 June 2011 On page(s):153 - 160
[46]Frankle, J. and McCann, J., "Method and apparatus for lightness imaging." US Patent (May 1983). Number Patent 4384336.
[47]Funt, B., Ciurea, F., and McCann, J., Retinex in matlab[C],J. of Electronic Imaging 13(1), 48-57 (2004).
[48]McCann, J., Lesson learned from mondrians applied to real images and color gamuts [C],Proc. IST/SID Seventh Color Imaging Conference, 1-8 (1999).
[49]Rahman Z,Jobson D.J,Woodell G. A. Retinex processing for automatic image enhancement[J]. Journal of Electronic Imaging, 2004,13(1):100-110
[50]Tumblin J,Turk G. a boundary hierarchy for detail preserving contrast reduction [C] Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH. Los Angeles, 1999: 83-90
[51]Choudhury P,Tumblin. The trilateral filter for high contrast images and meshes [C] Proceedings of Eurographics Symposium on Rendering,2003: 1-11
[52]H.T. Ngo, K.V. Asari, M.Z. Zhang, L. TaoDesign of a systolic-pipelined architecture for real-time enhancement of color video stream based on an illuminance/reflectance model Integration[J], the VLSI Journal, 41 (2008), pp. 474-488
[53]J. luc Starck, F. Murtagh, E. J. Cands, E. J. C, and D. L. Donoho. Gray and color image contrast enhancement by the curvelet transform[J]. IEEE TIP, 12, 2003.
[54]Anustup Choudhury, Gerard G. Medioni. Perceptually Motivated Automatic Color Contrast Enhancement[J]. IEEE International Conference on Computer Vision, Color and Reflectance in Imaging and Computer Vision Workshop, October 2009
[55]Horn, B. K. P., "Determinig lightness from an image[J]," Computer Graphics and Image Processing 3,277-299 (1974)
[56]Blake, A., "Boundary conditions of lightness computation in mondrian world[J]," Computer Vision Graphics and Image Processing 32,314-327 (1985)
[57]Terzopoulos, D.1986. Image analysis using multigrid relaxationmethods[J]. IEEE Trans. on PAMI,8:129-139.
[58]J. M.Morel, A. B. Petro, and C. Sbert. Fast implementation of color constancy algorithms[J]. Proc. SPIE, 7241, 724106, 2009. DOI:10.1117/12.805474
[59]E. J. Candes, M. Rudelson, T. Tao, and R. Vershynin. Error correction via linear programming[J]. In Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science, 2005
[60]W. Ma, S. Osher, A TV Bregman iterative model of Retinex theory. [J] CAM Report 10-13, 2010
[61]李明.杨艳屏TV—Retinex:一种快速图像增强算法计算机辅助设计与图形学学报[J]VOI.10 2O10.10: 1778-1782
[62]唐亮.谢维信,黄建军,市航空影像中基于模糊Retinex的阴影消除[J].电子学报Vol. 33 No. 3 2005.3: 498-503
[63]唐磊赵春霞.基于各向异性Retinex的路面图像阴影消除[J].中国图象图形学报Vol. 13. No. 2 2008.2: 264-268
[64]徐冠雷,王孝通,基于限邻域EMD的图像增强[J].电子学报Vol. 34 NO. 9 2006.9: 1635-1639
[65]汪荣贵张新龙.基于Retinex理论的压缩域图像增强方法研究计算机研究与发展[J]48(2)：259-270,2011
[66]许欣,陈强.消除光晕现象的快速Retinex图像增强[J].计算机辅助设计与图形学学报o1_20,No.10.2008.10：1325-1331
[67]令雷,周荫清,李景文Retinex理论在航空影像增强中的应用[J].系统工程与电子技术,2008,7(30)：1382一1385
[68]王湘晖,曾明.基于视觉感知的图像增强质量客观评价算法[J].光电子·激光,2008,19(2)：258-262
[69]邵桂芳,李祖枢.基于视觉感知的融合图像质量评价[J].计算机应用,2004,24(5)：69-75
[70]Karanaseka S A, et al. A distortion measure for blocking artifacts in image based onhuman visual sensitivity[C]. IEEE Transactions on Image Processing,1995,4(6): 713-724
[71]Wang Zhou,Bovik A C, et al. Image quality assessment from error visibility to structural similarity[C]. IEEE Transactions on Image Processing,2004,13(4): 600. 612
[72]祁云平,马慧芳,张其善.基于PSNR与SSM联合的图像质量评价模型[J].计算机应用,2007,27(2)：503-506
[73]杨春玲,旷开智,陈冠豪,谢胜利.基于梯度的结构相似度的图像质量评价方[J].计算机应用,2007:507-510
[74]佟雨兵,张其善,常青.基于NN与SVM的图像质量评价模型[J].北京：航空航天大学学报,2006,32(9)：1031-1034
[75]D.Jobson, Z. ur Rahman, and G. A. Woodell. The statistics of visual representation[C]. In Visual Information Processing, page pp., 2002
[76]徐燕.基于多尺度理论改进的分水岭医学图像分割算法[J].中国医学物理学杂志,2007, 24(2)：99-101.
[77]刘金华,龙图景.一种改进的模糊边缘检测快速算法[J].系统仿真学报,2003,2(2)：273-274.
[78]Yang Zhang. Research on Key Technologies of Video Processing System on Railway Handcarts [D]. Beijing: Beijing Jiaotong University. 2008.
[79]Jiang Chang. Research and achievement of key technologies of railway handcarts video processing system. [M] Beijing: Beijing Jiaotong University. 2009.
[80]Jin Huang.An image-based Method for fastener Inspection[C]. International Conference on Railway. Engineering Beijing. 2012.