恶劣天气环境下图像的清晰化
|
摘要
随着视频监测技术在各个领域越来越广泛的应用，要求系统的适用性也随着提高。为了使监测系统在恶劣的天气环境下仍然能够正常工作，提出了恶劣天气环境下的清晰化技术，以通过软件手段来达到强化微弱信息的目的。
本文主要针对雾天环境下图像的清晰化技术进行了研究。论文中首先对雾天的分类给出了介绍，并且分析了雾天下的成像模型的特点，以及由此带来的图像清晰化处理的困难。为了解决这些问题，论文分为两大类方法对图像进行处理，一类是基于模型的图像复原技术，一类是非建模的图像增强技术。由于轻雾天气和大雾天气下图像信息损失程度的不同，对它们分别采用不同的手段进行处理。采用图像自适分割方法以及图像局部增强方法对轻雾天气下的图像进行处理，在大幅度提高图像清晰度的同时避免了天空噪声的放大。对单深度图像的处理，则采用人机交互方式选取辐射黑点，后根据大气模型进行处理的方法，求取图像的光学深度，进而利用模型处理的方法恢复图像的信息。对变雾况的两幅同一场景的图像，采用差图像放大的方法，提高图像的清晰度并给出了理论证明。大雾天气下的图像由于其本身灰度范围有限的特点，采用动态范围拉伸的方法进行全局增强，并对其增强后出现的噪声干扰问题利用稀疏编码技术给予解决。
本论文的研究主要利用了计算机技术和图像处理技术来提高雾天下图像的
西安理工大学硕士学位论文
清晰度，对于提高户外全天候监测系统运行的鲁棒性的提高有着重大的意义，并
且对其他恶劣犬气下图像的清晰化处理也有一定的促进意义。
With the development of the video surveillance system techniques, the demands of system's reliability and stability have raised. In order to make video surveillance systems operate normally in bad weather, image clearness technique is proposed in the paper which aims to enhance weak information by software methods.
The paper studies on the image clearness technique in fog. Firstly, the classification of fog is introduced. Then the characteristic of atmospheric scattering models and the difficulty caused by these models are analyzed. To solve these problems, the paper presents two classes of ways: One based on image restoration technique and the other based on image enhancement technique. Due to the difference degree of information lost in haze and dense fog, different methods are adopted. Adaptive segmentation and local enhancement methods are used to process images taken in haze. As the result, higher contrast of image is obtained without noise magnification in sky region. Single depth image can easily be processed through models. Fist, black pixel whose radiance is zero is chosen mutually, then image optical depth is computed, at last image information is recovered, two images which
* This Work is supported by the Major Project of Science and Technology Research of Ministry of Education of China under Grant No: 01113
are taken in different degree of fog are processed by difference image information amplification. Results are satisfactory, besides theoretical proof also has been given. According to the characteristics that limited dynamic range of images taken in dense fog, dynamic range stretch as a global enhancement method is used. In order to reduce the effect of noise it brings, sparse coding is adopted.
In this paper, computer techniques and images process techniques are used to enhance the clearness of images taken in fog automatically, which has a great significance in improving the robustness of outdoor surveillance systems and also be helpful to the process of images taken in other bad weather.
本文主要针对雾天环境下图像的清晰化技术进行了研究。论文中首先对雾天的分类给出了介绍，并且分析了雾天下的成像模型的特点，以及由此带来的图像清晰化处理的困难。为了解决这些问题，论文分为两大类方法对图像进行处理，一类是基于模型的图像复原技术，一类是非建模的图像增强技术。由于轻雾天气和大雾天气下图像信息损失程度的不同，对它们分别采用不同的手段进行处理。采用图像自适分割方法以及图像局部增强方法对轻雾天气下的图像进行处理，在大幅度提高图像清晰度的同时避免了天空噪声的放大。对单深度图像的处理，则采用人机交互方式选取辐射黑点，后根据大气模型进行处理的方法，求取图像的光学深度，进而利用模型处理的方法恢复图像的信息。对变雾况的两幅同一场景的图像，采用差图像放大的方法，提高图像的清晰度并给出了理论证明。大雾天气下的图像由于其本身灰度范围有限的特点，采用动态范围拉伸的方法进行全局增强，并对其增强后出现的噪声干扰问题利用稀疏编码技术给予解决。
本论文的研究主要利用了计算机技术和图像处理技术来提高雾天下图像的
西安理工大学硕士学位论文
清晰度，对于提高户外全天候监测系统运行的鲁棒性的提高有着重大的意义，并
且对其他恶劣犬气下图像的清晰化处理也有一定的促进意义。
With the development of the video surveillance system techniques, the demands of system's reliability and stability have raised. In order to make video surveillance systems operate normally in bad weather, image clearness technique is proposed in the paper which aims to enhance weak information by software methods.
The paper studies on the image clearness technique in fog. Firstly, the classification of fog is introduced. Then the characteristic of atmospheric scattering models and the difficulty caused by these models are analyzed. To solve these problems, the paper presents two classes of ways: One based on image restoration technique and the other based on image enhancement technique. Due to the difference degree of information lost in haze and dense fog, different methods are adopted. Adaptive segmentation and local enhancement methods are used to process images taken in haze. As the result, higher contrast of image is obtained without noise magnification in sky region. Single depth image can easily be processed through models. Fist, black pixel whose radiance is zero is chosen mutually, then image optical depth is computed, at last image information is recovered, two images which
* This Work is supported by the Major Project of Science and Technology Research of Ministry of Education of China under Grant No: 01113
are taken in different degree of fog are processed by difference image information amplification. Results are satisfactory, besides theoretical proof also has been given. According to the characteristics that limited dynamic range of images taken in dense fog, dynamic range stretch as a global enhancement method is used. In order to reduce the effect of noise it brings, sparse coding is adopted.
In this paper, computer techniques and images process techniques are used to enhance the clearness of images taken in fog automatically, which has a great significance in improving the robustness of outdoor surveillance systems and also be helpful to the process of images taken in other bad weather.
引文
[1] L..Pirodda. Enhancing Visibility Through Fog. 1997, Optics & Laser Technology. Vol. 29 (No. 6):293-299.
[2] John P. Oakley, Brenda L. Satherley. Improving Image Quality in Poor Visibility Conditions Using a Physical Model for Contrast Degradation. IEEE Transactions on image Processing. Vol.14 (No. 3), 1998: 167-179.
[3] KokKeong Tan, Oakley, J.P. Enhancement of Color Images in Poor Visibility Conditions. International Conference on Image Processing. Vol. 2, 2000: 788-791.
[4] S.G. Narasimhan, S. K. Naya. Contrast Restoration of Weather Degraded Images. IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI). Vol. 25 (No. 6), 2003:713-724.
[5] Y. Y. Schechner, S. G. Narasimhan ,S. K. Nayar. Polarization-Based Vision through Haze. Applied Optics, Special issue "Light and Color in the Open Air". Vol. 42 (No. 3), 2003:511-525.
[6] S.G. Narasimhan, S. K. Nayar. Vision and the Atmosphere. International Journal of Computer Vision (IJCV). Vol. 48 (No. 3), 2002: 233-254.
[7] Srinivasa G. Narasimhan, Chi Wang, Shree K. Nayar. All the Images of an Outdoor Scene. Proceedings of the 7th European Conference on Computer Vision-Part Ⅲ. 2002:148-162.
[8] Y. Y. Schechner, S. G. Narasimhan, s. K. Nayar. Instant Dehazing of Images Using Polarization. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Vol. 1, 2001:325-332.
[9] S.G. Narasimhan, S. K. Nayar. Removing Weather Effects from Monochrome Images. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Vol. 2, 2001: 186-193.
[10] S. G. Narasimhan, S. K. Nayar. Chromatic Framework for Vision in Bad Weather. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Vol. 1, 2000: 1598-1605.
[11] S. K. Nayar, S. G. Narasimhan. Vision in Bad Weather. Proceedings of IEEE International Conference on Computer Vision. Vol. 2, 1999:820-827.
[12] S. G. Narasimhan, S. K. Nayar. Vision and the Atmosphere. International Journal of Computer Vision. Vol. 48(No. 3), 2002:233-254.
[13] Shree Nayar, Terry Boult. Human Identification in Bad Weather Quarterly Progress Report. wwwl. cs. columbia, edu/CAVE/HIDweather/reports/progress_July15_03_quarterly, ppt.
[14] V.R. Yazdanpanah, K. Ghafoori, Tabrizi. Application of Image Processing in Air Pollution Control. http://comp.uark.edu/~yazdan/Application.doc.
[15] C. Busch, E. Debes. Wavelet Transform for Analyzing Fog Visibility. IEEE Intelligent Systems & their applications, Vision-based driving assistance. 1998:66-71.
[16] 谢兴生，陶善昌．数字摄像法测量气象能见度．科学通报．vol．44，1999：97-100．
[17] Cozman, F., Krotkov E.. Depth from Scattering. Conference on Computer Vision and Pattern Recognition. 1997:801-806.
[18] 章毓晋．图象工程(上册)．清华大学出版社．1999：19-20．
[19] Masashi Matsuoka, Fumio Yamazaki. Detection of Damage Due to the 2001 El Salvador Earthquake Using Landsat Images. The 22nd Asian Conference on Remote Sensing. Vol. 2, 2001:1372-1377.
[20] 黄凯奇，王桥，吴镇扬，胡学龙．基于人眼视觉特征的多尺度彩色图象增强算法．中国图象图形学报．Vol．8(No．11)，2003：1242-1246．
[21] Paul E. Debevec, Jitendra Malik. Recovering High Dynamic Range Radiance Maps from Photographs. Siggraph Proceedings 1997:130-135.
[22] S. K. Nayar, T. Mitsunaga. High Dynamic Range Imaging: Spatially Varying Pixel Exposures. Proceeding Of Computer Vision and Pattern Recognition. Vol. 1, 2000:472-479.
[23] Y. Tsin, V. Ramesh, T. Kanade. Statistical Calibration of CCD Imaging Process. IEEE International Conference on Computer Vision., Vol. 1, 2001:480-487.
[24] T. Mitsunaga and S. K. Nayar. Radiometric Self Calibration. Proceeding Of Computer Vision and Pattern Recognition. Vol. 2, 1999:374-380.
[25] 杨枝灵，王开．数字图像获取 处理及实践应用，人民邮电出版社．2003：201-208．
[26] 钱徽，牛淼良．自然景物中大气退化模型的研究．计算机辅助设计与图形学学报．Vol．13(No．9)，2001：793-799．
[27] 钱徽，牛淼良．大气退化的自然山体图像复原研究．计算机辅助没计与图形学学报．Vol．14(No．6)，2002：526-529．
[28] 罗成平，龚沛曾．图象匹配技术．微型电脑应用．Vol．16(No．3)，2000：26-28．
[29] 附忠良．图象阈值选取方法的构造．中国图象图形学报．Vol．5(No．6)，2000：466-469．
[30] 谷口庆治．数字图像处理-基础篇．科学出版社．2002：81-83．
[31] 何斌，马天予．王云坚，朱红莲．Visual C++数字图像处理．人民邮电出版社．2001：78-151．
[32] 阮秋琦．数字图像处理学．电子工业出版社．2001：180-212．
[33] Kenneth R．Castleman．数字图像处理．电子工业出版社．2002：75-76．
[34] 陈冬青 谢洪波 郁道银．基于照明反射模型的内窥镜图象增强方法研究．中国生物医学工程学报。Vol．19(No．4)，2000：378-382．
[35] 郝志琦．同态滤波图象增强在微粒场全息图图象处理中的应用．光子学报．Vol．27(No．8)，1998：764-767．
[36] 王猛，白洪亮．同态滤波器在水下图像对比度增强中的应用．应用科技．Vol．30(No．7)，2003：15-17．
[37] 朱述龙．基于小波理论的影像增强技术．测绘通报．No．2，1996：12-13．
[38] 董汉丽．基于小波变换的图像增强方法研究．郑州纺织工学院学报．Vol．10(No．3)，1999，9：40-43．
[39] 吴颖谦，施鹏飞．基于小波变换的低对比度图像增强．红外与激光工程．Vol．32(No．1)．2003：4-7．
[40] T.O. Ozanian, R.Phillips. Enhancement of Fluoroscopic Images with Yarying Contrast. Computer Methods and Programs in Biomedicine. Vol. 65, 2001:1-16.
[41] Bruce A. Thomas, Robin N. Strickland, Jeffrey J. Rodriguez. Color Image Enhancement Using Spatially Adaptive Saturation Feedback. International Conference on Image Processing. Vol. 3, 1997:30-33.
[42] T.-L. Ji, M. K. Sundareshan, H. Roehrig. Adaptive image contrast
enhancement based on human visual properties. IEEE Transactions on Medical IMaging. Vol. 4, 1994:573-586.
[43] Antonella Carbonaro, Primo Zingaretti. A Comprehensive Approach to Image-Contrast Enhancement. International Conference on Image Analysis and Processing. 1999:241-246.
[44] Dah-Chung Chang, Wen-Rong Wu. Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation. IEEE Transaction on Medical Imaging. Vol. 17 (No. 4), 1998:518-531.
[45] Kim Tae Keun, Paik Joon Ki, Kang Bong Soon. Contrast Enhancement system using spatially adaptive histogram equalization with temporal filtering. IEEE Transactions on Consumer Electronics. Vol. 44 (No.1), 1998:82-86.
[46] Kim Joung-Youn, Kim Lee-Sup, Hwang Seung-Ho. An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization. IEEE Transactions on Circuits and Systems for Video Technology. Vol. 11 (No. 4), 2001:475-484.
[47] Z.Q. Wu, J.A. Ware, W.R. Stewart, J. Jiang. The Removal of Blocking Effects Caused by Partially Overlapped Sub-Block Contrast Enhancement. http://digita]imaging.inf.brad.ac.uk/publication/peter2.pdf.
[48] Hung-shung Wong, Jung-hua Wang. Contrast Enhancement Based on Divided Histogram Manipulation. IEEE International Conference on Systems, Man, and Cybernetics. Vol. 2, 2000:1551-1555.
[49] 沈嘉励．张宁．王秀坛．一种夜视图象处理的新算法．中国图象图形学报．Vol．5(No．6)，2000：479-483．
[50] 祝培，朱虹，钱学明，李晗．一种有雾天气图象景物影像的清晰化方法．中国图象图形学报．已录用．
[51] Patrik Hoyer. Independent Component Analysis in Image Denoising.
Master' s Thesis, Helsinki University of technology. 1999.
[52] Aapo Hyvrinea, Patrik Hoyer, Erkki Oja. Sparse Code Shrinkage: Denoising by Nonlinear Maximum Likelihood Estimation. Advances in Neural Information Processing Systems 11. 1998:473-479.
[53] Aapo Hyvrinen, Patrik Hoyer. Image Denoising by Sparse Code Shrinkage, Intelligent Signal Processing, IEEE Press 2000.
[54] 杨竹青．毛锦．胡德文．独立成分分析方法在图象处理中的应用．计算机工程与科学．vol．24(No．5)．2002：65-67．
[55] 彭煊，刘金福，王炳锡．基于独立分量分析的语音增强．信号处理．Vol．18(No．5)．2002：477-479．
[56] 康睿．基于盲源分离的图像噪声滤除．曲安理工大学学士论文．2003．
[57] Aapo Hyvrinen. Survey on Independent Component Analysis. Neual Computing Survery. Vol. 2, 1999:94-128.
[58] A. Hyvrinen, E. Oja. A Fast Fixed-Point Algorithm for Independent Component Analysis, Neural Computation. Vol. 9(No. 7), 1997:1483-1492.
[2] John P. Oakley, Brenda L. Satherley. Improving Image Quality in Poor Visibility Conditions Using a Physical Model for Contrast Degradation. IEEE Transactions on image Processing. Vol.14 (No. 3), 1998: 167-179.
[3] KokKeong Tan, Oakley, J.P. Enhancement of Color Images in Poor Visibility Conditions. International Conference on Image Processing. Vol. 2, 2000: 788-791.
[4] S.G. Narasimhan, S. K. Naya. Contrast Restoration of Weather Degraded Images. IEEE Transactions on Pattern Analysis and Machine Intelligence(PAMI). Vol. 25 (No. 6), 2003:713-724.
[5] Y. Y. Schechner, S. G. Narasimhan ,S. K. Nayar. Polarization-Based Vision through Haze. Applied Optics, Special issue "Light and Color in the Open Air". Vol. 42 (No. 3), 2003:511-525.
[6] S.G. Narasimhan, S. K. Nayar. Vision and the Atmosphere. International Journal of Computer Vision (IJCV). Vol. 48 (No. 3), 2002: 233-254.
[7] Srinivasa G. Narasimhan, Chi Wang, Shree K. Nayar. All the Images of an Outdoor Scene. Proceedings of the 7th European Conference on Computer Vision-Part Ⅲ. 2002:148-162.
[8] Y. Y. Schechner, S. G. Narasimhan, s. K. Nayar. Instant Dehazing of Images Using Polarization. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Vol. 1, 2001:325-332.
[9] S.G. Narasimhan, S. K. Nayar. Removing Weather Effects from Monochrome Images. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Vol. 2, 2001: 186-193.
[10] S. G. Narasimhan, S. K. Nayar. Chromatic Framework for Vision in Bad Weather. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Vol. 1, 2000: 1598-1605.
[11] S. K. Nayar, S. G. Narasimhan. Vision in Bad Weather. Proceedings of IEEE International Conference on Computer Vision. Vol. 2, 1999:820-827.
[12] S. G. Narasimhan, S. K. Nayar. Vision and the Atmosphere. International Journal of Computer Vision. Vol. 48(No. 3), 2002:233-254.
[13] Shree Nayar, Terry Boult. Human Identification in Bad Weather Quarterly Progress Report. wwwl. cs. columbia, edu/CAVE/HIDweather/reports/progress_July15_03_quarterly, ppt.
[14] V.R. Yazdanpanah, K. Ghafoori, Tabrizi. Application of Image Processing in Air Pollution Control. http://comp.uark.edu/~yazdan/Application.doc.
[15] C. Busch, E. Debes. Wavelet Transform for Analyzing Fog Visibility. IEEE Intelligent Systems & their applications, Vision-based driving assistance. 1998:66-71.
[16] 谢兴生，陶善昌．数字摄像法测量气象能见度．科学通报．vol．44，1999：97-100．
[17] Cozman, F., Krotkov E.. Depth from Scattering. Conference on Computer Vision and Pattern Recognition. 1997:801-806.
[18] 章毓晋．图象工程(上册)．清华大学出版社．1999：19-20．
[19] Masashi Matsuoka, Fumio Yamazaki. Detection of Damage Due to the 2001 El Salvador Earthquake Using Landsat Images. The 22nd Asian Conference on Remote Sensing. Vol. 2, 2001:1372-1377.
[20] 黄凯奇，王桥，吴镇扬，胡学龙．基于人眼视觉特征的多尺度彩色图象增强算法．中国图象图形学报．Vol．8(No．11)，2003：1242-1246．
[21] Paul E. Debevec, Jitendra Malik. Recovering High Dynamic Range Radiance Maps from Photographs. Siggraph Proceedings 1997:130-135.
[22] S. K. Nayar, T. Mitsunaga. High Dynamic Range Imaging: Spatially Varying Pixel Exposures. Proceeding Of Computer Vision and Pattern Recognition. Vol. 1, 2000:472-479.
[23] Y. Tsin, V. Ramesh, T. Kanade. Statistical Calibration of CCD Imaging Process. IEEE International Conference on Computer Vision., Vol. 1, 2001:480-487.
[24] T. Mitsunaga and S. K. Nayar. Radiometric Self Calibration. Proceeding Of Computer Vision and Pattern Recognition. Vol. 2, 1999:374-380.
[25] 杨枝灵，王开．数字图像获取 处理及实践应用，人民邮电出版社．2003：201-208．
[26] 钱徽，牛淼良．自然景物中大气退化模型的研究．计算机辅助设计与图形学学报．Vol．13(No．9)，2001：793-799．
[27] 钱徽，牛淼良．大气退化的自然山体图像复原研究．计算机辅助没计与图形学学报．Vol．14(No．6)，2002：526-529．
[28] 罗成平，龚沛曾．图象匹配技术．微型电脑应用．Vol．16(No．3)，2000：26-28．
[29] 附忠良．图象阈值选取方法的构造．中国图象图形学报．Vol．5(No．6)，2000：466-469．
[30] 谷口庆治．数字图像处理-基础篇．科学出版社．2002：81-83．
[31] 何斌，马天予．王云坚，朱红莲．Visual C++数字图像处理．人民邮电出版社．2001：78-151．
[32] 阮秋琦．数字图像处理学．电子工业出版社．2001：180-212．
[33] Kenneth R．Castleman．数字图像处理．电子工业出版社．2002：75-76．
[34] 陈冬青 谢洪波 郁道银．基于照明反射模型的内窥镜图象增强方法研究．中国生物医学工程学报。Vol．19(No．4)，2000：378-382．
[35] 郝志琦．同态滤波图象增强在微粒场全息图图象处理中的应用．光子学报．Vol．27(No．8)，1998：764-767．
[36] 王猛，白洪亮．同态滤波器在水下图像对比度增强中的应用．应用科技．Vol．30(No．7)，2003：15-17．
[37] 朱述龙．基于小波理论的影像增强技术．测绘通报．No．2，1996：12-13．
[38] 董汉丽．基于小波变换的图像增强方法研究．郑州纺织工学院学报．Vol．10(No．3)，1999，9：40-43．
[39] 吴颖谦，施鹏飞．基于小波变换的低对比度图像增强．红外与激光工程．Vol．32(No．1)．2003：4-7．
[40] T.O. Ozanian, R.Phillips. Enhancement of Fluoroscopic Images with Yarying Contrast. Computer Methods and Programs in Biomedicine. Vol. 65, 2001:1-16.
[41] Bruce A. Thomas, Robin N. Strickland, Jeffrey J. Rodriguez. Color Image Enhancement Using Spatially Adaptive Saturation Feedback. International Conference on Image Processing. Vol. 3, 1997:30-33.
[42] T.-L. Ji, M. K. Sundareshan, H. Roehrig. Adaptive image contrast
enhancement based on human visual properties. IEEE Transactions on Medical IMaging. Vol. 4, 1994:573-586.
[43] Antonella Carbonaro, Primo Zingaretti. A Comprehensive Approach to Image-Contrast Enhancement. International Conference on Image Analysis and Processing. 1999:241-246.
[44] Dah-Chung Chang, Wen-Rong Wu. Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation. IEEE Transaction on Medical Imaging. Vol. 17 (No. 4), 1998:518-531.
[45] Kim Tae Keun, Paik Joon Ki, Kang Bong Soon. Contrast Enhancement system using spatially adaptive histogram equalization with temporal filtering. IEEE Transactions on Consumer Electronics. Vol. 44 (No.1), 1998:82-86.
[46] Kim Joung-Youn, Kim Lee-Sup, Hwang Seung-Ho. An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization. IEEE Transactions on Circuits and Systems for Video Technology. Vol. 11 (No. 4), 2001:475-484.
[47] Z.Q. Wu, J.A. Ware, W.R. Stewart, J. Jiang. The Removal of Blocking Effects Caused by Partially Overlapped Sub-Block Contrast Enhancement. http://digita]imaging.inf.brad.ac.uk/publication/peter2.pdf.
[48] Hung-shung Wong, Jung-hua Wang. Contrast Enhancement Based on Divided Histogram Manipulation. IEEE International Conference on Systems, Man, and Cybernetics. Vol. 2, 2000:1551-1555.
[49] 沈嘉励．张宁．王秀坛．一种夜视图象处理的新算法．中国图象图形学报．Vol．5(No．6)，2000：479-483．
[50] 祝培，朱虹，钱学明，李晗．一种有雾天气图象景物影像的清晰化方法．中国图象图形学报．已录用．
[51] Patrik Hoyer. Independent Component Analysis in Image Denoising.
Master' s Thesis, Helsinki University of technology. 1999.
[52] Aapo Hyvrinea, Patrik Hoyer, Erkki Oja. Sparse Code Shrinkage: Denoising by Nonlinear Maximum Likelihood Estimation. Advances in Neural Information Processing Systems 11. 1998:473-479.
[53] Aapo Hyvrinen, Patrik Hoyer. Image Denoising by Sparse Code Shrinkage, Intelligent Signal Processing, IEEE Press 2000.
[54] 杨竹青．毛锦．胡德文．独立成分分析方法在图象处理中的应用．计算机工程与科学．vol．24(No．5)．2002：65-67．
[55] 彭煊，刘金福，王炳锡．基于独立分量分析的语音增强．信号处理．Vol．18(No．5)．2002：477-479．
[56] 康睿．基于盲源分离的图像噪声滤除．曲安理工大学学士论文．2003．
[57] Aapo Hyvrinen. Survey on Independent Component Analysis. Neual Computing Survery. Vol. 2, 1999:94-128.
[58] A. Hyvrinen, E. Oja. A Fast Fixed-Point Algorithm for Independent Component Analysis, Neural Computation. Vol. 9(No. 7), 1997:1483-1492.