基于人类视觉特性的结构相似度图像质量评价
|
摘要
随着网络及数字技术的发展,数字图像已广泛深入人们的日常生活,成为信息传递的重要载体。然而在现实生活中,由于各种因素的影响会使图像产生失真,影响传递的信息的质量,因此开展图像质量评价技术的研究,具有十分重要的现实意义。
主观评价方法是最准确的评价方法,但是耗时耗力,并且过程十分繁琐,因此在实际中很难应用。均方差和峰值信噪比等传统的客观评价方法不符合人的主观感受。一些简单地模拟人眼功能的图像质量评价方法能够较好地反映人的主观感受,但是人类视觉特性十分复杂,且目前的研究尚不够深入,所以其发展受到很大的限制。Zhou Wang等人提出了一种基于结构相似度的图像质量评价方法,该方法简单高效,在主客观一致性方面取得了更好的效果。
本文在深入研究人类视觉特性和结构性相似理论等地基础上,提出一种基于人类视觉特性的结构相似度图像质量评价方法。通过小波变换将原始图像和待测图像分解为不同频带和方向上的子带图像,分别计算各个对应子带图像的结构相似度值,并利用对比度敏感函数曲线计算人眼对每幅子带图像的敏感度,最终将所有图像的相似度值加权处理得到一个综合的测度值。通过仿真分析,结果表明本文提出的方法比传统的客观评价方法和基于结构相似度的评价方法更有效,其客观评价结果与人的主观感受具有更高的一致性。
With the development of the internet and digital technology, digital image has gone deep into people's daily lives thoroughly, which has become the most important carrier of information. However, the image will always be distorted by varities of factors in real life, which will reduce the quality of the information. Therefore, the study of image quality assessment technique has a very important practical significance.
Subjective evaluation is the most accurate evaluation method, but it costs too much manpower and time, and the process is too complicated to use in practice. Some traditional objective evaluation methods, such as MSE and PSNR, cann't reflect people's subjective feelings. Some methods of image quality evaluation which can simpy simulate the function of human eyes can reflect the people's subjective feelings better, but they are limited by the complexity of HVS and the unsolved problems. Zhou Wang proposed a simple and efficient method which based on the structure similarity theory, this method, too some extent, can objectively reflect people's subjective feelings.
This paper through in-depth research on HVS and structure similarity theory to propose a structure similarity method based on HVS. Firstly, the original image and the target image are decomposed into sub-band images in different frequency and directions by wavelet transform, and the SSIM values of every sub-band image are calculated according to the SSIM method. And then, the sensitivity values of each sub-band image will be got by using the contrast sensitivity function curve. Finally, a comprehensive value can be obtained by weighting the SSIM values of all sub-band images. Through the simulation and analysis, the results show that the method proposed in this paper is more effective than the traditional evaluation method and the SSIM method, and it reflects the people's subjective feeling with higher accuracy.
主观评价方法是最准确的评价方法,但是耗时耗力,并且过程十分繁琐,因此在实际中很难应用。均方差和峰值信噪比等传统的客观评价方法不符合人的主观感受。一些简单地模拟人眼功能的图像质量评价方法能够较好地反映人的主观感受,但是人类视觉特性十分复杂,且目前的研究尚不够深入,所以其发展受到很大的限制。Zhou Wang等人提出了一种基于结构相似度的图像质量评价方法,该方法简单高效,在主客观一致性方面取得了更好的效果。
本文在深入研究人类视觉特性和结构性相似理论等地基础上,提出一种基于人类视觉特性的结构相似度图像质量评价方法。通过小波变换将原始图像和待测图像分解为不同频带和方向上的子带图像,分别计算各个对应子带图像的结构相似度值,并利用对比度敏感函数曲线计算人眼对每幅子带图像的敏感度,最终将所有图像的相似度值加权处理得到一个综合的测度值。通过仿真分析,结果表明本文提出的方法比传统的客观评价方法和基于结构相似度的评价方法更有效,其客观评价结果与人的主观感受具有更高的一致性。
With the development of the internet and digital technology, digital image has gone deep into people's daily lives thoroughly, which has become the most important carrier of information. However, the image will always be distorted by varities of factors in real life, which will reduce the quality of the information. Therefore, the study of image quality assessment technique has a very important practical significance.
Subjective evaluation is the most accurate evaluation method, but it costs too much manpower and time, and the process is too complicated to use in practice. Some traditional objective evaluation methods, such as MSE and PSNR, cann't reflect people's subjective feelings. Some methods of image quality evaluation which can simpy simulate the function of human eyes can reflect the people's subjective feelings better, but they are limited by the complexity of HVS and the unsolved problems. Zhou Wang proposed a simple and efficient method which based on the structure similarity theory, this method, too some extent, can objectively reflect people's subjective feelings.
This paper through in-depth research on HVS and structure similarity theory to propose a structure similarity method based on HVS. Firstly, the original image and the target image are decomposed into sub-band images in different frequency and directions by wavelet transform, and the SSIM values of every sub-band image are calculated according to the SSIM method. And then, the sensitivity values of each sub-band image will be got by using the contrast sensitivity function curve. Finally, a comprehensive value can be obtained by weighting the SSIM values of all sub-band images. Through the simulation and analysis, the results show that the method proposed in this paper is more effective than the traditional evaluation method and the SSIM method, and it reflects the people's subjective feeling with higher accuracy.
引文
[1]谭耀麟.图像信息系统原理.北京：清华大学出版社,2006
[2]毕厚杰.图像通信工程.北京：人民邮电出版社,1991
[3]Zhou Wang, Alan C. Bovik, Ligang Lu. Why is Image Quality Assessment so Difficult. In Proc. IEEE Int. Con. Acoustics, Speech, and Signal Processing, Florida USA.2002,4: 3313-3316
[4]Scott Daly. The Visible Difference Predictor:An Algorithm for The Assessment of Image Fidelity. In Digital Images and Human Vision, A. B Watson, ed. Aambridge, MA: The MIT Press,1993,179-206
[5]Jeffrey Lubin. A Visual Discrimination Model for Image Syetem Design and Evaluation. In Visual Models for Target Detection and Recognition, E. Peli, ed. Singapore, World Scientific,1995,207-220
[6]R. J. Safranek, J. D. Johnson. A Perceptually Tuned Sub-band Image Coder with Image Dependent Quantization and Post-quantization Data Compression. In Proc. IEEE Int. Con. Acoustics, Speech, and Signal Processing,1989,1945-1948
[7]Reddy B.S, Chatterji B.N. An FFT-based technique for translation, rotation and scale-invariant image registration. IEEE Transaction on Image Processing,1996,5(8): 1266-127
[8]Andre B. Watson. DCT Quantization Matrices Visually Optimized for Individual Images.In Proc. SPIE Human Vision, Visual Processing and Digital Display IV, Bellingham, WA, USA,1993,1913(14):202-216
[9]Andre B. Watson, G. Y. Yang, J. A. Solomon. Visibility of Wavelet Quantization Noise. IEEE Trans. Image Processing,1997,6(8):1164-1175
[10]Zhou Wang, Alan C. Bovic, Hamid R. Sheikh. Image Quality Assessment:from Error Visibility to Structural Similarity. IEEE Trans. Processing,2004,13(4):600-612
[11]Guan-Hao Chen, Chun-Ling Wang and Sheng-Li Xie.Gradient-Based Structural Similarity for Image Quality Assessment. IEEE International Conference on Image Processing, Atlanta, GA 1,2006:2929-2932
[12]X. B. Gao, T Wang, J. Li. A Content-Based Image Quality Metric. D. Slezak et al. (EDs.): RSFDGrC2005, Lecture Notes in Artificial Intelligence, LNAI3642,2005:231-240 1986
[13]Makoto Miayahar, Kazunori Kotani, Ralph V. Algazi. Objective Picture Quality Scale for Image Coding. IEEE Trans. Communications,1998,46(9):1215-1225
[14]Aleksandr Shnayderman, Alexander Gusev, Ahmet M. Eskicioglu. An Image Quality Measure for Local and Global Assessment. IEEE Trans. Image Processing,2006,15(2): 422-429
[15]Damon M. Chandler, Sheila S. Hemami. A Wavelet-based Visual Signal-to-Noise Ratio for Natural Images. IEEE. Trans. Image Processing,2007,16(9):2284-2298
[16]Hamid R. Sheikh, Alan C. Bovic. Image Information and Visual Quality. IEEE. Trans. Image Processing,2006,15(2):430-444
[17]Van Dijk.H, J.B. Martens. Subjective quality assessment of compressed images. Signal Processing,1997,58(1):235-252
[18]周景超,戴汝为,肖柏华.图像质量评价研究综述[J].计算机科学,2008,35(7)：1-4
[19]何小海,滕奇志等.图像通信.西安：西安电子科技大学出版社,2005
[20]路文.基于视觉感知的影像质量评价方法研究.西安电子科技大学,2009
[21]Alan C. Bovic.The Handbook of Image and Video Processing. New York, Elsevier Academic Press,2005
[22]丁绪星,朱日宏,李建欣.一种基于人眼视觉特性的图像质量评价.中国图象图形学报,2004,9(2)：190-194
[23]马文波,赵宝军,任宏亮,毛二可.基于小波频带划分及CSF特性的图像质量评价方法.激光与红外,2007,37(7)：687-690
[24]俞斯乐,侯正信,冯启明,李文元.电视原理[M].北京：国防工业出版社,2000
[25]T. M. Kusuma, H.J. Zepernick. A Reduced-Reference Perceptual Quality Metric for In-Service Image Quality Assesment. In Proc. Joint First Workshop.on Mobile Future and IEEE Symposium in Trends in Communications,2003,71-74
[26]I. P. Gunawan, M. Ghanbari. Image Quality Assessment Based on Harmonics Gain/Loss Information. In Proc. IEEE Int. Conf. on Image Processing,2005,1:29-32
[27]Qiang Li. RR Image Quality Assessment Using Divisive Normmalization-based Image Reprensentation. IEEE Journal of Selected Topics in Signal Processing,2009,3(2): 202-211
[28]Zhou Wang, Guxing Wu, Skeikh, et al. Quality-Aware Images. IEEE Trans. Image Processing,2006,15(6):1680-1689
[29]Mathieu Carnec, Patric Le Callet, Dominique Barba. Objective Quality Assessment of Color Images Based on A Generic Perceptual Reduced Reference. Image Communication,2008,23(4):239-256
[30]Xinbo Gao, Wen Lu, Dacheng Tao. An Image Quality Assessment Based on Multiscale Geometric Analysis. IEEE Trans. Image Processing,2009,18(7):1409-1423
[31]T.N Comsweet. Visual Perception.Academic Press, New York,1970
[32]Richard Hartley, Andrew Zisserman. Multiply View Geometry in computer vision. Second Edition. Cambridge:Cambridge University Press,2003
[33]Campbell F.W. Kulikowski J. Orientation Selectivity of The Human Visual System. J. Physiol,1966,197:437-441
[34]Szeliski R. Image Alignment and Stitching:A Tutorial. Preliminary draft, Technical Report, MSR-TR-2004-92,2005
[35]G. E. Legge, J. M. Foley.Contrasnt Masking in Human Vision. Journal of the Optical Society of America,1980,70(12):1458-1471
[36]E. Switkes, A. Bradley, K. D. Valois. Contrast Dependence and Mechanisms of Masking Interactions among Chromatic and Luminance Gratings. Journal of the Optical Society of America,1988,5(7):1149-1162
[37]A. Grossman, J. Morlet. Decomposition of Hardly Functions into Square Integrable Wavelets of Constant Shape. SIAM J. Appl. Math,1984,15:723-7
[38]C. K Chui. An Introduction to Wavelets. Academic Press, San Diego,1992
[39]Daubechies I. Orthonormal Bases of Compactly Suppored Wavelets. Common on Pure and Applied Mathematics,1988,41:909-996
[40]Mallat S. A Theory for Multi-resolution Signal Decomposition:The Wavelets Representation. IEEE Trans. Pattern Anal. Machine Intell.1989,11(7):674-693
[41]龚洪涛.基于HVS特性的图像质量客观评价.南京理工大学,2011
[42]Mannos J. L., Sakrison D. J. The Effects of A Visual Fidelity Criterion of Encoding Images. IEEE Trans. Information Theory,1974,20(4):525-536
[43]H. R. Sheikh, Zhou Wang, A. C. Bovik. Image and Video Quality Assessment Research at LIVE. http://live.ece.utexas.edu/rese-arch/quality/,2003
[44]Video Quality Research Home Page. Available:http://www.vqeg.org/.
[45]VQEG. Final Report from the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment. Phase 1 VQEG,2000. Available: http://www.vqeg.org/.
[2]毕厚杰.图像通信工程.北京：人民邮电出版社,1991
[3]Zhou Wang, Alan C. Bovik, Ligang Lu. Why is Image Quality Assessment so Difficult. In Proc. IEEE Int. Con. Acoustics, Speech, and Signal Processing, Florida USA.2002,4: 3313-3316
[4]Scott Daly. The Visible Difference Predictor:An Algorithm for The Assessment of Image Fidelity. In Digital Images and Human Vision, A. B Watson, ed. Aambridge, MA: The MIT Press,1993,179-206
[5]Jeffrey Lubin. A Visual Discrimination Model for Image Syetem Design and Evaluation. In Visual Models for Target Detection and Recognition, E. Peli, ed. Singapore, World Scientific,1995,207-220
[6]R. J. Safranek, J. D. Johnson. A Perceptually Tuned Sub-band Image Coder with Image Dependent Quantization and Post-quantization Data Compression. In Proc. IEEE Int. Con. Acoustics, Speech, and Signal Processing,1989,1945-1948
[7]Reddy B.S, Chatterji B.N. An FFT-based technique for translation, rotation and scale-invariant image registration. IEEE Transaction on Image Processing,1996,5(8): 1266-127
[8]Andre B. Watson. DCT Quantization Matrices Visually Optimized for Individual Images.In Proc. SPIE Human Vision, Visual Processing and Digital Display IV, Bellingham, WA, USA,1993,1913(14):202-216
[9]Andre B. Watson, G. Y. Yang, J. A. Solomon. Visibility of Wavelet Quantization Noise. IEEE Trans. Image Processing,1997,6(8):1164-1175
[10]Zhou Wang, Alan C. Bovic, Hamid R. Sheikh. Image Quality Assessment:from Error Visibility to Structural Similarity. IEEE Trans. Processing,2004,13(4):600-612
[11]Guan-Hao Chen, Chun-Ling Wang and Sheng-Li Xie.Gradient-Based Structural Similarity for Image Quality Assessment. IEEE International Conference on Image Processing, Atlanta, GA 1,2006:2929-2932
[12]X. B. Gao, T Wang, J. Li. A Content-Based Image Quality Metric. D. Slezak et al. (EDs.): RSFDGrC2005, Lecture Notes in Artificial Intelligence, LNAI3642,2005:231-240 1986
[13]Makoto Miayahar, Kazunori Kotani, Ralph V. Algazi. Objective Picture Quality Scale for Image Coding. IEEE Trans. Communications,1998,46(9):1215-1225
[14]Aleksandr Shnayderman, Alexander Gusev, Ahmet M. Eskicioglu. An Image Quality Measure for Local and Global Assessment. IEEE Trans. Image Processing,2006,15(2): 422-429
[15]Damon M. Chandler, Sheila S. Hemami. A Wavelet-based Visual Signal-to-Noise Ratio for Natural Images. IEEE. Trans. Image Processing,2007,16(9):2284-2298
[16]Hamid R. Sheikh, Alan C. Bovic. Image Information and Visual Quality. IEEE. Trans. Image Processing,2006,15(2):430-444
[17]Van Dijk.H, J.B. Martens. Subjective quality assessment of compressed images. Signal Processing,1997,58(1):235-252
[18]周景超,戴汝为,肖柏华.图像质量评价研究综述[J].计算机科学,2008,35(7)：1-4
[19]何小海,滕奇志等.图像通信.西安：西安电子科技大学出版社,2005
[20]路文.基于视觉感知的影像质量评价方法研究.西安电子科技大学,2009
[21]Alan C. Bovic.The Handbook of Image and Video Processing. New York, Elsevier Academic Press,2005
[22]丁绪星,朱日宏,李建欣.一种基于人眼视觉特性的图像质量评价.中国图象图形学报,2004,9(2)：190-194
[23]马文波,赵宝军,任宏亮,毛二可.基于小波频带划分及CSF特性的图像质量评价方法.激光与红外,2007,37(7)：687-690
[24]俞斯乐,侯正信,冯启明,李文元.电视原理[M].北京：国防工业出版社,2000
[25]T. M. Kusuma, H.J. Zepernick. A Reduced-Reference Perceptual Quality Metric for In-Service Image Quality Assesment. In Proc. Joint First Workshop.on Mobile Future and IEEE Symposium in Trends in Communications,2003,71-74
[26]I. P. Gunawan, M. Ghanbari. Image Quality Assessment Based on Harmonics Gain/Loss Information. In Proc. IEEE Int. Conf. on Image Processing,2005,1:29-32
[27]Qiang Li. RR Image Quality Assessment Using Divisive Normmalization-based Image Reprensentation. IEEE Journal of Selected Topics in Signal Processing,2009,3(2): 202-211
[28]Zhou Wang, Guxing Wu, Skeikh, et al. Quality-Aware Images. IEEE Trans. Image Processing,2006,15(6):1680-1689
[29]Mathieu Carnec, Patric Le Callet, Dominique Barba. Objective Quality Assessment of Color Images Based on A Generic Perceptual Reduced Reference. Image Communication,2008,23(4):239-256
[30]Xinbo Gao, Wen Lu, Dacheng Tao. An Image Quality Assessment Based on Multiscale Geometric Analysis. IEEE Trans. Image Processing,2009,18(7):1409-1423
[31]T.N Comsweet. Visual Perception.Academic Press, New York,1970
[32]Richard Hartley, Andrew Zisserman. Multiply View Geometry in computer vision. Second Edition. Cambridge:Cambridge University Press,2003
[33]Campbell F.W. Kulikowski J. Orientation Selectivity of The Human Visual System. J. Physiol,1966,197:437-441
[34]Szeliski R. Image Alignment and Stitching:A Tutorial. Preliminary draft, Technical Report, MSR-TR-2004-92,2005
[35]G. E. Legge, J. M. Foley.Contrasnt Masking in Human Vision. Journal of the Optical Society of America,1980,70(12):1458-1471
[36]E. Switkes, A. Bradley, K. D. Valois. Contrast Dependence and Mechanisms of Masking Interactions among Chromatic and Luminance Gratings. Journal of the Optical Society of America,1988,5(7):1149-1162
[37]A. Grossman, J. Morlet. Decomposition of Hardly Functions into Square Integrable Wavelets of Constant Shape. SIAM J. Appl. Math,1984,15:723-7
[38]C. K Chui. An Introduction to Wavelets. Academic Press, San Diego,1992
[39]Daubechies I. Orthonormal Bases of Compactly Suppored Wavelets. Common on Pure and Applied Mathematics,1988,41:909-996
[40]Mallat S. A Theory for Multi-resolution Signal Decomposition:The Wavelets Representation. IEEE Trans. Pattern Anal. Machine Intell.1989,11(7):674-693
[41]龚洪涛.基于HVS特性的图像质量客观评价.南京理工大学,2011
[42]Mannos J. L., Sakrison D. J. The Effects of A Visual Fidelity Criterion of Encoding Images. IEEE Trans. Information Theory,1974,20(4):525-536
[43]H. R. Sheikh, Zhou Wang, A. C. Bovik. Image and Video Quality Assessment Research at LIVE. http://live.ece.utexas.edu/rese-arch/quality/,2003
[44]Video Quality Research Home Page. Available:http://www.vqeg.org/.
[45]VQEG. Final Report from the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment. Phase 1 VQEG,2000. Available: http://www.vqeg.org/.