A harmonic means pooling strategy for structural similarity index measurement in image quality assessment

详细信息    查看全文

• 作者：Yue Huang ; Xin Chen ; Xinghao Ding
• 关键词：Image quality assessment ; Full reference ; Pooling strategy ; Harmonic mean
• 刊名：Multimedia Tools and Applications
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：75
• 期：5
• 页码：2769-2780
• 全文大小：675 KB
• 参考文献：1.Achanta R, Hemami S, Estrada F, et al (2009) Frequency-tuned salient region detection[C]//Computer Vision and Pattern Recognition. CVPR 2009. IEEE Conference on. IEEE, 2009: 1597–1604
  2.Bondzulic BP, Petrovic VS (2014) Additive models and separable pooling, a new look at structural similarity. Signal Process 97:110–116CrossRef
  3.Chandler DM (2013) Seven challenges in image quality assessment: past, present, and future research. ISRN Signal Process 2013:53, Article ID 905685CrossRef
  4.Charrier C, L’ezoray O, Lebrun G (2012) Machine learning to design full-reference image quality assessment algorithm. IEEE Trans Image Commun 27(3):209–219
  5.Chen GH, Yang CL, Xie SL (2006) Gradient-based structural similarity for image quality assessment, 13th IEEE International Conference on Image Processing
  6.Gu K, Zhai G, Yang X, Chen L, et al (2012) Nonlinear additive model based saliency map weighting strategy for image quality assessment, (MMSP), 2012 I.E. 14 th Conference on. vol. 2, pp. 1308–1204
  7.Guo A, Zhao D, Liu S, Fan X, Gao W (2011) Visual attention based image quality assessment. In: Proceedings of the 18th IEEE International Conference on Image Processing (ICIP ’11), pp. 3297–3300
  8.Larson EC, Chandler DM (2010) Most apparent distortion: full reference image quality assessment and the role of strategy. J Electron Imaging 19:011006CrossRef
  9.Li C, Bovik AC (2010) Content-partitioned structural similarity index for image quality assessment. Signal Process Image Commun 25(7):517–526CrossRef
  10.Lin W, Jay Kuo C-C (2011) Perceptual visual quality metrics: A survey. J Vis Commun Image Represent 22(4):297–312CrossRef
  11.Lin Z, Lei Z, Mou X, Zhang D (2011) FSIM: a feature similarity index for image quality assessment. IEEE Trans Image Process 20(8):2378–2386MathSciNet CrossRef
  12.Moorthy AK, Bovik AC (2009) Visual importance pooling for image quality assessment. IEEE J Sel Top Sign Proces 3(2):193–201CrossRef
  13.Ninassi A, Le Meur O, Le Callet P et al (2007) Does where you gaze on an image affect your perception of quality? Applying visual attention to image quality metric. Int Conf IEEE Image Process 2:II-169–II-172
  14.Ponomarenko N, Lukin V, Zelensky A, Egiazarian K, Carli M, Battisti F (2009) TID2008 - A database for evaluation of full-reference visual quality assessment metrics. Adv Mod Radio Electron 10:30–45
  15.Rouse DM, Hemami SS (2008) Understanding and simplifying the structural similarity metric, In: Proceedings of the International Conference on Image Processing, pp. 1188C1191
  16.Saha A, Bhatnagar G, Wu Q (2012) Svd filter based multiscale approach for image quality assessment. In: Proceedings of the IEEE International Conference on Multimedia and Expo Workshops (ICMEW ’12), pp. 43–48
  17.Sheikh HR, Bovik AC (2006) Image informationand visual quality. IEEE Trans Image Process 15(2):430–444CrossRef
  18.Sheikh HR, Wang Z, Cormack L, Bovik AC (2005) Live Image quality assessment database release 2, [Online]. http://​live.​ece.​utexas.​edu/​research/​quality .
  19.Wang Z, Bovik AC, Sheikh HR, Simoncelli EP The SSIM index for image quality assessment, MATLAB implementation available online from: http://​www.​cns.​nyu.​edu/​lcv/​ssim/​ssim.​m .
  20.Wang Z, Bovik AC (2002) A universal image quality index. IEEE Signal Process Lett 9(3):81–84CrossRef
  21.Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612CrossRef
  22.Wang Z, Li Q (2011) Information content weighting for perceptual image quality assessment. IEEE Trans Image Process 20(5):1185–1198MathSciNet CrossRef
  23.Wang Z, Simoncelli EP, Bovik AC (2003) Multiscale structural similarity for image quality assessment. In: Signals, Systems and Computers, 2003. Conference Record of the Thirty-Seventh Asilomar Conference on. IEEE, vol. 2, pp. 1398–1402
  24.Wu J, Lin W, Shi G, Liu A (2012) A perceptual quality metric with internal generative mechanism. In: Proceedings of the IEEE Transactions Image Processing, no. 99
  25.Xue W, Zhang L, Mou X, et al (2014) Gradient magnitude similarity deviation: a highly efficient perceptual image quality index
  26.Zhang L, Zhang L, Mou X, et al (2012) A comprehensive evaluation of full reference image quality assessment algorithms[C]// Image Processing (ICIP), 2012 19th IEEE International Conference on. IEEE 1477–1480
  27.Zhu J, Wang N (2012) Image quality assessment by visual gradient similarity. In: Proceedings of the IEEE Transactions of Image Processing 21(3):919–933
  
• 作者单位：Yue Huang (1)
  Xin Chen (1)
  Xinghao Ding (1)
  
  1. Fujian Key Laboratory of Sensing and Computing for Smart City, College of Information Science and Engineering, Xiamen University, Xiamen, 361005, China
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

Structural similarity index measurement (SSIM) is one of the most well known method in full reference image quality assessment metrics (FR-IQA). In this paper, a novel pooling strategy based on harmonic mean is proposed to enhance the performance of SSIM. Instead of arithmetic mean, the proposed pooling by harmonic mean tends to emphasize the contributions from the local severely distorted regions or pixels in the definition of assessment function using reciprocal transformation. The proposed object function has higher correlation with human perception, which is mostly affected with the regions having severely distorted points or regions. In addition, salience information is introduced to the object function for a better consideration of subject visual attention. The proposed pooling strategy is applied to classical SSIM and its variants, GSSIM and FSIM. The experimental results have demonstrated that the FR-IQA metrics with proposed pooling strategy have better performances compared to the standard versions, especially on the images with small but seriously distorted regions.