User:KatyaShm/sandbox

From Wikipedia, the free encyclopedia

for PSNR:

Application[edit]

PSNR has applications in a variety of different problems. Some examples are:

  • Image compression. PSNR is commonly used to quantify reconstruction quality for images and video subject to lossy compression [1] [2] .
  • Image restoration. PSNR is one of the most popular metrics for the quality assessment of the restored images [3] [4] [5].
  • Steganography. PSNR is often used to evaluate the steganography methods quality [6] [7] [8].
  • Improvement of fabricated machines. PSNR criterion is employed to analyze the fabricated machine performance which aids its improvement. For example, the PSNR criterion is used to improvement of an apple sorting machine [9].
  • Image segmentation. PSNR is used as an analytic metric by several authors of threshold-based segmentation algorithms [10] [11] [12].
  • 3D video. PSNR used as estimation Method for 3D videos [13].
  • Super-resolution imaging. PSNR is the most popular metric for the quality assessment of Super-Resolution algorithms [14] [15] [16] [17] .


Criticism[edit]

PSNR has been widely criticized in independent research papers.

  • There are many examples when images with mostly the same PSNR scores have dramatically different visual quality [18] [19] [20].
  • In the task of representing the quality of a compressed video sequence, PSNR has been found to correlate poorly with subjective quality ratings [21] [22] .
  • PSNR is very sensitive to small geometric transformations, which doesn't alter visual quality a lot [23] [19].
  • PSNR is not an adequate quality measurement for segmentation algorithms [24].
  • PSNR doesn’t reflect the actual quality of stego images [25] [26].
  • PSNR correlates poorly with subjective assessment for the task of Super-Resolution [27].
  • Ways of cheating on popular objective metrics: blurring, noise, super-resolution, and others [].

for SSIM:

Application[edit]

Criticism[edit]

SSIM has been widely criticized in independent research papers.

  • Jim Nilsson and Tomas Akenine-Möller questioned the philosophy of perceptual motivated nature that was laid in the SSIM [35].
  • SSIM is very sensitive to small geometric transformations, which doesn't alter visual quality a lot [23].
  • Keyan Ding, Kede Ma, Shiqi Wang, and Eero P. Simoncelli evaluated SSIM and other full-reference metrics by using them as objective functions to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression [36].
  • SSIM has been found to correlate poorly with subjective assessment in the task of representing the quality of Super-Resolution images [27] [37].
  • Ways of cheating on popular objective metrics: blurring, noise, super-resolution, and others [].


References[edit]

  1. ^ Wiegand, T.; Sullivan, G.J.; Bjontegaard, G.; Luthra, A. (2003). "Overview of the H.264/AVC video coding standard". IEEE Transactions on Circuits and Systems for Video Technology. 13 (7). Institute of Electrical and Electronics Engineers (IEEE): 560–576. doi:10.1109/tcsvt.2003.815165. ISSN 1051-8215.
  2. ^ Kamaci, N.; Altunbasak, Y. (2003). Performance comparison of the emerging H.264 video coding standard with the existing standards. IEEE. doi:10.1109/icme.2003.1220925.
  3. ^ Akkoul, Smaïl; Ledee, Roger; Leconge, Remy; Harba, Rachid (2010). "A New Adaptive Switching Median Filter". IEEE Signal Processing Letters. 17 (6). Institute of Electrical and Electronics Engineers (IEEE): 587–590. doi:10.1109/lsp.2010.2048646. ISSN 1070-9908.
  4. ^ Yan, He; Zhang, Xing-lan; Li, Wei-wei; Chen, Feng (2010). Image Restoration Using Gaussian Scale Mixtures in Complex Curvelet Transform Domain. IEEE. doi:10.1109/icmtma.2010.242.
  5. ^ Jain, Akshat; Bhateja, Vikrant (2012). A novel detection and removal scheme for denoising images corrupted with Gaussian outliers. IEEE. doi:10.1109/sces.2012.6199102.
  6. ^ Hussain, Mehdi; Hussain, M. (2011). Embedding data in edge boundaries with high PSNR. IEEE. doi:10.1109/icet.2011.6048469.
  7. ^ Masud Karim, S. M.; Rahman, Md. Saifur; Hossain, Md. Ismail (2011). A new approach for LSB based image steganography using secret key. IEEE. doi:10.1109/iccitechn.2011.6164800.
  8. ^ Jangid, Sachin; Sharma, Somesh (2017). High PSNR based video steganography by MLC(multi-level clustering) algorithm. IEEE. doi:10.1109/iccons.2017.8250530.
  9. ^ Golpira H., Golpîra H. Improvement of an apple sorting machine using PSNR criterion //The 2012 International Conference on Advanced Mechatronic Systems. – IEEE, 2012. – С. 729-732.
  10. ^ Arora S. et al. Multilevel thresholding for image segmentation through a fast statistical recursive algorithm //Pattern Recognition Letters. – 2008. – Т. 29. – №. 2. – С. 119-125.
  11. ^ Chen, Yu-Kumg; Cheng, Fan-Chieh; Tsai, Pohsiang (2011). "A gray-level clustering reduction algorithm with the least PSNR". Expert Systems with Applications. 38 (8). Elsevier BV: 10183–10187. doi:10.1016/j.eswa.2011.02.071. ISSN 0957-4174.
  12. ^ Horng, Ming-Huwi; Liou, Ren-Jean (2011). "Multilevel minimum cross entropy threshold selection based on the firefly algorithm". Expert Systems with Applications. 38 (12). Elsevier BV: 14805–14811. doi:10.1016/j.eswa.2011.05.069. ISSN 0957-4174.
  13. ^ Yuan, Hui; Kwong, Sam; Wang, Xu; Zhang, Yun; Li, Fengrong (2016). "A Virtual View PSNR Estimation Method for 3-D Videos". IEEE Transactions on Broadcasting. 62 (1). Institute of Electrical and Electronics Engineers (IEEE): 134–140. doi:10.1109/tbc.2015.2492461. ISSN 0018-9316.
  14. ^ Bevilacqua, Marco; Roumy, Aline; Guillemot, Christine; Morel, Marie-Line Alberi (2013). Super-resolution using neighbor embedding of back-projection residuals. IEEE. doi:10.1109/icdsp.2013.6622796.
  15. ^ Chen, Huahua; Jiang, Baolin; Chen, Weiqiang (2011). Image super-resolution based on patches structure. IEEE. doi:10.1109/cisp.2011.6100283.
  16. ^ Guo, Liang; Wang, Guizhong; Zhang, Fan; Li, Xuemei (2016). Single Image Super-resolution Based on Self-Similarity and Dictionary Neighborhood. IEEE. doi:10.1109/dasc-picom-datacom-cyberscitec.2016.55.
  17. ^ Changjun, Fu; Xiangyang, Ji; Yongbing, Zhang; Qionghai, Dai (2012). A Single Frame Super-Resolution Method Based on Matrix Completion. IEEE. doi:10.1109/dcc.2012.36.
  18. ^ Brooks, A.C.; Pappas, T.N. (2008). "Structural Similarity Quality Metrics in a Coding Context: Exploring the Space of Realistic Distortions". IEEE Transactions on Image Processing. 17 (8). Institute of Electrical and Electronics Engineers (IEEE): 1261–1273. doi:10.1109/tip.2008.926161. ISSN 1057-7149.
  19. ^ a b Bovik, A.C. (2009). "Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures". IEEE Signal Processing Magazine. 26 (1). Institute of Electrical and Electronics Engineers (IEEE): 98–117. doi:10.1109/msp.2008.930649. ISSN 1053-5888.
  20. ^ Wang, Z.; Bovik, A.C.; Sheikh, H.R.; Simoncelli, E.P. (2004). "Image Quality Assessment: From Error Visibility to Structural Similarity". IEEE Transactions on Image Processing. 13 (4). Institute of Electrical and Electronics Engineers (IEEE): 600–612. doi:10.1109/tip.2003.819861. ISSN 1057-7149.
  21. ^ Ong, Ee Ping; Yang, Xiaokang; Lin, Weisi; Lu, Zhongkang; Yao, Susu; Lin, Xiao; Rahardja, Susanto; Seng, Boon Choong (2006). "Perceptual quality and objective quality measurements of compressed videos". Journal of Visual Communication and Image Representation. 17 (4). Elsevier BV: 717–737. doi:10.1016/j.jvcir.2005.11.002. ISSN 1047-3203.
  22. ^ Stoica, A.; Vertan, C.; Fernandez-Maloigne, C. Objective and subjective color image quality evaluation for JPEG 2000 compressed images. IEEE. doi:10.1109/scs.2003.1226967.
  23. ^ a b Simoncelli, E.P. Translation Insensitive Image Similarity in Complex Wavelet Domain. IEEE. doi:10.1109/icassp.2005.1415469.
  24. ^ Fardo F. A. et al. A formal evaluation of PSNR as quality measurement parameter for image segmentation algorithms //arXiv preprint arXiv:1605.07116. – 2016.
  25. ^ Almohammad, Adel; Ghinea, Gheorghita (2010). Stego image quality and the reliability of PSNR. IEEE. doi:10.1109/ipta.2010.5586786.
  26. ^ Wazirali, Raniyah; Slehat, Shaher; Chaczko, Zenon; Borowik, Grzegorz; Carrion, Lucia (2015). Objective Quality Metrics in Correlation with Subjective Quality Metrics for Steganography. IEEE. doi:10.1109/apcase.2015.49.
  27. ^ a b Lukes, Tomas; Fliegel, Karel; Klima, Milos (2013). Performance evaluation of image quality metrics with respect to their use for super-resolution enhancement. IEEE. doi:10.1109/qomex.2013.6603205.
  28. ^ Ndajah P. et al. SSIM image quality metric for denoised images //Proc. 3rd WSEAS Int. Conf. on Visualization, Imaging and Simulation. – 2010. – С. 53-58.
  29. ^ Zhao, Hang; Gallo, Orazio; Frosio, Iuri; Kautz, Jan (2017). "Loss Functions for Image Restoration With Neural Networks". IEEE Transactions on Computational Imaging. 3 (1). Institute of Electrical and Electronics Engineers (IEEE): 47–57. doi:10.1109/tci.2016.2644865. ISSN 2333-9403.
  30. ^ Aytekin C. et al. A Compression Objective and a Cycle Loss for Neural Image Compression //CVPR Workshops. – 2019. – С. 0.
  31. ^ Snell, Jake; Ridgeway, Karl; Liao, Renjie; Roads, Brett D.; Mozer, Michael C.; Zemel, Richard S. (2017). Learning to generate images with perceptual similarity metrics. IEEE. doi:10.1109/icip.2017.8297089.
  32. ^ Lan, Rushi; Sun, Long; Liu, Zhenbing; Lu, Huimin; Pang, Cheng; Luo, Xiaonan (2021). "MADNet: A Fast and Lightweight Network for Single-Image Super Resolution". IEEE Transactions on Cybernetics. 51 (3). Institute of Electrical and Electronics Engineers (IEEE): 1443–1453. doi:10.1109/tcyb.2020.2970104. ISSN 2168-2267.
  33. ^ Romano, Yaniv; Isidoro, John; Milanfar, Peyman (2017). "RAISR: Rapid and Accurate Image Super Resolution". IEEE Transactions on Computational Imaging. 3 (1). Institute of Electrical and Electronics Engineers (IEEE): 110–125. doi:10.1109/tci.2016.2629284. ISSN 2333-9403.
  34. ^ Li, Dingyi; Wang, Zengfu (2017). "Video Superresolution via Motion Compensation and Deep Residual Learning". IEEE Transactions on Computational Imaging. 3 (4). Institute of Electrical and Electronics Engineers (IEEE): 749–762. doi:10.1109/tci.2017.2671360. ISSN 2333-9403.
  35. ^ Nilsson J., Akenine-Möller T. Understanding ssim //arXiv preprint arXiv:2006.13846. – 2020.
  36. ^ Ding K. et al. Comparison of full-reference image quality models for optimization of image processing systems //International Journal of Computer Vision. – 2021. – Т. 129. – №. 4. – С. 1258-1281.
  37. ^ Reibman, Amy R.; Bell, Robert M.; Gray, Sharon (2006). Quality assessment for super-resolution image enhancement. IEEE. doi:10.1109/icip.2006.312895.
Retrieved from "https://en.wikipedia.org/w/index.php?title=User:KatyaShm/sandbox&oldid=1041911461"