Article
Full entry | Fulltext not available
(moving wall
24 months)
Feedback
Keywords:
generalized metric; vector-valued metric; scalarization; image comparison; structural similarity index
generalized metric; vector-valued metric; scalarization; image comparison; structural similarity index
Summary:
Distance metrics are at the core of many processing and machine learning algorithms. In many contexts, it is useful to compute the distance between data using multiple criteria. This naturally leads to consider vector-valued metrics, in which the distance is no longer a real positive number but a vector. In this paper, we propose a principled way to combine several metrics into either a scalar-valued or vector-valued metric. We illustrate our framework by reformulating the popular structural similarity (SSIM) index and a simple case of the Wasserstein distance used for optimal transport.
References:
[1] Amini-Harandi, A., Fakhar, M.: Fixed point theory in cone metric spaces obtained via the scalarization method. Comput. Math. Appl. 59 (2010), 3529-3534. DOI 10.1016/j.camwa.2010.03.046 | MR 2646324 | Zbl 1197.54055
[2] Athar, S., Wang, Z.: A comprehensive performance evaluation of image quality assessment algorithms. IEEE Access 7 (2019), 140030-140070. DOI 10.1109/ACCESS.2019.2943319
[3] Brunet, D., Vrscay, E. R., Wang, Z.: On the mathematical properties of the structural similarity index. IEEE Trans. Image Process. 21 (2012), 1488-1499. DOI 10.1109/TIP.2011.2173206 | MR 2959465 | Zbl 1373.94051
[4] Bures, D.: An extension of Kakutani's theorem on infinite product measures to the tensor product of semifinite $w^*$-algebras. Trans. Am. Math. Soc. 135 (1969), 199-212. DOI 10.1090/S0002-9947-1969-0236719-2 | MR 0236719 | Zbl 0176.11402
[5] Chen, G.-H., Yang, C.-L., Xie, S.-L.: Gradient-based structural similarity for image quality assessment. IEEE International Conference on Image Processing IEEE, Piscataway (2006), 2929-2932. DOI 10.1109/ICIP.2006.313132
[6] Dosselmann, R., Yang, X. D.: A comprehensive assessment of the structural similarity index. Signal Image Video Process. 5 (2011), 81-91. DOI 10.1007/s11760-009-0144-1
[7] Horé, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. 20th International Conference on Pattern Recognition IEEE, Piscataway (2010), 2366-2369. DOI 10.1109/ICPR.2010.579
[8] Huang, L.-G., Zhang, X.: Cone metric spaces and fixed point theorems of contractive mappings. J. Math. Anal. Appl. 332 (2007), 1468-1476. DOI 10.1016/j.jmaa.2005.03.087 | MR 2324351 | Zbl 1118.54022
[9] Kang, L., Ye, P., Li, Y., Doermann, D.: Convolutional neural networks for no-reference image quality assessment. IEEE Conference on Computer Vision and Pattern Recognition IEEE, Piscataway (2014), 1733-1740. DOI 10.1109/CVPR.2014.224
[10] Khani, M., Pourmahdian, M.: On the metrizability of cone metric spaces. Topology Appl. 158 (2011), 190-193. DOI 10.1016/j.topol.2010.10.016 | MR 2739889 | Zbl 1206.54026
[11] Li, C., Bovik, A. C.: Content-partitioned structural similarity index for image quality assessment. Signal Process., Image Commun. 25 (2010), 517-526. DOI 10.1016/j.image.2010.03.004
[12] Li, Y., Wang, G., Nie, L., Wang, Q., Tan, W.: Distance metric optimization driven convolutional neural network for age invariant face recognition. Pattern Recognition 75 (2018), 51-62. DOI 10.1016/j.patcog.2017.10.015
[13] Ma, Z., Zhou, S., Wu, X., Zhang, H., Yan, W., Sun, S., Zhou, J.: Nasopharyngeal carcinoma segmentation based on enhanced convolutional neural networks using multi-modal metric learning. Phys. Med. Biol. 64 (2019), Article ID 025005. DOI 10.1088/1361-6560/aaf5da
[14] Villani, C.: Optimal Transport: Old and New. Grundlehren der Mathematischen Wissenschaften 338. Springer, Berlin (2009). DOI 10.1007/978-3-540-71050-9 | MR 2459454 | Zbl 1156.53003
[15] Wainwright, M. J., Schwartz, O., Simoncelli, E. P.: Natural image statistics and divisive normalization. Probabilistic Models of the Brain: Perception and Neural Function MIT Press, Cambridge (2002), 203-222.
[16] Wang, C., Peng, G., Baets, B. De: Deep feature fusion through adaptive discriminative metric learning for scene recognition. Inf. Fusion 63 (2020), 1-12. DOI 10.1016/j.inffus.2020.05.005
[17] Wang, Z., Bovik, A. C.: A universal image quality index. IEEE Signal Process. Lett. 9 (2002), 81-84. DOI 10.1109/97.995823
[18] Wang, Z., Bovik, A. C., Lu, L.: Why is image quality assessment so difficult?. IEEE International Conference on Acoustics, Speech, and Signal Processing IEEE, Piscataway (2002), IV-3313--IV-3316. DOI 10.1109/ICASSP.2002.5745362 | MR 0642901
[19] Wang, Z., Bovik, A. C., Sheikh, H. R., Simoncelli, E. P.: Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 13 (2004), 600-612. DOI 10.1109/TIP.2003.819861
[20] Wang, Z., Simoncelli, E. P., Bovik, A. C.: Multiscale structural similarity for image quality assessment. 37th Asilomar Conference on Signals, Systems & Computers IEEE, Piscataway (2003), 1398-1402. DOI 10.1109/ACSSC.2003.1292216
[21] Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3 (2017), 47-57. DOI 10.1109/TCI.2016.2644865
Search
Partner of
