Tampere University of Technology

TUTCRIS Research Portal

Structural Similarity Index with Predictability of Image Blocks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Structural Similarity Index with Predictability of Image Blocks. / Ponomarenko, Mykola; Egiazarian, Karen; Lukin, Vladimir; Abramova, Victoriya.

2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings. Vol. 2018-July IEEE COMPUTER SOCIETY PRESS, 2018. p. 115-118 8460285.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Ponomarenko, M, Egiazarian, K, Lukin, V & Abramova, V 2018, Structural Similarity Index with Predictability of Image Blocks. in 2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings. vol. 2018-July, 8460285, IEEE COMPUTER SOCIETY PRESS, pp. 115-118, IEEE International Conference on Mathematical Methods in Electromagnetic Theory, Kyiv, Ukraine, 2/07/18. https://doi.org/10.1109/MMET.2018.8460285

APA

Ponomarenko, M., Egiazarian, K., Lukin, V., & Abramova, V. (2018). Structural Similarity Index with Predictability of Image Blocks. In 2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings (Vol. 2018-July, pp. 115-118). [8460285] IEEE COMPUTER SOCIETY PRESS. https://doi.org/10.1109/MMET.2018.8460285

Vancouver

Ponomarenko M, Egiazarian K, Lukin V, Abramova V. Structural Similarity Index with Predictability of Image Blocks. In 2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings. Vol. 2018-July. IEEE COMPUTER SOCIETY PRESS. 2018. p. 115-118. 8460285 https://doi.org/10.1109/MMET.2018.8460285

Author

Ponomarenko, Mykola ; Egiazarian, Karen ; Lukin, Vladimir ; Abramova, Victoriya. / Structural Similarity Index with Predictability of Image Blocks. 2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings. Vol. 2018-July IEEE COMPUTER SOCIETY PRESS, 2018. pp. 115-118

Bibtex - Download

@inproceedings{59fcc1b862c84eb0a036d0efb2f91c24,
title = "Structural Similarity Index with Predictability of Image Blocks",
abstract = "Structural similarity index (SSIM) is a widely used full-reference metric for assessment of visual quality of images and remote sensing data. It is calculated in a block-wise manner and is based on multiplication of three components: similarity of means of image blocks, similarity of contrasts and a correlation factor. In this paper, two modifications of SSIM are proposed. First, a fourth multiplicative component is introduced to SSIM (thus obtaining SSIM4) that describes a similarity of predictability of image blocks. A predictability for a given block is calculated as a minimal value of mean square error between the considered block and the neighboring blocks. Second, a simple scheme for calculating the metrics SSIM and SSIM4 for color images is proposed and optimized. Effectiveness of the proposed modifications is confirmed for the specialized image databases TID2013, LIVE, and FLT. In particular, the Spearman rank order correlation coefficient (SROCC) for the recently introduced FLT Database, calculated between the proposed metric color SSIM4 and mean opinion scores (MOS), has reached the value 0.85 (the best result for all compared metrics) whilst for SSIM it is equal to 0.58.",
keywords = "image visual quality assessment, masking of unpredictable energy",
author = "Mykola Ponomarenko and Karen Egiazarian and Vladimir Lukin and Victoriya Abramova",
note = "JUFOID=72887 EXT={"}Lukin, Vladimir{"}",
year = "2018",
month = "9",
day = "10",
doi = "10.1109/MMET.2018.8460285",
language = "English",
isbn = "9781538654385",
volume = "2018-July",
publisher = "IEEE COMPUTER SOCIETY PRESS",
pages = "115--118",
booktitle = "2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Structural Similarity Index with Predictability of Image Blocks

AU - Ponomarenko, Mykola

AU - Egiazarian, Karen

AU - Lukin, Vladimir

AU - Abramova, Victoriya

N1 - JUFOID=72887 EXT="Lukin, Vladimir"

PY - 2018/9/10

Y1 - 2018/9/10

N2 - Structural similarity index (SSIM) is a widely used full-reference metric for assessment of visual quality of images and remote sensing data. It is calculated in a block-wise manner and is based on multiplication of three components: similarity of means of image blocks, similarity of contrasts and a correlation factor. In this paper, two modifications of SSIM are proposed. First, a fourth multiplicative component is introduced to SSIM (thus obtaining SSIM4) that describes a similarity of predictability of image blocks. A predictability for a given block is calculated as a minimal value of mean square error between the considered block and the neighboring blocks. Second, a simple scheme for calculating the metrics SSIM and SSIM4 for color images is proposed and optimized. Effectiveness of the proposed modifications is confirmed for the specialized image databases TID2013, LIVE, and FLT. In particular, the Spearman rank order correlation coefficient (SROCC) for the recently introduced FLT Database, calculated between the proposed metric color SSIM4 and mean opinion scores (MOS), has reached the value 0.85 (the best result for all compared metrics) whilst for SSIM it is equal to 0.58.

AB - Structural similarity index (SSIM) is a widely used full-reference metric for assessment of visual quality of images and remote sensing data. It is calculated in a block-wise manner and is based on multiplication of three components: similarity of means of image blocks, similarity of contrasts and a correlation factor. In this paper, two modifications of SSIM are proposed. First, a fourth multiplicative component is introduced to SSIM (thus obtaining SSIM4) that describes a similarity of predictability of image blocks. A predictability for a given block is calculated as a minimal value of mean square error between the considered block and the neighboring blocks. Second, a simple scheme for calculating the metrics SSIM and SSIM4 for color images is proposed and optimized. Effectiveness of the proposed modifications is confirmed for the specialized image databases TID2013, LIVE, and FLT. In particular, the Spearman rank order correlation coefficient (SROCC) for the recently introduced FLT Database, calculated between the proposed metric color SSIM4 and mean opinion scores (MOS), has reached the value 0.85 (the best result for all compared metrics) whilst for SSIM it is equal to 0.58.

KW - image visual quality assessment

KW - masking of unpredictable energy

U2 - 10.1109/MMET.2018.8460285

DO - 10.1109/MMET.2018.8460285

M3 - Conference contribution

SN - 9781538654385

VL - 2018-July

SP - 115

EP - 118

BT - 2018 IEEE 17th International Conference on Mathematical Methods in Electromagnetic Theory, MMET 2018 - Proceedings

PB - IEEE COMPUTER SOCIETY PRESS

ER -