TY - GEN
T1 - Parameters optimization of the Structural Similarity Index
AU - Bakurov, Illya
AU - Buzzelli, Marco
AU - Castelli, Mauro
AU - Schettini, Raimondo
AU - Vanneschi, Leonardo
N1 - info:eu-repo/grantAgreement/FCT/9471 - RIDTI/PTDC%2FCCI-CIF%2F29877%2F2017/PT#
info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FDS%2F0113%2F2019/PT#
info:eu-repo/grantAgreement/FCT/3599-PPCDT/DSAIPA%2FDS%2F0022%2F2018/PT#
Bakurov, I., Buzzelli, M., Castelli, M., Schettini, R., & Vanneschi, L. (2020). Parameters optimization of the Structural Similarity Index. In London Imaging Meeting 2020: Future Colour Imaging (1 ed., Vol. 2020, pp. 19-23). (London Imaging Meeting). https://doi.org/10.2352/issn.2694-118X.2020.LIM-13
PY - 2020/9/29
Y1 - 2020/9/29
N2 - We exploit evolutionary computation to optimize the handcrafted Structural Similarity method (SSIM) through a datadriven approach. We estimate the best combination of luminance, contrast and structure components, as well as the sliding window size used for processing, with the objective of optimizing the similarity correlation with human-expressed mean opinion score on a standard dataset. We experimentally observe that better results can be obtained by penalizing the overall similarity only for very low levels of luminance similarity. Finally, we report a comparison of SSIM with the optimized parameters against other metrics for full reference quality assessment, showing superior performance on a different dataset.
AB - We exploit evolutionary computation to optimize the handcrafted Structural Similarity method (SSIM) through a datadriven approach. We estimate the best combination of luminance, contrast and structure components, as well as the sliding window size used for processing, with the objective of optimizing the similarity correlation with human-expressed mean opinion score on a standard dataset. We experimentally observe that better results can be obtained by penalizing the overall similarity only for very low levels of luminance similarity. Finally, we report a comparison of SSIM with the optimized parameters against other metrics for full reference quality assessment, showing superior performance on a different dataset.
U2 - 10.2352/issn.2694-118X.2020.LIM-13
DO - 10.2352/issn.2694-118X.2020.LIM-13
M3 - Conference contribution
VL - 2020
T3 - London Imaging Meeting
SP - 19
EP - 23
BT - London Imaging Meeting 2020
ER -