Detail publikace

Reference Free SSIM Estimation for Full HD Video Content

Originální název

Reference Free SSIM Estimation for Full HD Video Content

Anglický název

Reference Free SSIM Estimation for Full HD Video Content

Jazyk

en

Originální abstrakt

This paper proposes a reference free video quality estimation method for full high definition video services based on a structural similarity index. The design of our estimator is based on an artificial neural network. To achieve this, the neural network was trained with a set of video statistical parameters estracted from the most representative video contents. Moreover, estimations with neural networks allow higher applicability and require lower processing power as known reference based methods. Finally, the achieved correlation between the calculated and the estimated structural similarity index shows a very good fit.

Anglický abstrakt

This paper proposes a reference free video quality estimation method for full high definition video services based on a structural similarity index. The design of our estimator is based on an artificial neural network. To achieve this, the neural network was trained with a set of video statistical parameters estracted from the most representative video contents. Moreover, estimations with neural networks allow higher applicability and require lower processing power as known reference based methods. Finally, the achieved correlation between the calculated and the estimated structural similarity index shows a very good fit.

BibTex


@inproceedings{BUT37076,
  author="Michal {Ries} and Martin {Slanina} and David Mora {Garcia}",
  title="Reference Free SSIM Estimation for Full HD Video Content",
  annote="This paper proposes a reference free video quality estimation method for full high definition video services based on a structural similarity index. The design of our estimator is based on an artificial neural network. To achieve this, the neural network was trained with a set of video statistical parameters estracted from the most representative video contents. Moreover, estimations with neural networks allow higher applicability and require lower processing power as known reference based methods. Finally, the achieved correlation between the calculated and the estimated structural similarity index shows a very good fit.",
  address="Vysoké učení technické v Brně",
  booktitle="Proceedings of the 21st International Conference Radioelektronika 2011",
  chapter="37076",
  howpublished="print",
  institution="Vysoké učení technické v Brně",
  year="2011",
  month="april",
  pages="225--228",
  publisher="Vysoké učení technické v Brně",
  type="conference paper"
}