Title:
知覚的ビデオ品質を予測する技術
Document Type and Number:
Japanese Patent JP6707563
Kind Code:
B2
Abstract:
In one embodiment of the present invention, a quality trainer and quality calculator collaborate to establish a consistent perceptual quality metric via machine learning. In a training phase, the quality trainer leverages machine intelligence techniques to create a perceptual quality model that combines objective metrics to optimally track a subjective metric assigned during viewings of training videos. Subsequently, the quality calculator applies the perceptual quality model to values for the objective metrics for a target video, thereby generating a perceptual quality score for the target video. In this fashion, the perceptual quality model judiciously fuses the objective metrics for the target video based on the visual feedback processed during the training phase. Since the contribution of each objective metric to the perceptual quality score is determined based on empirical data, the perceptual quality score is a more accurate assessment of observed video quality than conventional objective metrics.
Inventors:
Aaron, Anne
Kim, Dae
Lynn, Yu-Chay
Ronca, David
Schuler, Andy
Cao, Quyen
Wu, Qi-hao
Kim, Dae
Lynn, Yu-Chay
Ronca, David
Schuler, Andy
Cao, Quyen
Wu, Qi-hao
Application Number:
JP2017559335A
Publication Date:
June 10, 2020
Filing Date:
May 09, 2016
Export Citation:
Assignee:
NETFLIX, INC.
International Classes:
H04N17/00; H04N19/51; H04N19/85
Domestic Patent References:
| JP11341526A | ||||
| JP2016111473A | ||||
| JP2014130427A |
Foreign References:
| US20130027568 |
Attorney, Agent or Firm:
Yanagita Seiji
Hideaki Takahashi
Hideaki Takahashi