摘要 |
The present invention relates to a method and apparatus for generating a model used to estimate the quality of input-video data. The apparatus is configured to obtain a plurality of average subjective scores from a plurality of sample video data, and a plurality of image metrics for each of the plurality of said average subjective scores is calculated. Some of the plurality of said image metrics is converted into corresponding, perceived quality metrics, then an image-quality metric is predicted based on the calculated quality metrics and the perceived quality metrics. |