A video classification method using user perceptive video quality

This paper analyzes relationship between video contents and subjective video quality for user-oriented streaming services. In this analysis, we conduct subjective assessments by using various kinds of video programs, and propose a method classifying video programs into some large majority of users feel the same groups in which a large video quality. The control with a high level of user satisfaction can be done by applying different control method to each group obtained from the proposed method. We also show the necessity of rate control according to video contents by comparing a classification result based on vision parameters with that based on the assessment result.