Content Clustering Based on Users'subjective Evaluation
説明
User's demand of the quality of streaming service depends on intrinsic characteristics of the content. Various items can be considered as a characteristic. These characteristics are rated on a scale of intensity from 1 to 5. In this paper it is denoted that intensity based on sound or image quality is a characteristic of the content. A subjective evaluation experiment was carried out on several genres of content. The relation between content characteristics and content types is shown by using, principal component analysis. Then, based on the image quality and sound quality, the content is divided into several groups using cluster analysis
収録刊行物
-
- 6th Asia-Pacific Symposium on Information and Telecommunication Technologies
-
6th Asia-Pacific Symposium on Information and Telecommunication Technologies 177-182, 2005-01-01
IEEE