The Institute of Electronics and Information Engineers
대한전자공학회 종합 학술 대회 논문집 (하계) 2001, Vol.3 : 컴퓨터 소사이어티 v. 24, no. 1, page. 109-112
This paper proposes an efficient algorithm to extract anchor blocks for a semantic structure of a news video.
We calculate the frame difference of anchor face region instead of simply using the general frame difference for the efficient extraction of the anchor region.
In this paper, an algorithm to extract a gace region using partial decoded MPEG data is also proposed.
In this way a news video can be structured semantically using the extracted anchor blocks.