Semantic Indexing for Soccer Videos Using Web-Extracted Information

웹에서 축출된 정보를 이용한 축구 경기의 시맨틱 인덱싱

The rapid growing of video content production leads to the necessity of developing more complex indexing systems in order to efficiently allow searching, retrieval and presentation of the desired segments of videos. This paper presents a method for indexing soccer video through automatic extraction of information from internet. The proposed paper defines a metadata structure to formally represent the knowledge of soccer matches and provides an automatic method to extract semantic information from web-sites. This approach improves the capability to extract more reliable and richer semantic Information for soccer videos. Experimental results demonstrate that the proposed method provides an efficient performance.