Anchorperson Detection for TV News Segmentation System viaVisual Features

• Main Authors: Ko-Yen Lu, 呂科諺
• Other Authors: 張敏寬
• Format: Others
• Language: en_US
• Published: 2007
• Online Access: http://ndltd.ncl.edu.tw/handle/88735793065027978044

碩士 === 國立中興大學 === 電機工程學系所 === 94 === In this thesis, we designed a scheme for TV news segmentation via video content analysis techniques and explored the efficient visual features. The scheme can be divided into three parts, such as anchorperson shot change detection based on skin color, probable anchorperson segment detection and anchorperson detection. An anchorperson shot surely contains face region, and this feature is informative and important for anchorperson shot change detection. In order to reduce computational complexity for face detection, we only use skin color information as the major tool for searching face region. Otherwise, the anchorperson shot time should be shorter than that of a report shot time. As a result, we make use of the properties above also called time constraint method to discover the probable anchorperson segments. However, the probable anchorperson segment might involve the report segment, it will effect the detect precision. Here, we exploit the region histogram based on non-skin color method to exclude report segments. According to simulation results, our proposed method can efficiently decompose TV news into anchorperson shots and report segments. The proposed method can easily apply to software and hardware based personal video recorder for efficiently accessing the large amount of TV news video in the near future.