Robust anchorperson detection for TV news segmentation

Ko Yen Lu*, Min Kuan Chang, Chia Hung Yeh, Maverick Shih

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we proposed a scheme for TV news segmentation via exploring the efficient visual features. The proposed scheme can be divided into three parts, such as shot change detection based on skin color; probable anchorperson shot detection and anchorperson detection. According to experimental results, our proposed method can efficiently decompose TV news into anchorperson shots and report shots. Compared to the traditional face detection methods, the proposed method can robustly exclude the non-anchorperson shots in report shots such as the interview scenes. Experimental results are given to demonstrate the feasibility and efficiency of the proposed technique.

Original languageEnglish
Title of host publicationMultimedia Systems and Applications IX
DOIs
Publication statusPublished - 2006
Externally publishedYes
EventMultimedia Systems and Applications IX - Boston, MA, United States
Duration: 2006 Oct 22006 Oct 3

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6391
ISSN (Print)0277-786X

Conference

ConferenceMultimedia Systems and Applications IX
Country/TerritoryUnited States
CityBoston, MA
Period2006/10/022006/10/03

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Robust anchorperson detection for TV news segmentation'. Together they form a unique fingerprint.

Cite this