Conference Paper

Classification of Near-Duplicate Video Segments Based on Their Appearance Patterns

Grad. Sch. of Inf. Sci., Nagoya Univ., Nagoya, Japan
DOI: 10.1109/ICPR.2010.766 Conference: Pattern Recognition (ICPR), 2010 20th International Conference on
Source: IEEE Xplore

ABSTRACT

We propose a method that analyzes the structure of a large volume of general broadcast video data by the appearance patterns of near-duplicate video segments. We define six classification rules based on the appearance patterns of near-duplicate video segments according to their roles, and evaluated them over more than 1,000 hours of actual broadcast video data.

Full-text preview

Available from: ac.jp
This research doesn't cite any other publications.