Premium
Scene similarity measure for video content segmentation in the framework of a rough indexing paradigm
Author(s) -
Krämer Petra,
BenoisPineau Jenny,
Domenger JeanPhilippe
Publication year - 2006
Publication title -
international journal of intelligent systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.291
H-Index - 87
eISSN - 1098-111X
pISSN - 0884-8173
DOI - 10.1002/int.20159
Subject(s) - search engine indexing , computer science , similarity measure , artificial intelligence , motion compensation , similarity (geometry) , segmentation , measure (data warehouse) , context (archaeology) , computer vision , content (measure theory) , pattern recognition (psychology) , data mining , image (mathematics) , mathematics , paleontology , mathematical analysis , biology
This article presents a scene similarity measure for video content segmentation. In the context of the rough indexing paradigm, we extract only partial information from MPEG compressed streams to measure the similarity of video frames through time. The similarity measure of I‐Frames is defined based on motion compensation of DC images and local contrast computation. The method allows a real‐time segmentation of the video content. © 2006 Wiley Periodicals, Inc. Int J Int Syst 21: 765–783, 2006.