Welcome to the InfoSci Platform
Reference Hub33
Weighted Association Rule Mining for Video Semantic Detection

Weighted Association Rule Mining for Video Semantic Detection

Lin Lin, Mei-Ling Shyu
Copyright: © 2010 |Volume: 1 |Issue: 1 |Pages: 18
ISSN: 1947-8534|EISSN: 1947-8542|ISSN: 1947-8534|EISBN13: 9781616929954|EISSN: 1947-8542|DOI: 10.4018/jmdem.2010111203
Cite Article Cite Article

MLA

Lin, Lin, and Mei-Ling Shyu. "Weighted Association Rule Mining for Video Semantic Detection." IJMDEM vol.1, no.1 2010: pp.37-54. http://doi.org/10.4018/jmdem.2010111203

APA

Lin, L. & Shyu, M. (2010). Weighted Association Rule Mining for Video Semantic Detection. International Journal of Multimedia Data Engineering and Management (IJMDEM), 1(1), 37-54. http://doi.org/10.4018/jmdem.2010111203

Chicago

Lin, Lin, and Mei-Ling Shyu. "Weighted Association Rule Mining for Video Semantic Detection," International Journal of Multimedia Data Engineering and Management (IJMDEM) 1, no.1: 37-54. http://doi.org/10.4018/jmdem.2010111203

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Semantic knowledge detection of multimedia content has become a very popular research topic in recent years. The association rule mining (ARM) technique has been shown to be an efficient and accurate approach for content-based multimedia retrieval and semantic concept detection in many applications. To further improve the performance of traditional association rule mining technique, a video semantic concept detection framework whose classifier is built upon a new weighted association rule mining (WARM) algorithm is proposed in this article. Our proposed WARM algorithm is able to capture the different significance degrees of the items (feature-value pairs) in generating the association rules for video semantic concept detection. Our proposed WARM-based framework first applies multiple correspondence analysis (MCA) to project the features and classes into a new principle component space and discover the correlation between feature-value pairs and classes. Next, it considers both correlation and percentage information as the measurement to weight the feature-value pairs and to generate the association rules. Finally, it performs classification by using these weighted association rules. To evaluate our WARM-based framework, we compare its performance of video semantic concept detection with several well-known classifiers using the benchmark data available from the 2007 and 2008 TRECVID projects. The results demonstrate that our WARM-based framework achieves promising performance and performs significantly better than those classifiers in the comparison.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.