Abstract
Association rule mining (ARM) has been adopted in automatic semantic concept detection to discover the association patterns from the multimedia data and predict the target concept classes. As a rule-based method, ARM faces the challenges on rule pruning. Such challenges could be addressed by utilising proper interestingness measures. In this paper, a video semantic concept detection framework that uses ARM together with a novel correlation-based interestingness measure is proposed. The interestingness measure is obtained from applying multiple correspondence analysis (MCA) to capture the correlation between features and concept classes. This new correlation-based interestingness measure is first used in the rule generation stage, and then reused and combined with the inter-similarity and intra-similarity values to select the final rule set for classification. Experimented with 14 concepts from the benchmark TRECVID data, our proposed framework achieves higher accuracy than the other six classifiers that are commonly used in semantic concept detection.