User Concept Pattern Discovery Using Relevance Feedback And Multiple Instance Learning For Content-Based Image Retrieval

Xin Huang, Shu-Ching Chen, Mei-Ling Shyu, Chengcui Zhang

Abstract: Understanding and learning the subjective aspect of humans in Content-Based Image Retrieval has been an active research field during the past few years. However, how to effectively discover users' concept patterns when there are multiple visual features existing in the retrieval system still remains a big issue. In this paper, we propose a multimedia data mining framework that incorporates Multiple Instance Learning into the user relevance feedback in a seamless way to discover the concept patterns of users, especially where the user's most interested region and how to map the local feature vector of that region to the high-level concept pattern of users. This underlying mapping can be progressively discovered through the feedback and learning procedure. The role user plays in the retrieval system is to guide the system mining process to his/her own focus of attention. The retrieval performance is tested under a couple of conditions.