EFFICIENT RELEVANT FEEDBACK FOR MINING USER NAVIGATION PATTERS USING CBIR

Computer Engineering

These a days, content-based image retrieval (CBIR) is the important of image retrieval systems. To be more suitable, relevance feedback techniques were changed into CBIR such that more the results can be obtained by taking user feedback into account. However, previous relevance feedback-based CBIR methods usually request a number of iterative feedbacks to produce refined search results, especially in a big image database. This is not practical and inefficient in real applications. In this paper, we propose a novel method, Navigation-Pattern-based Relevance Feedback (NPRF), to achieve the high efficiency and effectiveness of CBIR in coping with the large-scale image data. In terms of efficiency, the iterations of feedback are reduced substantially by using the navigation patterns discovered from the user query log. In terms of effectiveness, our proposed search algorithm NPRF Search makes use of the discovered navigation patterns and three kinds of query refinement strategies, Query Point Movement (QPM), Query Reweighting (QR), and Query Expansion (QEX), to converge the search space toward the user’s intention effectively

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.