A unified framework for semantics and feature based relevance feedback in image retrieval systems

Abstract

The relevance feedback approach to image retrieval is a powerful technique and has been an active research direction for the past few years. Various ad hoc parameter estimation techniques have been proposed for relevance feedback. In addition, methods that perform optimization on multi-level image content model have been formulated. However, these methods only perform relevance feedback on the low-level image features and fail to address the images' semantic content. In this paper, we propose a relevance feedback technique, iFind, to take advantage of the semantic contents of the images in addition to the low-level features. By forming a semantic network on top of the keyword association on the images, we are able to accurately deduce and utilize the images' semantic contents for retrieval purposes. The accuracy and effectiveness of our method is demonstrated with experimental results on real-world image collections.

Search for Multi-modality Data in Digital Libraries

“…A hybrid approach of semantics-and feature-based relevance feedback is proposed by Lu et al [2] for image retrieval. We generalize this method so that it can accommodate all kinds of media.…”

Bayesian fusion of camera metadata cues in semantic scene classification

“…For example, the use of key word annotations has been studied extensively in the context of image retrieval, e.g., [4,7]. Timestamps have been used successfully to cluster photographs by events [10].…”

Image retrieval and relevance feedback using peer indexing

“…In most cases, keywords are assigned manually, which is not only time-consuming but also vulnerable to subjective errors. In the iFind system [1], a semi-automatic image annotation strategy is devised to learn the keywords from the user feedbacks. Our learning strategy suggested in Section 2.2 can be regarded as the counterpart of that annotation strategy on the peer index.…”