Xiangyu Jin

Improving Image Retrieval Effectiveness via Multiple Queries

Conventional approaches to image retrieval are based on the assumption that relevant images are physically near the query image in some feature space. This is the basis of the cluster hypothesis. However, semantically related images are often scattered across several visual clusters. Although traditional Content-based Image Retrieval (CBIR) technologies may utilize the information contained in multiple queries (gotten in one step or through a feedback process), this is often only a reformulation of the original query. As a result most of these strategies only get the images in some neighborhood of the original query as the retrieval result. This severely restricts the system performance. Relevance feedback techniques are generally used to mitigate this problem. In this paper, we present a novel approach to relevance feedback which can return semantically related images in different visual clusters by merging the result sets of multiple queries. We also provide experimental results to demonstrate the effectiveness of our approach.

An Empirical Investigation of the Scalability of a Multiple Viewpoint CBIR System

Our work in content-based image retrieval (CBIR) relies on content-analysis of multiple representations of an image which we term multiple viewpoints or channels. The conceptual idea is to place each image in multiple feature spaces and then perform retrieval by querying each of these spaces and merging the several responses. We have shown that a simple realization of this strategy can be used to boost the retrieval effectiveness of conventional CBIR. In this work we evaluate our framework in a larger, more demanding test environment and find that while absolute retrieval effectiveness is reduced, substantial relative improvement can be consistently attained.

An exogenous approach for adding multiple image representations to content-based image retrieval systems

Content-based image retrieval (CBIR) uses features that can be extracted from the images themselves. In previous work we have shown that using more than one representation of the images in a collection can improve the results presented to a user without changing the underlying feature extraction or search technologies French, J.C. et al., (2003). In this paper we show that we can also merge the results of multiple CBIR systems to achieve even greater retrieval effectiveness again without changing the underlying CBIR technology. We also present an example of this combined approach and show that it can dramatically improve retrieval effectiveness in content-based image retrieval systems.

Quantative analysis of the impact of judging inconsistency on the performance of relevance feedback

Practical constrains of user interfaces make the users judgment (during the feedback loop) deviate from real thoughts (when the full document is read).This is often overlooked in evaluation of relevance feedback.This paper quantitatively analyze the impact of judging inconsistency on the performance of relevance feedback.