Generalized Manifold-Ranking-Based Image Retrieval

In this paper, we propose a general transductive learning framework named generalized manifold-ranking-based image retrieval (gMRBIR) for image retrieval. Comparing with an existing transductive learning method named MRBIR , our method could work well whether or not the query image is in the database; thus, it is more applicable for real applications. Given a query image, gMRBIR first initializes a pseudo seed vector based on neighborhood relationship and then spread its scores via manifold ranking to all the unlabeled images in the database. Furthermore, in gMRBIR, we also make use of relevance feedback and active learning to refine the retrieval result so that it converges to the query concept as fast as possible. Systematic experiments on a general-purpose image database consisting of 5 000 Corel images demonstrate the superiority of gMRBIR over state-of-the-art techniques

I. Introduction

The history of image retrieval can be traced back to the late 1970s, which aims to provide an effective and efficient tool for managing large image databases. Up until now, with the advent and popularity of World Wide Web, the number of digital images available for various purposes has grown tremendously, and many researchers have put their attention to the development of an image retrieval system, which works well in general or specific contexts [4], [14], [27], [30].