EMR: A Scalable Graph-Based Ranking Model for Content-Based Image Retrieval
- 2 May 2013
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 27 (1), 102-114
- https://doi.org/10.1109/tkde.2013.70
Abstract
Graph-based ranking models have been widely applied in information retrieval area. In this paper, we focus on a well known graph-based model - the Ranking on Data Manifold model, or Manifold Ranking (MR). Particularly, it has been successfully applied to content-based image retrieval, because of its outstanding ability to discover underlying geometrical structure of the given image database. However, manifold ranking is computationally very expensive, which significantly limits its applicability to large databases especially for the cases that the queries are out of the database (new samples). We propose a novel scalable graph-based ranking model called Efficient Manifold Ranking (EMR), trying to address the shortcomings of MR from two main perspectives: scalable graph construction and efficient ranking computation. Specifically, we build an anchor graph on the database instead of a traditional k-nearest neighbor graph, and design a new form of adjacency matrix utilized to speed up the ranking. An approximate method is adopted for efficient out-of-sample retrieval. Experimental results on some large scale image databases demonstrate that EMR is a promising method for real world retrieval applications.Keywords
This publication has 32 references indexed in Scilit:
- Adaptive Hypergraph Learning and its Application in Image ClassificationIEEE Transactions on Image Processing, 2012
- Learning Incoherent Sparse and Low-Rank Patterns from Multiple TasksACM Transactions on Knowledge Discovery From Data, 2012
- Fast Manifold-Ranking for Content-Based Image RetrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Prototype vector machine for large scale semi-supervised learningPublished by Association for Computing Machinery (ACM) ,2009
- Generalized Manifold-Ranking-Based Image RetrievalIEEE Transactions on Image Processing, 2006
- Active learning via transductive experimental designPublished by Association for Computing Machinery (ACM) ,2006
- Ranking on graph dataPublished by Association for Computing Machinery (ACM) ,2006
- Manifold-ranking based image retrievalPublished by Association for Computing Machinery (ACM) ,2004
- An efficient k-means clustering algorithm: analysis and implementationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Support vector machine active learning for image retrievalPublished by Association for Computing Machinery (ACM) ,2001