MR-MIL: Manifold Ranking Based Multiple-Instance Learning for Automatic Image Annotation

Yufeng ZHAO; Yao ZHAO; Zhenfeng ZHU; Jeng-Shyang PAN

doi:10.1093/ietfec/e91-a.10.3088

Regular Section

MR-MIL: Manifold Ranking Based Multiple-Instance Learning for Automatic Image Annotation

Yufeng ZHAO, Yao ZHAO, Zhenfeng ZHU, Jeng-Shyang PAN

Author information

Keywords: automatic image annotation, multiple-instance leaning, manifold ranking, SVM

JOURNAL RESTRICTED ACCESS

2008 Volume E91.A Issue 10 Pages 3088-3089

DOI https://doi.org/10.1093/ietfec/e91-a.10.3088

Details

Abstract

A novel automatic image annotation (AIA) scheme is proposed based on multiple-instance learning (MIL). For a given concept, manifold ranking (MR) is first employed to MIL (referred as MR-MIL) for effectively mining the positive instances (i. e. regions in images) embedded in the positive bags (i. e. images). With the mined positive instances, the semantic model of the concept is built by the probabilistic output of SVM classifier. The experimental results reveal that high annotation accuracy can be achieved at region-level.

Corresponding author

Register with J-STAGE for free!