Saliency-based multi-feature modeling for semantic image retrieval - Archive ouverte HAL Access content directly
Journal Articles Journal of Visual Communication and Image Representation Year : 2018

Saliency-based multi-feature modeling for semantic image retrieval

(1) , (1) , (1) , (2) , (1)
1
2

Abstract

Semantic gap is an important challenging problem in content-based image retrieval (CBIR) up to now. Bag-of-words (BOW) framework is a popular approach that tries to reduce the semantic gap in CBIR. In this paper, an approach integrating visual saliency model with BOW is proposed for semantic image retrieval. Images are firstly segmented into background regions and foreground objects by a visual saliency-based segmentation method. And then multi-features including Scale Invariant Feature Transform (SIFT) features packed in BOW are extracted from regions and objects respectively and fused considering different characteristics of background regions and foreground objects. Finally, a fusion of z-score normalized Chi-Square distance is adopted as the similarity measurement. This proposal has been implemented on two widely used benchmark databases and the results evaluated in terms of mean Average Precision (mAP) show that our proposal outperforms the referred state-of-the-art approaches. © 2017 Elsevier Inc.
Not file

Dates and versions

hal-01671560 , version 1 (22-12-2017)

Identifiers

Cite

C. Bai, J.-N. Chen, L. Huang, K. Kpalma, S. Chen. Saliency-based multi-feature modeling for semantic image retrieval. Journal of Visual Communication and Image Representation, 2018, 50, pp.199-204. ⟨10.1016/j.jvcir.2017.11.021⟩. ⟨hal-01671560⟩
126 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More