A Novel Saliency-Based Graph Learning Framework with Application to CBIR

Hong BAO; Song-He FENG; De XU; Shuoyan LIU

doi:10.1587/transinf.E94.D.1353

A Novel Saliency-Based Graph Learning Framework with Application to CBIR

Hong BAO, Song-He FENG, De XU, Shuoyan LIU

Full Text Views

0

Share
Cite this

Summary :

Localized content-based image retrieval (LCBIR) has emerged as a hot topic more recently because in the scenario of CBIR, the user is interested in a portion of the image and the rest of the image is irrelevant. In this paper, we propose a novel region-level relevance feedback method to solve the LCBIR problem. Firstly, the visual attention model is employed to measure the regional saliency of each image in the feedback image set provided by the user. Secondly, the regions in the image set are constructed to form an affinity matrix and a novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. After the iteration, regions in the positive images with high confident scores are selected as the candidate query set to conduct the next-round retrieval task until the retrieval results are satisfactory. Experimental results conducted on the SIVAL dataset demonstrate the effectiveness of the proposed approach.

Publication: IEICE TRANSACTIONS on Information Vol.E94-D No.6 pp.1353-1356

Publication Date: 2011/06/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E94.D.1353

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Cite this

Copy

Hong BAO, Song-He FENG, De XU, Shuoyan LIU, "A Novel Saliency-Based Graph Learning Framework with Application to CBIR" in IEICE TRANSACTIONS on Information, vol. E94-D, no. 6, pp. 1353-1356, June 2011, doi: 10.1587/transinf.E94.D.1353.
Abstract: Localized content-based image retrieval (LCBIR) has emerged as a hot topic more recently because in the scenario of CBIR, the user is interested in a portion of the image and the rest of the image is irrelevant. In this paper, we propose a novel region-level relevance feedback method to solve the LCBIR problem. Firstly, the visual attention model is employed to measure the regional saliency of each image in the feedback image set provided by the user. Secondly, the regions in the image set are constructed to form an affinity matrix and a novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. After the iteration, regions in the positive images with high confident scores are selected as the candidate query set to conduct the next-round retrieval task until the retrieval results are satisfactory. Experimental results conducted on the SIVAL dataset demonstrate the effectiveness of the proposed approach.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1353/_p

Copy

@ARTICLE{e94-d_6_1353,
author={Hong BAO, Song-He FENG, De XU, Shuoyan LIU, },
journal={IEICE TRANSACTIONS on Information},
title={A Novel Saliency-Based Graph Learning Framework with Application to CBIR},
year={2011},
volume={E94-D},
number={6},
pages={1353-1356},
abstract={Localized content-based image retrieval (LCBIR) has emerged as a hot topic more recently because in the scenario of CBIR, the user is interested in a portion of the image and the rest of the image is irrelevant. In this paper, we propose a novel region-level relevance feedback method to solve the LCBIR problem. Firstly, the visual attention model is employed to measure the regional saliency of each image in the feedback image set provided by the user. Secondly, the regions in the image set are constructed to form an affinity matrix and a novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. After the iteration, regions in the positive images with high confident scores are selected as the candidate query set to conduct the next-round retrieval task until the retrieval results are satisfactory. Experimental results conducted on the SIVAL dataset demonstrate the effectiveness of the proposed approach.},
keywords={},
doi={10.1587/transinf.E94.D.1353},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - A Novel Saliency-Based Graph Learning Framework with Application to CBIR
T2 - IEICE TRANSACTIONS on Information
SP - 1353
EP - 1356
AU - Hong BAO
AU - Song-He FENG
AU - De XU
AU - Shuoyan LIU
PY - 2011
DO - 10.1587/transinf.E94.D.1353
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2011
AB - Localized content-based image retrieval (LCBIR) has emerged as a hot topic more recently because in the scenario of CBIR, the user is interested in a portion of the image and the rest of the image is irrelevant. In this paper, we propose a novel region-level relevance feedback method to solve the LCBIR problem. Firstly, the visual attention model is employed to measure the regional saliency of each image in the feedback image set provided by the user. Secondly, the regions in the image set are constructed to form an affinity matrix and a novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. After the iteration, regions in the positive images with high confident scores are selected as the candidate query set to conduct the next-round retrieval task until the retrieval results are satisfactory. Experimental results conducted on the SIVAL dataset demonstrate the effectiveness of the proposed approach.
ER -