QDFA: Query-dependent feature aggregation for medical image retrieval

Yonggang Huang; Dianfu Ma; Jun Zhang; Yongwang Zhao

doi:10.1587/transinf.E95.D.275

QDFA: Query-dependent feature aggregation for medical image retrieval

Yonggang Huang^*
, Dianfu Ma
, Jun Zhang
, Yongwang Zhao

^*Corresponding author for this work

School of Computer Science and Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

We propose a novel query-dependent feature aggregation (QDFA) method for medical image retrieval. The QDFA method can learn an optimal feature aggregation function for a multi-example query, which takes into account multiple features and multiple examples with different importance. The experiments demonstrate that the QDFA method outperforms three other feature aggregation methods.

Original language	English
Pages (from-to)	275-279
Number of pages	5
Journal	IEICE Transactions on Information and Systems
Volume	E-95-D
Issue number	1
DOIs	https://doi.org/10.1587/transinf.E95.D.275
State	Published - Jan 2012

Keywords

CBIR
Feature aggregation
Fuzzy SVM
Query-dependent

Access to Document

10.1587/transinf.E95.D.275

Cite this

@article{068e25cc753a42e6a044b8630b95f935,

title = "QDFA: Query-dependent feature aggregation for medical image retrieval",

abstract = "We propose a novel query-dependent feature aggregation (QDFA) method for medical image retrieval. The QDFA method can learn an optimal feature aggregation function for a multi-example query, which takes into account multiple features and multiple examples with different importance. The experiments demonstrate that the QDFA method outperforms three other feature aggregation methods.",

keywords = "CBIR, Feature aggregation, Fuzzy SVM, Query-dependent",

author = "Yonggang Huang and Dianfu Ma and Jun Zhang and Yongwang Zhao",

year = "2012",

month = jan,

doi = "10.1587/transinf.E95.D.275",

language = "英语",

volume = "E-95-D",

pages = "275--279",

journal = "IEICE Transactions on Information and Systems",

issn = "0916-8532",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "1",

}

TY - JOUR

T1 - QDFA

T2 - Query-dependent feature aggregation for medical image retrieval

AU - Huang, Yonggang

AU - Ma, Dianfu

AU - Zhang, Jun

AU - Zhao, Yongwang

PY - 2012/1

Y1 - 2012/1

N2 - We propose a novel query-dependent feature aggregation (QDFA) method for medical image retrieval. The QDFA method can learn an optimal feature aggregation function for a multi-example query, which takes into account multiple features and multiple examples with different importance. The experiments demonstrate that the QDFA method outperforms three other feature aggregation methods.

AB - We propose a novel query-dependent feature aggregation (QDFA) method for medical image retrieval. The QDFA method can learn an optimal feature aggregation function for a multi-example query, which takes into account multiple features and multiple examples with different importance. The experiments demonstrate that the QDFA method outperforms three other feature aggregation methods.

KW - CBIR

KW - Feature aggregation

KW - Fuzzy SVM

KW - Query-dependent

UR - https://www.scopus.com/pages/publications/84855299875

U2 - 10.1587/transinf.E95.D.275

DO - 10.1587/transinf.E95.D.275

M3 - 文章

AN - SCOPUS:84855299875

SN - 0916-8532

VL - E-95-D

SP - 275

EP - 279

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

IS - 1

ER -

QDFA: Query-dependent feature aggregation for medical image retrieval

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this