A relevance feedback image retrieval scheme using multi-instance and pseudo image concepts

Feng Cheng Chang; Hsueh-Ming Hang

doi:10.1117/12.586678

A relevance feedback image retrieval scheme using multi-instance and pseudo image concepts

Feng Cheng Chang^*, Hsueh-Ming Hang

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Content-based image search has long been considered a difficult task. Making correct conjectures on the user intention (perception) based on the query images is a critical step in the content-based search. One key concept in this paper is how we find the user preferred image characteristics from the multiple positive samples provided by the user. The second key concept is that when the user does not provide a sufficient number of samples, how we generate a set of consistent "pseudo images". The notion of image feature stability is thus introduced. The third key concept is how we use negative images as pruning criterion. In realizing the preceding concepts, an image search scheme is developed using the weighted low-level image features. At the end, quantitative simulation results are used to show the effectiveness of these concepts.

Original language	English
Article number	23
Pages (from-to)	224-235
Number of pages	12
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	5682
DOIs	https://doi.org/10.1117/12.586678
State	Published - 21 Jul 2005
Event	Proceedings of SPIE-IS and T Electronic Imaging - Storage and Retrieval Methods for Multimedia 2005 - San Jose, CA, United States Duration: 18 Jan 2005 → 19 Jan 2005

Keywords

Image retrieval
Perception weighting

Access to Document

10.1117/12.586678

Cite this

@article{09abc52d7a6e426699e2fb18bcd541d9,

title = "A relevance feedback image retrieval scheme using multi-instance and pseudo image concepts",

abstract = "Content-based image search has long been considered a difficult task. Making correct conjectures on the user intention (perception) based on the query images is a critical step in the content-based search. One key concept in this paper is how we find the user preferred image characteristics from the multiple positive samples provided by the user. The second key concept is that when the user does not provide a sufficient number of samples, how we generate a set of consistent {"}pseudo images{"}. The notion of image feature stability is thus introduced. The third key concept is how we use negative images as pruning criterion. In realizing the preceding concepts, an image search scheme is developed using the weighted low-level image features. At the end, quantitative simulation results are used to show the effectiveness of these concepts.",

keywords = "Image retrieval, Perception weighting",

author = "Chang, {Feng Cheng} and Hsueh-Ming Hang",

year = "2005",

month = jul,

day = "21",

doi = "10.1117/12.586678",

language = "English",

volume = "5682",

pages = "224--235",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Proceedings of SPIE-IS and T Electronic Imaging - Storage and Retrieval Methods for Multimedia 2005 ; Conference date: 18-01-2005 Through 19-01-2005",

}

TY - JOUR

T1 - A relevance feedback image retrieval scheme using multi-instance and pseudo image concepts

AU - Chang, Feng Cheng

AU - Hang, Hsueh-Ming

PY - 2005/7/21

Y1 - 2005/7/21

N2 - Content-based image search has long been considered a difficult task. Making correct conjectures on the user intention (perception) based on the query images is a critical step in the content-based search. One key concept in this paper is how we find the user preferred image characteristics from the multiple positive samples provided by the user. The second key concept is that when the user does not provide a sufficient number of samples, how we generate a set of consistent "pseudo images". The notion of image feature stability is thus introduced. The third key concept is how we use negative images as pruning criterion. In realizing the preceding concepts, an image search scheme is developed using the weighted low-level image features. At the end, quantitative simulation results are used to show the effectiveness of these concepts.

AB - Content-based image search has long been considered a difficult task. Making correct conjectures on the user intention (perception) based on the query images is a critical step in the content-based search. One key concept in this paper is how we find the user preferred image characteristics from the multiple positive samples provided by the user. The second key concept is that when the user does not provide a sufficient number of samples, how we generate a set of consistent "pseudo images". The notion of image feature stability is thus introduced. The third key concept is how we use negative images as pruning criterion. In realizing the preceding concepts, an image search scheme is developed using the weighted low-level image features. At the end, quantitative simulation results are used to show the effectiveness of these concepts.

KW - Image retrieval

KW - Perception weighting

UR - http://www.scopus.com/inward/record.url?scp=21844447634&partnerID=8YFLogxK

U2 - 10.1117/12.586678

DO - 10.1117/12.586678

M3 - Conference article

AN - SCOPUS:21844447634

SN - 0277-786X

VL - 5682

SP - 224

EP - 235

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

M1 - 23

T2 - Proceedings of SPIE-IS and T Electronic Imaging - Storage and Retrieval Methods for Multimedia 2005

Y2 - 18 January 2005 through 19 January 2005

ER -

A relevance feedback image retrieval scheme using multi-instance and pseudo image concepts

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this