Effective extraction of Gabor features for adaptive mammogram retrieval

Chia Hung Wei, Yue Li, Chang Tsun Li

Research output: Book chapter/Published conference paperConference paper

22 Citations (Scopus)

Abstract

Breast cancer is one of the most common diseases among women. Content-based mammogram retrieval has been proposed to aid various medical procedures. To develop a content-based mammogram retrieval system, textural feature extraction is one of the crucial requirements. This study proposes a Gabor filtering method for the extraction of textural features, which firstly performs Gabor filtering on the underlying image, applies the physical properties of a probability wave to probability transformation and then computes features to describe the textural pattern of the mammogram. This study also proposes an adaptive strategy for feature selection, filter selection and feature weighting, which utilizes a user's relevance feedback to reduce the redundancy in the representation and incorporates the user's information needs in image retrieval. Experimental results show that hypothesis tests can effectively find discriminated features and this retrieval system can improve its performance through just a few rounds of relevance feedback.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
Pages1503-1506
Number of pages4
Publication statusPublished - 2007
EventIEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, China
Duration: 02 Jul 200705 Jul 2007

Conference

ConferenceIEEE International Conference onMultimedia and Expo, ICME 2007
CountryChina
CityBeijing
Period02/07/0705/07/07

Fingerprint

Content based retrieval
Feature extraction
Feedback
Image retrieval
Redundancy
Physical properties

Cite this

Wei, C. H., Li, Y., & Li, C. T. (2007). Effective extraction of Gabor features for adaptive mammogram retrieval. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007 (pp. 1503-1506). [4284947]
Wei, Chia Hung ; Li, Yue ; Li, Chang Tsun. / Effective extraction of Gabor features for adaptive mammogram retrieval. Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. pp. 1503-1506
@inproceedings{37533ad699e64743b104d3766f873a0c,
title = "Effective extraction of Gabor features for adaptive mammogram retrieval",
abstract = "Breast cancer is one of the most common diseases among women. Content-based mammogram retrieval has been proposed to aid various medical procedures. To develop a content-based mammogram retrieval system, textural feature extraction is one of the crucial requirements. This study proposes a Gabor filtering method for the extraction of textural features, which firstly performs Gabor filtering on the underlying image, applies the physical properties of a probability wave to probability transformation and then computes features to describe the textural pattern of the mammogram. This study also proposes an adaptive strategy for feature selection, filter selection and feature weighting, which utilizes a user's relevance feedback to reduce the redundancy in the representation and incorporates the user's information needs in image retrieval. Experimental results show that hypothesis tests can effectively find discriminated features and this retrieval system can improve its performance through just a few rounds of relevance feedback.",
author = "Wei, {Chia Hung} and Yue Li and Li, {Chang Tsun}",
year = "2007",
language = "English",
isbn = "1424410177",
pages = "1503--1506",
booktitle = "Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007",

}

Wei, CH, Li, Y & Li, CT 2007, Effective extraction of Gabor features for adaptive mammogram retrieval. in Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007., 4284947, pp. 1503-1506, IEEE International Conference onMultimedia and Expo, ICME 2007, Beijing, China, 02/07/07.

Effective extraction of Gabor features for adaptive mammogram retrieval. / Wei, Chia Hung; Li, Yue; Li, Chang Tsun.

Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. p. 1503-1506 4284947.

Research output: Book chapter/Published conference paperConference paper

TY - GEN

T1 - Effective extraction of Gabor features for adaptive mammogram retrieval

AU - Wei, Chia Hung

AU - Li, Yue

AU - Li, Chang Tsun

PY - 2007

Y1 - 2007

N2 - Breast cancer is one of the most common diseases among women. Content-based mammogram retrieval has been proposed to aid various medical procedures. To develop a content-based mammogram retrieval system, textural feature extraction is one of the crucial requirements. This study proposes a Gabor filtering method for the extraction of textural features, which firstly performs Gabor filtering on the underlying image, applies the physical properties of a probability wave to probability transformation and then computes features to describe the textural pattern of the mammogram. This study also proposes an adaptive strategy for feature selection, filter selection and feature weighting, which utilizes a user's relevance feedback to reduce the redundancy in the representation and incorporates the user's information needs in image retrieval. Experimental results show that hypothesis tests can effectively find discriminated features and this retrieval system can improve its performance through just a few rounds of relevance feedback.

AB - Breast cancer is one of the most common diseases among women. Content-based mammogram retrieval has been proposed to aid various medical procedures. To develop a content-based mammogram retrieval system, textural feature extraction is one of the crucial requirements. This study proposes a Gabor filtering method for the extraction of textural features, which firstly performs Gabor filtering on the underlying image, applies the physical properties of a probability wave to probability transformation and then computes features to describe the textural pattern of the mammogram. This study also proposes an adaptive strategy for feature selection, filter selection and feature weighting, which utilizes a user's relevance feedback to reduce the redundancy in the representation and incorporates the user's information needs in image retrieval. Experimental results show that hypothesis tests can effectively find discriminated features and this retrieval system can improve its performance through just a few rounds of relevance feedback.

UR - http://www.scopus.com/inward/record.url?scp=46449092520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46449092520&partnerID=8YFLogxK

M3 - Conference paper

AN - SCOPUS:46449092520

SN - 1424410177

SN - 9781424410170

SP - 1503

EP - 1506

BT - Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

ER -

Wei CH, Li Y, Li CT. Effective extraction of Gabor features for adaptive mammogram retrieval. In Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007. 2007. p. 1503-1506. 4284947