NCTU-DBLAB@Imageclefmed 2005: Medical image retrieval task

Pei Cheng Cheng; Been Chian Chien; Hao Ren Ke; Wei Pang Yang

NCTU-DBLAB@Imageclefmed 2005: Medical image retrieval task

Pei Cheng Cheng^*, Been Chian Chien, Hao Ren Ke, Wei Pang Yang

^*Corresponding author for this work

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

Abstract

In this paper, we use Support Vector Machine (SVM) to learn image feature characteristics for assisting the task of image classification. The ImageCLEF 2005 evaluation offers a superior test bed for medical image content retrieval. Several image visual features (including histogram, spatial layout, coherence moment and gabor features) have been employed in this paper to categorize the 1,000 test images into 57 classes. Based on the SVM model, we can examine which image feature is more promising in medical image retrieval. The result shows that the spatial relationship of pixels is a very important feature in medical image data, because medical image data always have similar anatomic regions (lung, liver, head, and so on); therefore image features emphasizing spatial relationship have better result than others.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	1171
Publication status	Published - 2005
Externally published	Yes
Event	2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005 - Wien, Austria Duration: 2005 Sept 21 → 2005 Sept 22

Keywords

Medical Image Classification
Support Vector Machine

ASJC Scopus subject areas

General Computer Science

Cite this

@article{9be6afe3ad79486b959d055bf902f2bc,

title = "NCTU-DBLAB@Imageclefmed 2005: Medical image retrieval task",

abstract = "In this paper, we use Support Vector Machine (SVM) to learn image feature characteristics for assisting the task of image classification. The ImageCLEF 2005 evaluation offers a superior test bed for medical image content retrieval. Several image visual features (including histogram, spatial layout, coherence moment and gabor features) have been employed in this paper to categorize the 1,000 test images into 57 classes. Based on the SVM model, we can examine which image feature is more promising in medical image retrieval. The result shows that the spatial relationship of pixels is a very important feature in medical image data, because medical image data always have similar anatomic regions (lung, liver, head, and so on); therefore image features emphasizing spatial relationship have better result than others.",

keywords = "Medical Image Classification, Support Vector Machine",

author = "Cheng, {Pei Cheng} and Chien, {Been Chian} and Ke, {Hao Ren} and Yang, {Wei Pang}",

year = "2005",

language = "English",

volume = "1171",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

note = "2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005 ; Conference date: 21-09-2005 Through 22-09-2005",

}

TY - JOUR

T1 - NCTU-DBLAB@Imageclefmed 2005

T2 - 2005 Cross Language Evaluation Forum Workshop, CLEF 2005, co-located with the 9th European Conference on Digital Libraries, ECDL 2005

AU - Cheng, Pei Cheng

AU - Chien, Been Chian

AU - Ke, Hao Ren

AU - Yang, Wei Pang

PY - 2005

Y1 - 2005

N2 - In this paper, we use Support Vector Machine (SVM) to learn image feature characteristics for assisting the task of image classification. The ImageCLEF 2005 evaluation offers a superior test bed for medical image content retrieval. Several image visual features (including histogram, spatial layout, coherence moment and gabor features) have been employed in this paper to categorize the 1,000 test images into 57 classes. Based on the SVM model, we can examine which image feature is more promising in medical image retrieval. The result shows that the spatial relationship of pixels is a very important feature in medical image data, because medical image data always have similar anatomic regions (lung, liver, head, and so on); therefore image features emphasizing spatial relationship have better result than others.

AB - In this paper, we use Support Vector Machine (SVM) to learn image feature characteristics for assisting the task of image classification. The ImageCLEF 2005 evaluation offers a superior test bed for medical image content retrieval. Several image visual features (including histogram, spatial layout, coherence moment and gabor features) have been employed in this paper to categorize the 1,000 test images into 57 classes. Based on the SVM model, we can examine which image feature is more promising in medical image retrieval. The result shows that the spatial relationship of pixels is a very important feature in medical image data, because medical image data always have similar anatomic regions (lung, liver, head, and so on); therefore image features emphasizing spatial relationship have better result than others.

KW - Medical Image Classification

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=84922022135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922022135&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84922022135

SN - 1613-0073

VL - 1171

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 21 September 2005 through 22 September 2005

ER -

NCTU-DBLAB@Imageclefmed 2005: Medical image retrieval task

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this