Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis

Lucia Ballerini; Xiang Li; Robert B. Fisher; Ben Aldridge; Jonathan Rees

doi:10.1007/978-3-642-12239-2_32

Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis

Lucia Ballerini, Xiang Li, Robert B. Fisher, Ben Aldridge, Jonathan Rees

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper gives an example of evolved features that improve image retrieval performance. A content-based image retrieval system for skin lesion images is presented. The aim is to support decision making by retrieving and displaying relevant past cases visually similar to the one under examination. Skin lesions of five common classes, including two non-melanoma cancer types, are used. Colour and texture features are extracted from lesions. Evolutionary algorithms are used to create composite features that optimise a similarity matching function. Experiments on our database of 533 images are performed and results are compared to those obtained using simple features. The use of the evolved composite features improves the precision by about 7%.

Original language	English
Title of host publication	APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS
Editors	C DiChic, C Cotta, M Ebner, A Ekart, AI EsparciaAlcazar, CK Goh, JJ Merelo, F Neri, M Preuss, J Togelius, GN Yannakakis
Place of Publication	BERLIN
Publisher	Springer
Pages	312-319
Number of pages	8
ISBN (Print)	978-3-642-12238-5
DOIs	https://doi.org/10.1007/978-3-642-12239-2_32
Publication status	Published - 2010
Event	European Conference on the Applications of Evolutionary Computation - Istanbul Duration: 7 Apr 2010 → 9 Apr 2010

Conference

Conference	European Conference on the Applications of Evolutionary Computation
City	Istanbul
Period	7/04/10 → 9/04/10

Access to Document

10.1007/978-3-642-12239-2_32

Ballerini et al 2010
The final publication is available at link.springer.com
Submitted manuscript, 831 KB

http://link.springer.com/chapter/10.1007%2F978-3-642-12239-2_32

Cite this

Ballerini, L., Li, X., Fisher, R. B., Aldridge, B., & Rees, J. (2010). Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis. In C. DiChic, C. Cotta, M. Ebner, A. Ekart, AI. EsparciaAlcazar, CK. Goh, JJ. Merelo, F. Neri, M. Preuss, J. Togelius, & GN. Yannakakis (Eds.), APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS (pp. 312-319). Springer. https://doi.org/10.1007/978-3-642-12239-2_32

Ballerini, Lucia ; Li, Xiang ; Fisher, Robert B. et al. / Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis. APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS. editor / C DiChic ; C Cotta ; M Ebner ; A Ekart ; AI EsparciaAlcazar ; CK Goh ; JJ Merelo ; F Neri ; M Preuss ; J Togelius ; GN Yannakakis. BERLIN : Springer, 2010. pp. 312-319

@inproceedings{eba6bb2088784c478d83e8f4b52bf38b,

title = "Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis",

abstract = "This paper gives an example of evolved features that improve image retrieval performance. A content-based image retrieval system for skin lesion images is presented. The aim is to support decision making by retrieving and displaying relevant past cases visually similar to the one under examination. Skin lesions of five common classes, including two non-melanoma cancer types, are used. Colour and texture features are extracted from lesions. Evolutionary algorithms are used to create composite features that optimise a similarity matching function. Experiments on our database of 533 images are performed and results are compared to those obtained using simple features. The use of the evolved composite features improves the precision by about 7%.",

author = "Lucia Ballerini and Xiang Li and Fisher, {Robert B.} and Ben Aldridge and Jonathan Rees",

year = "2010",

doi = "10.1007/978-3-642-12239-2_32",

language = "English",

isbn = "978-3-642-12238-5",

pages = "312--319",

editor = "C DiChic and C Cotta and M Ebner and A Ekart and AI EsparciaAlcazar and CK Goh and JJ Merelo and F Neri and M Preuss and J Togelius and GN Yannakakis",

booktitle = "APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS",

publisher = "Springer",

address = "United Kingdom",

note = "European Conference on the Applications of Evolutionary Computation ; Conference date: 07-04-2010 Through 09-04-2010",

}

Ballerini, L, Li, X, Fisher, RB, Aldridge, B & Rees, J 2010, Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis. in C DiChic, C Cotta, M Ebner, A Ekart, AI EsparciaAlcazar, CK Goh, JJ Merelo, F Neri, M Preuss, J Togelius & GN Yannakakis (eds), APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS. Springer, BERLIN, pp. 312-319, European Conference on the Applications of Evolutionary Computation, Istanbul, 7/04/10. https://doi.org/10.1007/978-3-642-12239-2_32

Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis. / Ballerini, Lucia; Li, Xiang; Fisher, Robert B. et al.
APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS. ed. / C DiChic; C Cotta; M Ebner; A Ekart; AI EsparciaAlcazar; CK Goh; JJ Merelo; F Neri; M Preuss; J Togelius; GN Yannakakis. BERLIN: Springer, 2010. p. 312-319.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis

AU - Ballerini, Lucia

AU - Li, Xiang

AU - Fisher, Robert B.

AU - Aldridge, Ben

AU - Rees, Jonathan

PY - 2010

Y1 - 2010

N2 - This paper gives an example of evolved features that improve image retrieval performance. A content-based image retrieval system for skin lesion images is presented. The aim is to support decision making by retrieving and displaying relevant past cases visually similar to the one under examination. Skin lesions of five common classes, including two non-melanoma cancer types, are used. Colour and texture features are extracted from lesions. Evolutionary algorithms are used to create composite features that optimise a similarity matching function. Experiments on our database of 533 images are performed and results are compared to those obtained using simple features. The use of the evolved composite features improves the precision by about 7%.

AB - This paper gives an example of evolved features that improve image retrieval performance. A content-based image retrieval system for skin lesion images is presented. The aim is to support decision making by retrieving and displaying relevant past cases visually similar to the one under examination. Skin lesions of five common classes, including two non-melanoma cancer types, are used. Colour and texture features are extracted from lesions. Evolutionary algorithms are used to create composite features that optimise a similarity matching function. Experiments on our database of 533 images are performed and results are compared to those obtained using simple features. The use of the evolved composite features improves the precision by about 7%.

U2 - 10.1007/978-3-642-12239-2_32

DO - 10.1007/978-3-642-12239-2_32

M3 - Conference contribution

SN - 978-3-642-12238-5

SP - 312

EP - 319

BT - APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS

A2 - DiChic, C

A2 - Cotta, C

A2 - Ebner, M

A2 - Ekart, A

A2 - EsparciaAlcazar, AI

A2 - Goh, CK

A2 - Merelo, JJ

A2 - Neri, F

A2 - Preuss, M

A2 - Togelius, J

A2 - Yannakakis, GN

PB - Springer

CY - BERLIN

T2 - European Conference on the Applications of Evolutionary Computation

Y2 - 7 April 2010 through 9 April 2010

ER -

Ballerini L, Li X, Fisher RB, Aldridge B, Rees J. Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis. In DiChic C, Cotta C, Ebner M, Ekart A, EsparciaAlcazar AI, Goh CK, Merelo JJ, Neri F, Preuss M, Togelius J, Yannakakis GN, editors, APPLICATIONS OF EVOLUTIONARY COMPUTATION, PT I, PROCEEDINGS. BERLIN: Springer. 2010. p. 312-319 doi: 10.1007/978-3-642-12239-2_32

Content-Based Image Retrieval of Skin Lesions by Evolutionary Feature Synthesis

Abstract

Conference

Access to Document

Fingerprint

Cite this