Comparative Exudate Classification using Support Vector Machines and Neural Networks

A Osareh; M Mirmehdi; B Thomas; R Markham

Comparative Exudate Classification using Support Vector Machines and Neural Networks

A Osareh, M Mirmehdi, B Thomas, R Markham

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

104 Citations (Scopus)

Abstract

Abstract. After segmenting candidate exudates regions in colour retinal images we present and compare two methods for their classification. The Neural Network based approach performs marginally better than the Support Vector Machine based approach, but we show that the latter are more flexible given criteria such as control of sensitivity and specificity rates. We present classification results for different learning algorithms for the Neural Net and use both hard and soft margins for the Support Vector Machines. We also present ROC curves to examine the trade-off between the sensitivity and specificity of the classifiers.

Translated title of the contribution	Comparative Exudate Classification using Support Vector Machines and Neural Networks
Original language	English
Title of host publication	Unknown
Editors	T. Dohi, R. Kikinis
Publisher	Springer Berlin Heidelberg
Pages	413 - 420
Number of pages	7
Publication status	Published - Sept 2002

Bibliographical note

Conference Proceedings/Title of Journal: 5th International Conference on Medical Image Computing and Computer-Assisted Intervention

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000671

Handle.net

Persistent link

Cite this

@inproceedings{10c5551432c74156be958ca0e18041a2,

title = "Comparative Exudate Classification using Support Vector Machines and Neural Networks",

abstract = "Abstract. After segmenting candidate exudates regions in colour retinal images we present and compare two methods for their classification. The Neural Network based approach performs marginally better than the Support Vector Machine based approach, but we show that the latter are more flexible given criteria such as control of sensitivity and specificity rates. We present classification results for different learning algorithms for the Neural Net and use both hard and soft margins for the Support Vector Machines. We also present ROC curves to examine the trade-off between the sensitivity and specificity of the classifiers.",

author = "A Osareh and M Mirmehdi and B Thomas and R Markham",

note = "Conference Proceedings/Title of Journal: 5th International Conference on Medical Image Computing and Computer-Assisted Intervention",

year = "2002",

month = sep,

language = "English",

pages = "413 -- 420",

editor = "T. Dohi and R. Kikinis",

booktitle = "Unknown",

publisher = "Springer Berlin Heidelberg",

address = "Germany",

}

TY - GEN

T1 - Comparative Exudate Classification using Support Vector Machines and Neural Networks

AU - Osareh, A

AU - Mirmehdi, M

AU - Thomas, B

AU - Markham, R

N1 - Conference Proceedings/Title of Journal: 5th International Conference on Medical Image Computing and Computer-Assisted Intervention

PY - 2002/9

Y1 - 2002/9

N2 - Abstract. After segmenting candidate exudates regions in colour retinal images we present and compare two methods for their classification. The Neural Network based approach performs marginally better than the Support Vector Machine based approach, but we show that the latter are more flexible given criteria such as control of sensitivity and specificity rates. We present classification results for different learning algorithms for the Neural Net and use both hard and soft margins for the Support Vector Machines. We also present ROC curves to examine the trade-off between the sensitivity and specificity of the classifiers.

AB - Abstract. After segmenting candidate exudates regions in colour retinal images we present and compare two methods for their classification. The Neural Network based approach performs marginally better than the Support Vector Machine based approach, but we show that the latter are more flexible given criteria such as control of sensitivity and specificity rates. We present classification results for different learning algorithms for the Neural Net and use both hard and soft margins for the Support Vector Machines. We also present ROC curves to examine the trade-off between the sensitivity and specificity of the classifiers.

M3 - Conference Contribution (Conference Proceeding)

SP - 413

EP - 420

BT - Unknown

A2 - Dohi, T.

A2 - Kikinis, R.

PB - Springer Berlin Heidelberg

ER -

Comparative Exudate Classification using Support Vector Machines and Neural Networks

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this