An empirical mode decomposition approach for automatic diagnosis of retina digital images

Salim Lahmiri; Christian S. Gargour; Marcel Gabrea

doi:10.1109/CCECE.2012.6334830

An empirical mode decomposition approach for automatic diagnosis of retina digital images

Salim Lahmiri
, Christian S. Gargour
, Marcel Gabrea

École de technologie supérieure

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

3 Citations (Scopus)

Abstract

In this study six statistical textural features are extracted from retina digital images processed with the empirical mode decomposition (EMD). They are the mean, standard deviation, smoothness, third moment, uniformity, and entropy. The purpose is to classify normal and abnormal images. Five different pathologies are considered. They are artery sheath, blot hemorrhage, circinates, age-related macular drusens, and microaneurysms. Support vector machines are employed as classifier. Ten random folds are generated to perform cross-validation tests. The average and standard deviation of the correct recognition rate, sensitivity and specificity are computed for each simulation to assess the performance of the classifier. The obtained results generally outperform those given by using the discrete wavelet transform (DWT) instead of the EMD.

Original language	English
Title of host publication	2012 25th IEEE Canadian Conference on Electrical and Computer Engineering
Subtitle of host publication	Vision for a Greener Future, CCECE 2012
DOIs	https://doi.org/10.1109/CCECE.2012.6334830
Publication status	Published - 2012
Event	2012 25th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2012 - Montreal, QC, Canada Duration: 29 Apr 2012 → 2 May 2012

Publication series

Name	2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012

Conference

Conference	2012 25th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2012
Country/Territory	Canada
City	Montreal, QC
Period	29/04/12 → 2/05/12

!!!Keywords

Classification
Discrete wavelet transform
Empirical mode decomposition
Retina digital image
Support vector machines

Access to Document

10.1109/CCECE.2012.6334830

Cite this

Lahmiri, S., Gargour, C. S., & Gabrea, M. (2012). An empirical mode decomposition approach for automatic diagnosis of retina digital images. In 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012 Article 6334830 (2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012). https://doi.org/10.1109/CCECE.2012.6334830

Lahmiri, Salim ; Gargour, Christian S. ; Gabrea, Marcel. / An empirical mode decomposition approach for automatic diagnosis of retina digital images. 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012. 2012. (2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012).

@inproceedings{421ce4cf044d40689cee0d4f21e58751,

title = "An empirical mode decomposition approach for automatic diagnosis of retina digital images",

abstract = "In this study six statistical textural features are extracted from retina digital images processed with the empirical mode decomposition (EMD). They are the mean, standard deviation, smoothness, third moment, uniformity, and entropy. The purpose is to classify normal and abnormal images. Five different pathologies are considered. They are artery sheath, blot hemorrhage, circinates, age-related macular drusens, and microaneurysms. Support vector machines are employed as classifier. Ten random folds are generated to perform cross-validation tests. The average and standard deviation of the correct recognition rate, sensitivity and specificity are computed for each simulation to assess the performance of the classifier. The obtained results generally outperform those given by using the discrete wavelet transform (DWT) instead of the EMD.",

keywords = "Classification, Discrete wavelet transform, Empirical mode decomposition, Retina digital image, Support vector machines",

author = "Salim Lahmiri and Gargour, \{Christian S.\} and Marcel Gabrea",

year = "2012",

doi = "10.1109/CCECE.2012.6334830",

language = "English",

isbn = "9781467314336",

series = "2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012",

booktitle = "2012 25th IEEE Canadian Conference on Electrical and Computer Engineering",

note = "2012 25th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2012 ; Conference date: 29-04-2012 Through 02-05-2012",

}

Lahmiri, S, Gargour, CS & Gabrea, M 2012, An empirical mode decomposition approach for automatic diagnosis of retina digital images. in 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012., 6334830, 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012, 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2012, Montreal, QC, Canada, 29/04/12. https://doi.org/10.1109/CCECE.2012.6334830

An empirical mode decomposition approach for automatic diagnosis of retina digital images. / Lahmiri, Salim; Gargour, Christian S.; Gabrea, Marcel.
2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012. 2012. 6334830 (2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012).

Research output: Contribution to Book/Report types › Contribution to conference proceedings › peer-review

TY - GEN

T1 - An empirical mode decomposition approach for automatic diagnosis of retina digital images

AU - Lahmiri, Salim

AU - Gargour, Christian S.

AU - Gabrea, Marcel

PY - 2012

Y1 - 2012

N2 - In this study six statistical textural features are extracted from retina digital images processed with the empirical mode decomposition (EMD). They are the mean, standard deviation, smoothness, third moment, uniformity, and entropy. The purpose is to classify normal and abnormal images. Five different pathologies are considered. They are artery sheath, blot hemorrhage, circinates, age-related macular drusens, and microaneurysms. Support vector machines are employed as classifier. Ten random folds are generated to perform cross-validation tests. The average and standard deviation of the correct recognition rate, sensitivity and specificity are computed for each simulation to assess the performance of the classifier. The obtained results generally outperform those given by using the discrete wavelet transform (DWT) instead of the EMD.

AB - In this study six statistical textural features are extracted from retina digital images processed with the empirical mode decomposition (EMD). They are the mean, standard deviation, smoothness, third moment, uniformity, and entropy. The purpose is to classify normal and abnormal images. Five different pathologies are considered. They are artery sheath, blot hemorrhage, circinates, age-related macular drusens, and microaneurysms. Support vector machines are employed as classifier. Ten random folds are generated to perform cross-validation tests. The average and standard deviation of the correct recognition rate, sensitivity and specificity are computed for each simulation to assess the performance of the classifier. The obtained results generally outperform those given by using the discrete wavelet transform (DWT) instead of the EMD.

KW - Classification

KW - Discrete wavelet transform

KW - Empirical mode decomposition

KW - Retina digital image

KW - Support vector machines

UR - https://www.scopus.com/pages/publications/84870412350

U2 - 10.1109/CCECE.2012.6334830

DO - 10.1109/CCECE.2012.6334830

M3 - Contribution to conference proceedings

AN - SCOPUS:84870412350

SN - 9781467314336

T3 - 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012

BT - 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering

T2 - 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2012

Y2 - 29 April 2012 through 2 May 2012

ER -

Lahmiri S, Gargour CS, Gabrea M. An empirical mode decomposition approach for automatic diagnosis of retina digital images. In 2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012. 2012. 6334830. (2012 25th IEEE Canadian Conference on Electrical and Computer Engineering: Vision for a Greener Future, CCECE 2012). doi: 10.1109/CCECE.2012.6334830

An empirical mode decomposition approach for automatic diagnosis of retina digital images

Abstract

Publication series

Conference

!!!Keywords

Access to Document

Other files and links

Fingerprint

Cite this