Iris feature extraction using principally rotated complex wavelet filters (PR-CWF)

Charles O. Ukpai; S. S. Dlay; W. L. Woo

doi:10.1109/ICCVIA.2015.7351904

Iris feature extraction using principally rotated complex wavelet filters (PR-CWF)

Charles O. Ukpai, S. S. Dlay, W. L. Woo

Computer Information Sciences Department

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

7 Citations (Scopus)

Abstract

Deriving effective iris feature from the segmented iris image is a crucial step in iris recognition system. In this paper we propose a new iris feature extraction method based on the Principal Texture Pattern (PTP) and dual tree complex wavelet transform (DT-CWT). We compute the principal direction (PD) of the iris texture using principal component analysis (PCA) and obtain the angle θ of the PD. Then, complex wavelet filters CWFs are constructed and rotated in the direction θ of the PD and also in the opposite direction - θ for decomposition of the image into 12 sub-bands using DT-CWT. Rotational invariant and scale invariant features are obtained by combining LL and HL sub-bands at each level. Consequently, channel energies and standard deviations are constructed as feature representation of the iris while SVM is used for classification of iris images. Our experiments demonstrate the superiority of the proposed method on CASIA iris databases, over existing methods.

Original language	English
Title of host publication	Proceedings - International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015
Publisher	IEEE
ISBN (Electronic)	9781479971862
ISBN (Print)	9781479971855
DOIs	https://doi.org/10.1109/ICCVIA.2015.7351904
Publication status	Published - 10 Dec 2015
Event	International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015 - Sousse, Tunisia Duration: 18 Jan 2015 → 20 Jan 2015

Conference

Conference	International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015
Country/Territory	Tunisia
City	Sousse
Period	18/01/15 → 20/01/15

Keywords

complex wavelet
discrete wavelet transform
Gabor filters
Iris recognition
principal component analysis

Access to Document

10.1109/ICCVIA.2015.7351904

Cite this

@inproceedings{c68cf9effa334c279f197f36d260bb86,

title = "Iris feature extraction using principally rotated complex wavelet filters (PR-CWF)",

abstract = "Deriving effective iris feature from the segmented iris image is a crucial step in iris recognition system. In this paper we propose a new iris feature extraction method based on the Principal Texture Pattern (PTP) and dual tree complex wavelet transform (DT-CWT). We compute the principal direction (PD) of the iris texture using principal component analysis (PCA) and obtain the angle θ of the PD. Then, complex wavelet filters CWFs are constructed and rotated in the direction θ of the PD and also in the opposite direction - θ for decomposition of the image into 12 sub-bands using DT-CWT. Rotational invariant and scale invariant features are obtained by combining LL and HL sub-bands at each level. Consequently, channel energies and standard deviations are constructed as feature representation of the iris while SVM is used for classification of iris images. Our experiments demonstrate the superiority of the proposed method on CASIA iris databases, over existing methods.",

keywords = "complex wavelet, discrete wavelet transform, Gabor filters, Iris recognition, principal component analysis",

author = "Ukpai, {Charles O.} and Dlay, {S. S.} and Woo, {W. L.}",

year = "2015",

month = dec,

day = "10",

doi = "10.1109/ICCVIA.2015.7351904",

language = "English",

isbn = "9781479971855",

booktitle = "Proceedings - International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015",

publisher = "IEEE",

address = "United States",

note = "International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015 ; Conference date: 18-01-2015 Through 20-01-2015",

}

Ukpai, CO, Dlay, SS & Woo, WL 2015, Iris feature extraction using principally rotated complex wavelet filters (PR-CWF). in Proceedings - International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015. IEEE, International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015, Sousse, Tunisia, 18/01/15. https://doi.org/10.1109/ICCVIA.2015.7351904

TY - GEN

T1 - Iris feature extraction using principally rotated complex wavelet filters (PR-CWF)

AU - Ukpai, Charles O.

AU - Dlay, S. S.

AU - Woo, W. L.

PY - 2015/12/10

Y1 - 2015/12/10

N2 - Deriving effective iris feature from the segmented iris image is a crucial step in iris recognition system. In this paper we propose a new iris feature extraction method based on the Principal Texture Pattern (PTP) and dual tree complex wavelet transform (DT-CWT). We compute the principal direction (PD) of the iris texture using principal component analysis (PCA) and obtain the angle θ of the PD. Then, complex wavelet filters CWFs are constructed and rotated in the direction θ of the PD and also in the opposite direction - θ for decomposition of the image into 12 sub-bands using DT-CWT. Rotational invariant and scale invariant features are obtained by combining LL and HL sub-bands at each level. Consequently, channel energies and standard deviations are constructed as feature representation of the iris while SVM is used for classification of iris images. Our experiments demonstrate the superiority of the proposed method on CASIA iris databases, over existing methods.

AB - Deriving effective iris feature from the segmented iris image is a crucial step in iris recognition system. In this paper we propose a new iris feature extraction method based on the Principal Texture Pattern (PTP) and dual tree complex wavelet transform (DT-CWT). We compute the principal direction (PD) of the iris texture using principal component analysis (PCA) and obtain the angle θ of the PD. Then, complex wavelet filters CWFs are constructed and rotated in the direction θ of the PD and also in the opposite direction - θ for decomposition of the image into 12 sub-bands using DT-CWT. Rotational invariant and scale invariant features are obtained by combining LL and HL sub-bands at each level. Consequently, channel energies and standard deviations are constructed as feature representation of the iris while SVM is used for classification of iris images. Our experiments demonstrate the superiority of the proposed method on CASIA iris databases, over existing methods.

KW - complex wavelet

KW - discrete wavelet transform

KW - Gabor filters

KW - Iris recognition

KW - principal component analysis

U2 - 10.1109/ICCVIA.2015.7351904

DO - 10.1109/ICCVIA.2015.7351904

M3 - Conference contribution

AN - SCOPUS:84963811372

SN - 9781479971855

BT - Proceedings - International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015

PB - IEEE

T2 - International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015

Y2 - 18 January 2015 through 20 January 2015

ER -

Iris feature extraction using principally rotated complex wavelet filters (PR-CWF)

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this