Fast and accurate method for complete iris segmentation with active contour and morphology

Mohammed A.M. Abdullah; S. S. Dlay; W. L. Woo

doi:10.1109/IST.2014.6958458

Fast and accurate method for complete iris segmentation with active contour and morphology

Mohammed A.M. Abdullah, S. S. Dlay, W. L. Woo

Computer Information Sciences Department

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

13 Citations (Scopus)

Abstract

The performance of iris recognition systems is significantly affected by the segmentation accuracy, especially in non-ideal iris images. This paper proposes a fast and accurate method for segmenting the iris using a combination of morphological operations and Chan-Vese active contour model. The morphological operations are used to determine a rough boundary of the iris region while the active contour is used to find the precise boundary. The proposed scheme is robust in finding the exact iris boundary and isolating the eyelids and the eyelashes of the iris images. Experimental results on the CASIA version 4.0 iris database have indicated a high level of accuracy using the proposed technique.

Original language	English
Title of host publication	IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings
Publisher	IEEE
Pages	123-128
Number of pages	6
ISBN (Electronic)	978-1-4799-5220-5
DOIs	https://doi.org/10.1109/IST.2014.6958458
Publication status	Published - 20 Nov 2014
Event	2014 IEEE International Conference on Imaging Systems and Techniques, IST 2014 - Santorini Island, Greece Duration: 14 Oct 2014 → 17 Oct 2014

Conference

Conference	2014 IEEE International Conference on Imaging Systems and Techniques, IST 2014
Country/Territory	Greece
City	Santorini Island
Period	14/10/14 → 17/10/14

Keywords

active contour
biometrics identification
image segmentation
iris recognition
morphological operations

Access to Document

10.1109/IST.2014.6958458

Cite this

@inproceedings{9af067625773446988d2ae14b8f0a0f5,

title = "Fast and accurate method for complete iris segmentation with active contour and morphology",

abstract = "The performance of iris recognition systems is significantly affected by the segmentation accuracy, especially in non-ideal iris images. This paper proposes a fast and accurate method for segmenting the iris using a combination of morphological operations and Chan-Vese active contour model. The morphological operations are used to determine a rough boundary of the iris region while the active contour is used to find the precise boundary. The proposed scheme is robust in finding the exact iris boundary and isolating the eyelids and the eyelashes of the iris images. Experimental results on the CASIA version 4.0 iris database have indicated a high level of accuracy using the proposed technique.",

keywords = "active contour, biometrics identification, image segmentation, iris recognition, morphological operations",

author = "Abdullah, {Mohammed A.M.} and Dlay, {S. S.} and Woo, {W. L.}",

year = "2014",

month = nov,

day = "20",

doi = "10.1109/IST.2014.6958458",

language = "English",

pages = "123--128",

booktitle = "IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings",

publisher = "IEEE",

address = "United States",

note = "2014 IEEE International Conference on Imaging Systems and Techniques, IST 2014 ; Conference date: 14-10-2014 Through 17-10-2014",

}

Abdullah, MAM, Dlay, SS & Woo, WL 2014, Fast and accurate method for complete iris segmentation with active contour and morphology. in IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings. IEEE, pp. 123-128, 2014 IEEE International Conference on Imaging Systems and Techniques, IST 2014, Santorini Island, Greece, 14/10/14. https://doi.org/10.1109/IST.2014.6958458

TY - GEN

T1 - Fast and accurate method for complete iris segmentation with active contour and morphology

AU - Abdullah, Mohammed A.M.

AU - Dlay, S. S.

AU - Woo, W. L.

PY - 2014/11/20

Y1 - 2014/11/20

N2 - The performance of iris recognition systems is significantly affected by the segmentation accuracy, especially in non-ideal iris images. This paper proposes a fast and accurate method for segmenting the iris using a combination of morphological operations and Chan-Vese active contour model. The morphological operations are used to determine a rough boundary of the iris region while the active contour is used to find the precise boundary. The proposed scheme is robust in finding the exact iris boundary and isolating the eyelids and the eyelashes of the iris images. Experimental results on the CASIA version 4.0 iris database have indicated a high level of accuracy using the proposed technique.

AB - The performance of iris recognition systems is significantly affected by the segmentation accuracy, especially in non-ideal iris images. This paper proposes a fast and accurate method for segmenting the iris using a combination of morphological operations and Chan-Vese active contour model. The morphological operations are used to determine a rough boundary of the iris region while the active contour is used to find the precise boundary. The proposed scheme is robust in finding the exact iris boundary and isolating the eyelids and the eyelashes of the iris images. Experimental results on the CASIA version 4.0 iris database have indicated a high level of accuracy using the proposed technique.

KW - active contour

KW - biometrics identification

KW - image segmentation

KW - iris recognition

KW - morphological operations

U2 - 10.1109/IST.2014.6958458

DO - 10.1109/IST.2014.6958458

M3 - Conference contribution

AN - SCOPUS:84916603340

SP - 123

EP - 128

BT - IST 2014 - 2014 IEEE International Conference on Imaging Systems and Techniques, Proceedings

PB - IEEE

T2 - 2014 IEEE International Conference on Imaging Systems and Techniques, IST 2014

Y2 - 14 October 2014 through 17 October 2014

ER -

Fast and accurate method for complete iris segmentation with active contour and morphology

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this