A new iris segmentation method for non-ideal iris images

Dae Sik Jeong, Jae Won Hwang, Byung Jun Kang, Kang Ryoung Park, Chee Sun Won, Dong Kwon Park, Jaihie Kim

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Many researchers have studied iris recognition techniques in unconstrained environments, where the probability of acquiring non-ideal iris images is very high due to off-angles, noise, blurring and occlusion by eyelashes, eyelids, glasses, and hair. Although there have been many iris segmentation methods, most focus primarily on the accurate detection with iris images which are captured in a closely controlled environment. This paper proposes a new iris segmentation method that can be used to accurately extract iris regions from non-ideal quality iris images. This research has following three novelties compared to previous works; firstly, the proposed method uses AdaBoost eye detection in order to compensate for the iris detection error caused by the two circular edge detection operations; secondly, it uses a color segmentation technique for detecting obstructions by the ghosting effects of visible light; and thirdly, if there is no extracted corneal specular reflection in the detected pupil and iris regions, the captured iris image is determined as a "closed eye" image. The proposed method has been tested using the UBIRIS.v2 database via NICE.I (Noisy Iris Challenge Evaluation - Part I) contest. The results show that FP (False Positive) error rate and FN (False Negative) error rate are 1.2% and 27.6%, respectively, from NICE.I report (the 5th highest rank).

Original languageEnglish
Pages (from-to)254-260
Number of pages7
JournalImage and Vision Computing
Volume28
Issue number2
DOIs
Publication statusPublished - 2010 Jan 1

Fingerprint

Adaptive boosting
Error detection
Edge detection
Image quality
Color
Glass

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Jeong, D. S., Hwang, J. W., Kang, B. J., Park, K. R., Won, C. S., Park, D. K., & Kim, J. (2010). A new iris segmentation method for non-ideal iris images. Image and Vision Computing, 28(2), 254-260. https://doi.org/10.1016/j.imavis.2009.04.001
Jeong, Dae Sik ; Hwang, Jae Won ; Kang, Byung Jun ; Park, Kang Ryoung ; Won, Chee Sun ; Park, Dong Kwon ; Kim, Jaihie. / A new iris segmentation method for non-ideal iris images. In: Image and Vision Computing. 2010 ; Vol. 28, No. 2. pp. 254-260.
@article{0fe3cee87693498e90192d1eb50d32e7,
title = "A new iris segmentation method for non-ideal iris images",
abstract = "Many researchers have studied iris recognition techniques in unconstrained environments, where the probability of acquiring non-ideal iris images is very high due to off-angles, noise, blurring and occlusion by eyelashes, eyelids, glasses, and hair. Although there have been many iris segmentation methods, most focus primarily on the accurate detection with iris images which are captured in a closely controlled environment. This paper proposes a new iris segmentation method that can be used to accurately extract iris regions from non-ideal quality iris images. This research has following three novelties compared to previous works; firstly, the proposed method uses AdaBoost eye detection in order to compensate for the iris detection error caused by the two circular edge detection operations; secondly, it uses a color segmentation technique for detecting obstructions by the ghosting effects of visible light; and thirdly, if there is no extracted corneal specular reflection in the detected pupil and iris regions, the captured iris image is determined as a {"}closed eye{"} image. The proposed method has been tested using the UBIRIS.v2 database via NICE.I (Noisy Iris Challenge Evaluation - Part I) contest. The results show that FP (False Positive) error rate and FN (False Negative) error rate are 1.2{\%} and 27.6{\%}, respectively, from NICE.I report (the 5th highest rank).",
author = "Jeong, {Dae Sik} and Hwang, {Jae Won} and Kang, {Byung Jun} and Park, {Kang Ryoung} and Won, {Chee Sun} and Park, {Dong Kwon} and Jaihie Kim",
year = "2010",
month = "1",
day = "1",
doi = "10.1016/j.imavis.2009.04.001",
language = "English",
volume = "28",
pages = "254--260",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",
number = "2",

}

Jeong, DS, Hwang, JW, Kang, BJ, Park, KR, Won, CS, Park, DK & Kim, J 2010, 'A new iris segmentation method for non-ideal iris images', Image and Vision Computing, vol. 28, no. 2, pp. 254-260. https://doi.org/10.1016/j.imavis.2009.04.001

A new iris segmentation method for non-ideal iris images. / Jeong, Dae Sik; Hwang, Jae Won; Kang, Byung Jun; Park, Kang Ryoung; Won, Chee Sun; Park, Dong Kwon; Kim, Jaihie.

In: Image and Vision Computing, Vol. 28, No. 2, 01.01.2010, p. 254-260.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new iris segmentation method for non-ideal iris images

AU - Jeong, Dae Sik

AU - Hwang, Jae Won

AU - Kang, Byung Jun

AU - Park, Kang Ryoung

AU - Won, Chee Sun

AU - Park, Dong Kwon

AU - Kim, Jaihie

PY - 2010/1/1

Y1 - 2010/1/1

N2 - Many researchers have studied iris recognition techniques in unconstrained environments, where the probability of acquiring non-ideal iris images is very high due to off-angles, noise, blurring and occlusion by eyelashes, eyelids, glasses, and hair. Although there have been many iris segmentation methods, most focus primarily on the accurate detection with iris images which are captured in a closely controlled environment. This paper proposes a new iris segmentation method that can be used to accurately extract iris regions from non-ideal quality iris images. This research has following three novelties compared to previous works; firstly, the proposed method uses AdaBoost eye detection in order to compensate for the iris detection error caused by the two circular edge detection operations; secondly, it uses a color segmentation technique for detecting obstructions by the ghosting effects of visible light; and thirdly, if there is no extracted corneal specular reflection in the detected pupil and iris regions, the captured iris image is determined as a "closed eye" image. The proposed method has been tested using the UBIRIS.v2 database via NICE.I (Noisy Iris Challenge Evaluation - Part I) contest. The results show that FP (False Positive) error rate and FN (False Negative) error rate are 1.2% and 27.6%, respectively, from NICE.I report (the 5th highest rank).

AB - Many researchers have studied iris recognition techniques in unconstrained environments, where the probability of acquiring non-ideal iris images is very high due to off-angles, noise, blurring and occlusion by eyelashes, eyelids, glasses, and hair. Although there have been many iris segmentation methods, most focus primarily on the accurate detection with iris images which are captured in a closely controlled environment. This paper proposes a new iris segmentation method that can be used to accurately extract iris regions from non-ideal quality iris images. This research has following three novelties compared to previous works; firstly, the proposed method uses AdaBoost eye detection in order to compensate for the iris detection error caused by the two circular edge detection operations; secondly, it uses a color segmentation technique for detecting obstructions by the ghosting effects of visible light; and thirdly, if there is no extracted corneal specular reflection in the detected pupil and iris regions, the captured iris image is determined as a "closed eye" image. The proposed method has been tested using the UBIRIS.v2 database via NICE.I (Noisy Iris Challenge Evaluation - Part I) contest. The results show that FP (False Positive) error rate and FN (False Negative) error rate are 1.2% and 27.6%, respectively, from NICE.I report (the 5th highest rank).

UR - http://www.scopus.com/inward/record.url?scp=70449640414&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449640414&partnerID=8YFLogxK

U2 - 10.1016/j.imavis.2009.04.001

DO - 10.1016/j.imavis.2009.04.001

M3 - Article

AN - SCOPUS:70449640414

VL - 28

SP - 254

EP - 260

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 2

ER -

Jeong DS, Hwang JW, Kang BJ, Park KR, Won CS, Park DK et al. A new iris segmentation method for non-ideal iris images. Image and Vision Computing. 2010 Jan 1;28(2):254-260. https://doi.org/10.1016/j.imavis.2009.04.001