Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut

Abduljalil Radman, Nasharuddin Zainal, Shahrel Azmin Suandi

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Iris recognition systems have demonstrated considerable improvement in recognizing people through their iris patterns. Recent iris recognition systems have focused on images acquired in unconstrained environments. Unconstrained imaging environments allow the capture of iris images at a distance, in motion and under visible wavelength illumination which lead to more noise factors such as off-focus, gaze deviation, and obstruction by eyelids, eyeglasses, hair, lighting and specular reflections. Segmenting irises taken in an unconstrained environment remains a challenging task for iris recognition. In this paper, a new iris segmentation method is developed and tested on UBIRIS.v2 and MICHE iris databases that reflect the challenges in recognition by unconstrained images. This method accurately localizes the iris by a model designed on the basis of the Histograms of Oriented Gradients (HOG) descriptor and Support Vector Machine (SVM), namely HOG-SVM. Based on this localization, iris texture is automatically extracted by means of a cellular automata which evolved via the GrowCut technique. Pre- and post-processing operations are also introduced to ensure higher segmentation accuracy. Extensive experimental results illustrate the effectiveness of the proposed method on unconstrained iris images.

Original languageEnglish
Pages (from-to)60-70
Number of pages11
JournalDigital Signal Processing: A Review Journal
Volume64
DOIs
Publication statusPublished - 1 May 2017

Fingerprint

Support vector machines
Lighting
Eyeglasses
Cellular automata
Processing
Textures
Imaging techniques
Wavelength

Keywords

  • GrowCut
  • Histograms of Oriented Gradients (HOG)
  • Iris recognition
  • Iris segmentation
  • Support Vector Machine (SVM)

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut. / Radman, Abduljalil; Zainal, Nasharuddin; Suandi, Shahrel Azmin.

In: Digital Signal Processing: A Review Journal, Vol. 64, 01.05.2017, p. 60-70.

Research output: Contribution to journalArticle

@article{56fd9b08399045c3ae91eccd2fde42da,
title = "Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut",
abstract = "Iris recognition systems have demonstrated considerable improvement in recognizing people through their iris patterns. Recent iris recognition systems have focused on images acquired in unconstrained environments. Unconstrained imaging environments allow the capture of iris images at a distance, in motion and under visible wavelength illumination which lead to more noise factors such as off-focus, gaze deviation, and obstruction by eyelids, eyeglasses, hair, lighting and specular reflections. Segmenting irises taken in an unconstrained environment remains a challenging task for iris recognition. In this paper, a new iris segmentation method is developed and tested on UBIRIS.v2 and MICHE iris databases that reflect the challenges in recognition by unconstrained images. This method accurately localizes the iris by a model designed on the basis of the Histograms of Oriented Gradients (HOG) descriptor and Support Vector Machine (SVM), namely HOG-SVM. Based on this localization, iris texture is automatically extracted by means of a cellular automata which evolved via the GrowCut technique. Pre- and post-processing operations are also introduced to ensure higher segmentation accuracy. Extensive experimental results illustrate the effectiveness of the proposed method on unconstrained iris images.",
keywords = "GrowCut, Histograms of Oriented Gradients (HOG), Iris recognition, Iris segmentation, Support Vector Machine (SVM)",
author = "Abduljalil Radman and Nasharuddin Zainal and Suandi, {Shahrel Azmin}",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.dsp.2017.02.003",
language = "English",
volume = "64",
pages = "60--70",
journal = "Digital Signal Processing: A Review Journal",
issn = "1051-2004",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Automated segmentation of iris images acquired in an unconstrained environment using HOG-SVM and GrowCut

AU - Radman, Abduljalil

AU - Zainal, Nasharuddin

AU - Suandi, Shahrel Azmin

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Iris recognition systems have demonstrated considerable improvement in recognizing people through their iris patterns. Recent iris recognition systems have focused on images acquired in unconstrained environments. Unconstrained imaging environments allow the capture of iris images at a distance, in motion and under visible wavelength illumination which lead to more noise factors such as off-focus, gaze deviation, and obstruction by eyelids, eyeglasses, hair, lighting and specular reflections. Segmenting irises taken in an unconstrained environment remains a challenging task for iris recognition. In this paper, a new iris segmentation method is developed and tested on UBIRIS.v2 and MICHE iris databases that reflect the challenges in recognition by unconstrained images. This method accurately localizes the iris by a model designed on the basis of the Histograms of Oriented Gradients (HOG) descriptor and Support Vector Machine (SVM), namely HOG-SVM. Based on this localization, iris texture is automatically extracted by means of a cellular automata which evolved via the GrowCut technique. Pre- and post-processing operations are also introduced to ensure higher segmentation accuracy. Extensive experimental results illustrate the effectiveness of the proposed method on unconstrained iris images.

AB - Iris recognition systems have demonstrated considerable improvement in recognizing people through their iris patterns. Recent iris recognition systems have focused on images acquired in unconstrained environments. Unconstrained imaging environments allow the capture of iris images at a distance, in motion and under visible wavelength illumination which lead to more noise factors such as off-focus, gaze deviation, and obstruction by eyelids, eyeglasses, hair, lighting and specular reflections. Segmenting irises taken in an unconstrained environment remains a challenging task for iris recognition. In this paper, a new iris segmentation method is developed and tested on UBIRIS.v2 and MICHE iris databases that reflect the challenges in recognition by unconstrained images. This method accurately localizes the iris by a model designed on the basis of the Histograms of Oriented Gradients (HOG) descriptor and Support Vector Machine (SVM), namely HOG-SVM. Based on this localization, iris texture is automatically extracted by means of a cellular automata which evolved via the GrowCut technique. Pre- and post-processing operations are also introduced to ensure higher segmentation accuracy. Extensive experimental results illustrate the effectiveness of the proposed method on unconstrained iris images.

KW - GrowCut

KW - Histograms of Oriented Gradients (HOG)

KW - Iris recognition

KW - Iris segmentation

KW - Support Vector Machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=85013156551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013156551&partnerID=8YFLogxK

U2 - 10.1016/j.dsp.2017.02.003

DO - 10.1016/j.dsp.2017.02.003

M3 - Article

AN - SCOPUS:85013156551

VL - 64

SP - 60

EP - 70

JO - Digital Signal Processing: A Review Journal

JF - Digital Signal Processing: A Review Journal

SN - 1051-2004

ER -