Quantitative evaluation of depth of capture volume extension by constrained least-square-based image restoration

Ho Gi Jung, Kang Ryoung Park, Jaihie Kim

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Using quantitative evaluation, we show that constrained least-square (CLS)-based image restoration extends depth of capture volume (DCV) significantly, and suggest that performance degradation characteristics of a feature extractor by defocus blurring should be considered while developing unconstrained iris recognition systems. When developing an unconstrained iris recognition system (assuming a relatively cooperative user) the extension of the DCV clearly stands out as one of the most important problems. Although it has already been reported that CSL-based image restoration can improve recognition performance by mitigating the effect of defocus blurring, until now there have been no reports as to how much the DCV could be extended. This work inspects the Hamming distance (HD) distribution and error rate while changing the strength of defocus blurring with iris images of CASIA-IrisV3-Interval. It is derived that the ratio of the maximum blurring parameters satisfying a certain acceptable error rate is the ratio of the DCV. Using this fact, experimental results show that CLS-based image restoration extends the DCV by more than 70%. Additionally, it is observed that a log-Gabor filter is superior to a Gabor filter as the feature extractor. It should be noted that although these two feature extractors show a relatively small performance gap when a focused image set is used, the gap becomes significantly larger as the blurring becomes more severe. This is thought to suggest an important principle that performance characteristics should be considered with respect to defocus blurring when selecting or developing the feature extractor of an unconstrained iris recognition system.

Original languageEnglish
Article number047004
JournalOptical Engineering
Volume49
Issue number4
DOIs
Publication statusPublished - 2010 Dec 1

Fingerprint

blurring
Image reconstruction
restoration
Gabor filters
evaluation
Hamming distance
Degradation
degradation
intervals

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

@article{b3cd077386984632817fdfad0d3ceb58,
title = "Quantitative evaluation of depth of capture volume extension by constrained least-square-based image restoration",
abstract = "Using quantitative evaluation, we show that constrained least-square (CLS)-based image restoration extends depth of capture volume (DCV) significantly, and suggest that performance degradation characteristics of a feature extractor by defocus blurring should be considered while developing unconstrained iris recognition systems. When developing an unconstrained iris recognition system (assuming a relatively cooperative user) the extension of the DCV clearly stands out as one of the most important problems. Although it has already been reported that CSL-based image restoration can improve recognition performance by mitigating the effect of defocus blurring, until now there have been no reports as to how much the DCV could be extended. This work inspects the Hamming distance (HD) distribution and error rate while changing the strength of defocus blurring with iris images of CASIA-IrisV3-Interval. It is derived that the ratio of the maximum blurring parameters satisfying a certain acceptable error rate is the ratio of the DCV. Using this fact, experimental results show that CLS-based image restoration extends the DCV by more than 70{\%}. Additionally, it is observed that a log-Gabor filter is superior to a Gabor filter as the feature extractor. It should be noted that although these two feature extractors show a relatively small performance gap when a focused image set is used, the gap becomes significantly larger as the blurring becomes more severe. This is thought to suggest an important principle that performance characteristics should be considered with respect to defocus blurring when selecting or developing the feature extractor of an unconstrained iris recognition system.",
author = "Jung, {Ho Gi} and Park, {Kang Ryoung} and Jaihie Kim",
year = "2010",
month = "12",
day = "1",
doi = "10.1117/1.3378026",
language = "English",
volume = "49",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "4",

}

Quantitative evaluation of depth of capture volume extension by constrained least-square-based image restoration. / Jung, Ho Gi; Park, Kang Ryoung; Kim, Jaihie.

In: Optical Engineering, Vol. 49, No. 4, 047004, 01.12.2010.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Quantitative evaluation of depth of capture volume extension by constrained least-square-based image restoration

AU - Jung, Ho Gi

AU - Park, Kang Ryoung

AU - Kim, Jaihie

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Using quantitative evaluation, we show that constrained least-square (CLS)-based image restoration extends depth of capture volume (DCV) significantly, and suggest that performance degradation characteristics of a feature extractor by defocus blurring should be considered while developing unconstrained iris recognition systems. When developing an unconstrained iris recognition system (assuming a relatively cooperative user) the extension of the DCV clearly stands out as one of the most important problems. Although it has already been reported that CSL-based image restoration can improve recognition performance by mitigating the effect of defocus blurring, until now there have been no reports as to how much the DCV could be extended. This work inspects the Hamming distance (HD) distribution and error rate while changing the strength of defocus blurring with iris images of CASIA-IrisV3-Interval. It is derived that the ratio of the maximum blurring parameters satisfying a certain acceptable error rate is the ratio of the DCV. Using this fact, experimental results show that CLS-based image restoration extends the DCV by more than 70%. Additionally, it is observed that a log-Gabor filter is superior to a Gabor filter as the feature extractor. It should be noted that although these two feature extractors show a relatively small performance gap when a focused image set is used, the gap becomes significantly larger as the blurring becomes more severe. This is thought to suggest an important principle that performance characteristics should be considered with respect to defocus blurring when selecting or developing the feature extractor of an unconstrained iris recognition system.

AB - Using quantitative evaluation, we show that constrained least-square (CLS)-based image restoration extends depth of capture volume (DCV) significantly, and suggest that performance degradation characteristics of a feature extractor by defocus blurring should be considered while developing unconstrained iris recognition systems. When developing an unconstrained iris recognition system (assuming a relatively cooperative user) the extension of the DCV clearly stands out as one of the most important problems. Although it has already been reported that CSL-based image restoration can improve recognition performance by mitigating the effect of defocus blurring, until now there have been no reports as to how much the DCV could be extended. This work inspects the Hamming distance (HD) distribution and error rate while changing the strength of defocus blurring with iris images of CASIA-IrisV3-Interval. It is derived that the ratio of the maximum blurring parameters satisfying a certain acceptable error rate is the ratio of the DCV. Using this fact, experimental results show that CLS-based image restoration extends the DCV by more than 70%. Additionally, it is observed that a log-Gabor filter is superior to a Gabor filter as the feature extractor. It should be noted that although these two feature extractors show a relatively small performance gap when a focused image set is used, the gap becomes significantly larger as the blurring becomes more severe. This is thought to suggest an important principle that performance characteristics should be considered with respect to defocus blurring when selecting or developing the feature extractor of an unconstrained iris recognition system.

UR - http://www.scopus.com/inward/record.url?scp=81355153773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81355153773&partnerID=8YFLogxK

U2 - 10.1117/1.3378026

DO - 10.1117/1.3378026

M3 - Article

AN - SCOPUS:81355153773

VL - 49

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 4

M1 - 047004

ER -