Authenticating corrupted photo images based on noise parameter estimation

Sang Woong Lee, Ho Cheol Jung, Bon Woo Hwang, Seong Whan Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Photo image authentication is an interesting and demanding field in the computer vision and image processing community. This research is motivated by its wide range of applications, which include smart card authentication systems, biometric passport systems, etc. In this paper, we propose a method of authenticating corrupted photo images based on noise parameter estimation. The proposed method first generates corrupted images by adjusting the noise parameters in the initial training phase. This set of corrupted images and the noise parameters can be represented by a linear combination of the prototypes of the corrupted images and the noise parameters. In the testing phase, the noise parameters of the corrupted photo image can be estimated with a corrupted image and an original image. Finally, we can make a synthesized photo image from the original photo image using the estimated noise parameters and verify it with the corrupted photo image. The experimental results show that the proposed method can estimate the noise parameters accurately and improve the performance of photo image authentication.

Original languageEnglish
Pages (from-to)910-920
Number of pages11
JournalPattern Recognition
Volume39
Issue number5
DOIs
Publication statusPublished - 2006 May 1

Fingerprint

Parameter estimation
Authentication
Smart cards
Biometrics
Computer vision
Image processing
Testing

Keywords

  • Corrupted photo image
  • Noise model
  • Noise parameter estimation
  • Photo image authentication

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Authenticating corrupted photo images based on noise parameter estimation. / Lee, Sang Woong; Jung, Ho Cheol; Hwang, Bon Woo; Lee, Seong Whan.

In: Pattern Recognition, Vol. 39, No. 5, 01.05.2006, p. 910-920.

Research output: Contribution to journalArticle

Lee, Sang Woong ; Jung, Ho Cheol ; Hwang, Bon Woo ; Lee, Seong Whan. / Authenticating corrupted photo images based on noise parameter estimation. In: Pattern Recognition. 2006 ; Vol. 39, No. 5. pp. 910-920.
@article{2b68d850b3c5412aa47200783cc9284d,
title = "Authenticating corrupted photo images based on noise parameter estimation",
abstract = "Photo image authentication is an interesting and demanding field in the computer vision and image processing community. This research is motivated by its wide range of applications, which include smart card authentication systems, biometric passport systems, etc. In this paper, we propose a method of authenticating corrupted photo images based on noise parameter estimation. The proposed method first generates corrupted images by adjusting the noise parameters in the initial training phase. This set of corrupted images and the noise parameters can be represented by a linear combination of the prototypes of the corrupted images and the noise parameters. In the testing phase, the noise parameters of the corrupted photo image can be estimated with a corrupted image and an original image. Finally, we can make a synthesized photo image from the original photo image using the estimated noise parameters and verify it with the corrupted photo image. The experimental results show that the proposed method can estimate the noise parameters accurately and improve the performance of photo image authentication.",
keywords = "Corrupted photo image, Noise model, Noise parameter estimation, Photo image authentication",
author = "Lee, {Sang Woong} and Jung, {Ho Cheol} and Hwang, {Bon Woo} and Lee, {Seong Whan}",
year = "2006",
month = "5",
day = "1",
doi = "10.1016/j.patcog.2005.09.017",
language = "English",
volume = "39",
pages = "910--920",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Authenticating corrupted photo images based on noise parameter estimation

AU - Lee, Sang Woong

AU - Jung, Ho Cheol

AU - Hwang, Bon Woo

AU - Lee, Seong Whan

PY - 2006/5/1

Y1 - 2006/5/1

N2 - Photo image authentication is an interesting and demanding field in the computer vision and image processing community. This research is motivated by its wide range of applications, which include smart card authentication systems, biometric passport systems, etc. In this paper, we propose a method of authenticating corrupted photo images based on noise parameter estimation. The proposed method first generates corrupted images by adjusting the noise parameters in the initial training phase. This set of corrupted images and the noise parameters can be represented by a linear combination of the prototypes of the corrupted images and the noise parameters. In the testing phase, the noise parameters of the corrupted photo image can be estimated with a corrupted image and an original image. Finally, we can make a synthesized photo image from the original photo image using the estimated noise parameters and verify it with the corrupted photo image. The experimental results show that the proposed method can estimate the noise parameters accurately and improve the performance of photo image authentication.

AB - Photo image authentication is an interesting and demanding field in the computer vision and image processing community. This research is motivated by its wide range of applications, which include smart card authentication systems, biometric passport systems, etc. In this paper, we propose a method of authenticating corrupted photo images based on noise parameter estimation. The proposed method first generates corrupted images by adjusting the noise parameters in the initial training phase. This set of corrupted images and the noise parameters can be represented by a linear combination of the prototypes of the corrupted images and the noise parameters. In the testing phase, the noise parameters of the corrupted photo image can be estimated with a corrupted image and an original image. Finally, we can make a synthesized photo image from the original photo image using the estimated noise parameters and verify it with the corrupted photo image. The experimental results show that the proposed method can estimate the noise parameters accurately and improve the performance of photo image authentication.

KW - Corrupted photo image

KW - Noise model

KW - Noise parameter estimation

KW - Photo image authentication

UR - http://www.scopus.com/inward/record.url?scp=33244462398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33244462398&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2005.09.017

DO - 10.1016/j.patcog.2005.09.017

M3 - Article

AN - SCOPUS:33244462398

VL - 39

SP - 910

EP - 920

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 5

ER -