An embedded face verification system against image degradation

Sang Woong Lee, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose an embedded face verification system against image degradation using a TMS320C6711 DSP chip. Our proposed system has several advantages over general systems in terms of price, size and applicability. As well as physical merits, it has an efficient approach for degraded facial images based on noise parameter estimation under real-life environments. The proposed method linearly combines image vector and noise parameters into one vector for training. When estimating noise parameters, we calculate the optimal coefficients of linear decomposition of an input image vector only. The noise parameters can be obtained from the linear composition step using these optimal coefficients. In contrast to conventional methods, we add the estimated noises to original images instead of removing them. Finally we perform a verification step with the input and synthesized image. The experimental results of this system show that the proposed method can estimate noise parameters accurately while improving the performance of photo image verification.

Original languageEnglish
Title of host publicationConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Pages3571-3576
Number of pages6
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 - Montreal, QC, Canada
Duration: 2007 Oct 72007 Oct 10

Other

Other2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
CountryCanada
CityMontreal, QC
Period07/10/707/10/10

Fingerprint

Degradation
Digital signal processors
Parameter estimation
Decomposition
Chemical analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Lee, S. W., & Lee, S. W. (2007). An embedded face verification system against image degradation. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics (pp. 3571-3576). [4413904] https://doi.org/10.1109/ICSMC.2007.4413904

An embedded face verification system against image degradation. / Lee, Sang Woong; Lee, Seong Whan.

Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2007. p. 3571-3576 4413904.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, SW & Lee, SW 2007, An embedded face verification system against image degradation. in Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics., 4413904, pp. 3571-3576, 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007, Montreal, QC, Canada, 07/10/7. https://doi.org/10.1109/ICSMC.2007.4413904
Lee SW, Lee SW. An embedded face verification system against image degradation. In Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2007. p. 3571-3576. 4413904 https://doi.org/10.1109/ICSMC.2007.4413904
Lee, Sang Woong ; Lee, Seong Whan. / An embedded face verification system against image degradation. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics. 2007. pp. 3571-3576
@inproceedings{763b5b1f7ebc40edbfb2e89fe6c84f0c,
title = "An embedded face verification system against image degradation",
abstract = "In this paper, we propose an embedded face verification system against image degradation using a TMS320C6711 DSP chip. Our proposed system has several advantages over general systems in terms of price, size and applicability. As well as physical merits, it has an efficient approach for degraded facial images based on noise parameter estimation under real-life environments. The proposed method linearly combines image vector and noise parameters into one vector for training. When estimating noise parameters, we calculate the optimal coefficients of linear decomposition of an input image vector only. The noise parameters can be obtained from the linear composition step using these optimal coefficients. In contrast to conventional methods, we add the estimated noises to original images instead of removing them. Finally we perform a verification step with the input and synthesized image. The experimental results of this system show that the proposed method can estimate noise parameters accurately while improving the performance of photo image verification.",
author = "Lee, {Sang Woong} and Lee, {Seong Whan}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICSMC.2007.4413904",
language = "English",
isbn = "1424409918",
pages = "3571--3576",
booktitle = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

}

TY - GEN

T1 - An embedded face verification system against image degradation

AU - Lee, Sang Woong

AU - Lee, Seong Whan

PY - 2007/12/1

Y1 - 2007/12/1

N2 - In this paper, we propose an embedded face verification system against image degradation using a TMS320C6711 DSP chip. Our proposed system has several advantages over general systems in terms of price, size and applicability. As well as physical merits, it has an efficient approach for degraded facial images based on noise parameter estimation under real-life environments. The proposed method linearly combines image vector and noise parameters into one vector for training. When estimating noise parameters, we calculate the optimal coefficients of linear decomposition of an input image vector only. The noise parameters can be obtained from the linear composition step using these optimal coefficients. In contrast to conventional methods, we add the estimated noises to original images instead of removing them. Finally we perform a verification step with the input and synthesized image. The experimental results of this system show that the proposed method can estimate noise parameters accurately while improving the performance of photo image verification.

AB - In this paper, we propose an embedded face verification system against image degradation using a TMS320C6711 DSP chip. Our proposed system has several advantages over general systems in terms of price, size and applicability. As well as physical merits, it has an efficient approach for degraded facial images based on noise parameter estimation under real-life environments. The proposed method linearly combines image vector and noise parameters into one vector for training. When estimating noise parameters, we calculate the optimal coefficients of linear decomposition of an input image vector only. The noise parameters can be obtained from the linear composition step using these optimal coefficients. In contrast to conventional methods, we add the estimated noises to original images instead of removing them. Finally we perform a verification step with the input and synthesized image. The experimental results of this system show that the proposed method can estimate noise parameters accurately while improving the performance of photo image verification.

UR - http://www.scopus.com/inward/record.url?scp=40949117981&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40949117981&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2007.4413904

DO - 10.1109/ICSMC.2007.4413904

M3 - Conference contribution

AN - SCOPUS:40949117981

SN - 1424409918

SN - 9781424409914

SP - 3571

EP - 3576

BT - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

ER -