Robust face recognition against soft-errors using a cross-layer approach

Gu Min Jeong, Chang Woo Park, Sang Il Choi, Kyoungwoo Lee, Nikil Dutt

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Recently, soft-errors, temporary bit toggles in memory systems, have become increasingly important. Although soft-errors are not critical to the stability of recognition systems or multimedia systems, they can significantly degrade the system performance. Considering these facts, in this paper, we propose a novel method for robust face recognition against soft-errors using a cross layer approach. To attenuate the effect of soft-errors in the face recognition system, they are detected in the embedded system layer by using a parity bit checker and compensated in the application layer by using a mean face. We present the soft-error detection module for face recognition and the compensation module based on the mean face of the facial images. Simulation results show that the proposed system effectively compensates for the performance degradation due to soft errors and improves the performance by 2.11 % in case of the Yale database and by 10.43 % in case of the ORL database on average as compared to that with the soft-errors induced.

Original languageEnglish
Pages (from-to)657-666
Number of pages10
JournalInternational Journal of Computers, Communications and Control
Volume11
Issue number5
DOIs
Publication statusPublished - 2016 Jan 1

Fingerprint

Face recognition
Multimedia systems
Error detection
Embedded systems
Data storage equipment
Degradation

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Networks and Communications
  • Computational Theory and Mathematics

Cite this

Jeong, Gu Min ; Park, Chang Woo ; Choi, Sang Il ; Lee, Kyoungwoo ; Dutt, Nikil. / Robust face recognition against soft-errors using a cross-layer approach. In: International Journal of Computers, Communications and Control. 2016 ; Vol. 11, No. 5. pp. 657-666.
@article{1036fd8d77444b8d9d5f04f2da5a8f1c,
title = "Robust face recognition against soft-errors using a cross-layer approach",
abstract = "Recently, soft-errors, temporary bit toggles in memory systems, have become increasingly important. Although soft-errors are not critical to the stability of recognition systems or multimedia systems, they can significantly degrade the system performance. Considering these facts, in this paper, we propose a novel method for robust face recognition against soft-errors using a cross layer approach. To attenuate the effect of soft-errors in the face recognition system, they are detected in the embedded system layer by using a parity bit checker and compensated in the application layer by using a mean face. We present the soft-error detection module for face recognition and the compensation module based on the mean face of the facial images. Simulation results show that the proposed system effectively compensates for the performance degradation due to soft errors and improves the performance by 2.11 {\%} in case of the Yale database and by 10.43 {\%} in case of the ORL database on average as compared to that with the soft-errors induced.",
author = "Jeong, {Gu Min} and Park, {Chang Woo} and Choi, {Sang Il} and Kyoungwoo Lee and Nikil Dutt",
year = "2016",
month = "1",
day = "1",
doi = "10.15837/ijccc.2016.5.2020",
language = "English",
volume = "11",
pages = "657--666",
journal = "International Journal of Computers, Communications and Control",
issn = "1841-9836",
publisher = "CCC Publications, R & D Agora",
number = "5",

}

Robust face recognition against soft-errors using a cross-layer approach. / Jeong, Gu Min; Park, Chang Woo; Choi, Sang Il; Lee, Kyoungwoo; Dutt, Nikil.

In: International Journal of Computers, Communications and Control, Vol. 11, No. 5, 01.01.2016, p. 657-666.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Robust face recognition against soft-errors using a cross-layer approach

AU - Jeong, Gu Min

AU - Park, Chang Woo

AU - Choi, Sang Il

AU - Lee, Kyoungwoo

AU - Dutt, Nikil

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Recently, soft-errors, temporary bit toggles in memory systems, have become increasingly important. Although soft-errors are not critical to the stability of recognition systems or multimedia systems, they can significantly degrade the system performance. Considering these facts, in this paper, we propose a novel method for robust face recognition against soft-errors using a cross layer approach. To attenuate the effect of soft-errors in the face recognition system, they are detected in the embedded system layer by using a parity bit checker and compensated in the application layer by using a mean face. We present the soft-error detection module for face recognition and the compensation module based on the mean face of the facial images. Simulation results show that the proposed system effectively compensates for the performance degradation due to soft errors and improves the performance by 2.11 % in case of the Yale database and by 10.43 % in case of the ORL database on average as compared to that with the soft-errors induced.

AB - Recently, soft-errors, temporary bit toggles in memory systems, have become increasingly important. Although soft-errors are not critical to the stability of recognition systems or multimedia systems, they can significantly degrade the system performance. Considering these facts, in this paper, we propose a novel method for robust face recognition against soft-errors using a cross layer approach. To attenuate the effect of soft-errors in the face recognition system, they are detected in the embedded system layer by using a parity bit checker and compensated in the application layer by using a mean face. We present the soft-error detection module for face recognition and the compensation module based on the mean face of the facial images. Simulation results show that the proposed system effectively compensates for the performance degradation due to soft errors and improves the performance by 2.11 % in case of the Yale database and by 10.43 % in case of the ORL database on average as compared to that with the soft-errors induced.

UR - http://www.scopus.com/inward/record.url?scp=84990990187&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84990990187&partnerID=8YFLogxK

U2 - 10.15837/ijccc.2016.5.2020

DO - 10.15837/ijccc.2016.5.2020

M3 - Article

AN - SCOPUS:84990990187

VL - 11

SP - 657

EP - 666

JO - International Journal of Computers, Communications and Control

JF - International Journal of Computers, Communications and Control

SN - 1841-9836

IS - 5

ER -