Low-resolution face recognition in uses of multiple-size discrete cosine transforms and selective Gaussian mixture models

Shih Ming Huang, Yang Ting Chou, Jar-Ferr Yang

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Owing to losing the detailed information, the low-resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face-recognition system has been proposed, consisting of the extracted feature vectors from the multiple-size discrete cosine transforms (mDCTs) and the recognition mechanism with selective Gaussian mixture models (sGMMs). The mDCT could extract enough visual features from low-resolution face images while the sGMM could exclude unreliable observation features in recognition phase. Thus, the mDCT and the sGMM can greatly improve recognition rate at low-resolution conditions. Experiments are carried out on George Tech and AR facial databases in 16 × 16 and 12 × 12 pixels resolution. The results show that the proposed system achieves better performance than the existing methods for low-resolution face recognition.

Original languageEnglish
Pages (from-to)382-390
Number of pages9
JournalIET Computer Vision
Volume8
Issue number5
DOIs
Publication statusPublished - 2014 Oct 1

Fingerprint

Discrete cosine transforms
Face recognition
Pixels
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{68f6bdc4effd4ab5a1ffeb9da3bc2769,
title = "Low-resolution face recognition in uses of multiple-size discrete cosine transforms and selective Gaussian mixture models",
abstract = "Owing to losing the detailed information, the low-resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face-recognition system has been proposed, consisting of the extracted feature vectors from the multiple-size discrete cosine transforms (mDCTs) and the recognition mechanism with selective Gaussian mixture models (sGMMs). The mDCT could extract enough visual features from low-resolution face images while the sGMM could exclude unreliable observation features in recognition phase. Thus, the mDCT and the sGMM can greatly improve recognition rate at low-resolution conditions. Experiments are carried out on George Tech and AR facial databases in 16 × 16 and 12 × 12 pixels resolution. The results show that the proposed system achieves better performance than the existing methods for low-resolution face recognition.",
author = "Huang, {Shih Ming} and Chou, {Yang Ting} and Jar-Ferr Yang",
year = "2014",
month = "10",
day = "1",
doi = "10.1049/iet-cvi.2012.0211",
language = "English",
volume = "8",
pages = "382--390",
journal = "IET Computer Vision",
issn = "1751-9632",
publisher = "Institution of Engineering and Technology",
number = "5",

}

Low-resolution face recognition in uses of multiple-size discrete cosine transforms and selective Gaussian mixture models. / Huang, Shih Ming; Chou, Yang Ting; Yang, Jar-Ferr.

In: IET Computer Vision, Vol. 8, No. 5, 01.10.2014, p. 382-390.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Low-resolution face recognition in uses of multiple-size discrete cosine transforms and selective Gaussian mixture models

AU - Huang, Shih Ming

AU - Chou, Yang Ting

AU - Yang, Jar-Ferr

PY - 2014/10/1

Y1 - 2014/10/1

N2 - Owing to losing the detailed information, the low-resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face-recognition system has been proposed, consisting of the extracted feature vectors from the multiple-size discrete cosine transforms (mDCTs) and the recognition mechanism with selective Gaussian mixture models (sGMMs). The mDCT could extract enough visual features from low-resolution face images while the sGMM could exclude unreliable observation features in recognition phase. Thus, the mDCT and the sGMM can greatly improve recognition rate at low-resolution conditions. Experiments are carried out on George Tech and AR facial databases in 16 × 16 and 12 × 12 pixels resolution. The results show that the proposed system achieves better performance than the existing methods for low-resolution face recognition.

AB - Owing to losing the detailed information, the low-resolution problem in face recognition degrades the recognition performance dramatically. To overcome this problem, a novel face-recognition system has been proposed, consisting of the extracted feature vectors from the multiple-size discrete cosine transforms (mDCTs) and the recognition mechanism with selective Gaussian mixture models (sGMMs). The mDCT could extract enough visual features from low-resolution face images while the sGMM could exclude unreliable observation features in recognition phase. Thus, the mDCT and the sGMM can greatly improve recognition rate at low-resolution conditions. Experiments are carried out on George Tech and AR facial databases in 16 × 16 and 12 × 12 pixels resolution. The results show that the proposed system achieves better performance than the existing methods for low-resolution face recognition.

UR - http://www.scopus.com/inward/record.url?scp=84907160769&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907160769&partnerID=8YFLogxK

U2 - 10.1049/iet-cvi.2012.0211

DO - 10.1049/iet-cvi.2012.0211

M3 - Article

VL - 8

SP - 382

EP - 390

JO - IET Computer Vision

JF - IET Computer Vision

SN - 1751-9632

IS - 5

ER -