Compression of personal identification pictures using vector quantization with facial feature correction

Jian Hong Hu, Ru Shang Wang, Yao Wang

Research output: Contribution to journalArticle

Abstract

This paper describes a feature-correction two-stage vector quantization (FC2VQ) algorithm for the compression of photo ID pictures. The FC2VQ method treats different regions in a facial image differently. A region of facial features (ROFF), containing the eyes and the mouth, is detected and rendered more accurately than the rest of the image. The technique can compress a 128 ×128×8-bit (16,384 bytes total) ID image to an average size of 350 bytes. The quality of the compressed images is far superior to that obtained by other methods, including the JPEG standard, at similar compression ratios.

Original languageEnglish (US)
Pages (from-to)198-203
Number of pages6
JournalOptical Engineering
Volume35
Issue number1
StatePublished - Jan 1996

Fingerprint

vector quantization
Vector quantization
compression ratio
mouth

Keywords

  • Facial feature detection
  • Facial image compression
  • Vector quantization
  • Visual communications and image processing

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics

Cite this

Compression of personal identification pictures using vector quantization with facial feature correction. / Hu, Jian Hong; Wang, Ru Shang; Wang, Yao.

In: Optical Engineering, Vol. 35, No. 1, 01.1996, p. 198-203.

Research output: Contribution to journalArticle

@article{86a279f6636249678f81acae039614ef,
title = "Compression of personal identification pictures using vector quantization with facial feature correction",
abstract = "This paper describes a feature-correction two-stage vector quantization (FC2VQ) algorithm for the compression of photo ID pictures. The FC2VQ method treats different regions in a facial image differently. A region of facial features (ROFF), containing the eyes and the mouth, is detected and rendered more accurately than the rest of the image. The technique can compress a 128 ×128×8-bit (16,384 bytes total) ID image to an average size of 350 bytes. The quality of the compressed images is far superior to that obtained by other methods, including the JPEG standard, at similar compression ratios.",
keywords = "Facial feature detection, Facial image compression, Vector quantization, Visual communications and image processing",
author = "Hu, {Jian Hong} and Wang, {Ru Shang} and Yao Wang",
year = "1996",
month = "1",
language = "English (US)",
volume = "35",
pages = "198--203",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "1",

}

TY - JOUR

T1 - Compression of personal identification pictures using vector quantization with facial feature correction

AU - Hu, Jian Hong

AU - Wang, Ru Shang

AU - Wang, Yao

PY - 1996/1

Y1 - 1996/1

N2 - This paper describes a feature-correction two-stage vector quantization (FC2VQ) algorithm for the compression of photo ID pictures. The FC2VQ method treats different regions in a facial image differently. A region of facial features (ROFF), containing the eyes and the mouth, is detected and rendered more accurately than the rest of the image. The technique can compress a 128 ×128×8-bit (16,384 bytes total) ID image to an average size of 350 bytes. The quality of the compressed images is far superior to that obtained by other methods, including the JPEG standard, at similar compression ratios.

AB - This paper describes a feature-correction two-stage vector quantization (FC2VQ) algorithm for the compression of photo ID pictures. The FC2VQ method treats different regions in a facial image differently. A region of facial features (ROFF), containing the eyes and the mouth, is detected and rendered more accurately than the rest of the image. The technique can compress a 128 ×128×8-bit (16,384 bytes total) ID image to an average size of 350 bytes. The quality of the compressed images is far superior to that obtained by other methods, including the JPEG standard, at similar compression ratios.

KW - Facial feature detection

KW - Facial image compression

KW - Vector quantization

KW - Visual communications and image processing

UR - http://www.scopus.com/inward/record.url?scp=0009664856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0009664856&partnerID=8YFLogxK

M3 - Article

VL - 35

SP - 198

EP - 203

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 1

ER -