Human face image coding using deformable templates, wavelet decomposition and VQ

Mustafa Sakalli; Hong Yan

doi:10.1109/TENCON.1997.648270

Human face image coding using deformable templates, wavelet decomposition and VQ

Mustafa Sakalli^*
, Hong Yan

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

A new model based compression scheme of face images is proposed as a combination of context-based and classic compression schemes. Deformable templates are employed to locate salient features of face images whose residuals are refined in a further residual vector quantization. Normalized face images are decomposed into subbands by using bi-orthogonal spline filters. Subbands and their first degree residuals are vector quantized sequentially in a pyramidal fashion. Wavelet coefficients are zonal truncated.

Original language	English
Title of host publication	IEEE TENCON '97 - Speech and Image Technologies for Computing and Telecommunications
Subtitle of host publication	Proceedings
Publisher	IEEE
Pages	569-572
Volume	2
ISBN (Print)	0-7803-4365-4
DOIs	https://doi.org/10.1109/TENCON.1997.648270
Publication status	Published - Dec 1997
Externally published	Yes
Event	1997 IEEE TENCON Conference (TENCON'97) - Brisbane, Australia Duration: 2 Dec 1997 → 4 Dec 1997

Conference

Conference	1997 IEEE TENCON Conference (TENCON'97)
Place	Australia
City	Brisbane
Period	2/12/97 → 4/12/97

Research Keywords

Face image coding
zonal truncation
deformable templates
based compression
wavelet decomposition
VQ
recognition

Access Output

10.1109/TENCON.1997.648270

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{c14c5cff2b844b0cacc50364bda18606,

title = "Human face image coding using deformable templates, wavelet decomposition and VQ",

abstract = "A new model based compression scheme of face images is proposed as a combination of context-based and classic compression schemes. Deformable templates are employed to locate salient features of face images whose residuals are refined in a further residual vector quantization. Normalized face images are decomposed into subbands by using bi-orthogonal spline filters. Subbands and their first degree residuals are vector quantized sequentially in a pyramidal fashion. Wavelet coefficients are zonal truncated.",

keywords = "Face image coding, zonal truncation, deformable templates, based compression, wavelet decomposition, VQ, recognition",

author = "Mustafa Sakalli and Hong Yan",

year = "1997",

month = dec,

doi = "10.1109/TENCON.1997.648270",

language = "English",

isbn = "0-7803-4365-4",

volume = "2",

pages = "569--572",

booktitle = "IEEE TENCON '97 - Speech and Image Technologies for Computing and Telecommunications",

publisher = "IEEE",

address = "United States",

note = "1997 IEEE TENCON Conference (TENCON'97) ; Conference date: 02-12-1997 Through 04-12-1997",

}

Human face image coding using deformable templates, wavelet decomposition and VQ. / Sakalli, Mustafa; Yan, Hong.
IEEE TENCON '97 - Speech and Image Technologies for Computing and Telecommunications: Proceedings. Vol. 2 IEEE, 1997. p. 569-572.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Human face image coding using deformable templates, wavelet decomposition and VQ

AU - Sakalli, Mustafa

AU - Yan, Hong

PY - 1997/12

Y1 - 1997/12

N2 - A new model based compression scheme of face images is proposed as a combination of context-based and classic compression schemes. Deformable templates are employed to locate salient features of face images whose residuals are refined in a further residual vector quantization. Normalized face images are decomposed into subbands by using bi-orthogonal spline filters. Subbands and their first degree residuals are vector quantized sequentially in a pyramidal fashion. Wavelet coefficients are zonal truncated.

AB - A new model based compression scheme of face images is proposed as a combination of context-based and classic compression schemes. Deformable templates are employed to locate salient features of face images whose residuals are refined in a further residual vector quantization. Normalized face images are decomposed into subbands by using bi-orthogonal spline filters. Subbands and their first degree residuals are vector quantized sequentially in a pyramidal fashion. Wavelet coefficients are zonal truncated.

KW - Face image coding

KW - zonal truncation

KW - deformable templates

KW - based compression

KW - wavelet decomposition

KW - VQ

KW - recognition

UR - https://www.scopus.com/pages/publications/0031368063

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0031368063&origin=recordpage

U2 - 10.1109/TENCON.1997.648270

DO - 10.1109/TENCON.1997.648270

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-7803-4365-4

VL - 2

SP - 569

EP - 572

BT - IEEE TENCON '97 - Speech and Image Technologies for Computing and Telecommunications

PB - IEEE

T2 - 1997 IEEE TENCON Conference (TENCON'97)

Y2 - 2 December 1997 through 4 December 1997

ER -

Human face image coding using deformable templates, wavelet decomposition and VQ

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this