Share Email Print

Optical Engineering

Feature-based compression of human face images
Author(s): Mustafa Sakalli; Hong Yan
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

A method is developed for feature-based coding of human face images. Deformable templates, wavelet decomposition, and residual vector quantization (RVQ) form three consecutive stages of the proposed method, which aims for recognition-based very low bit rate coding. Deformable templates are employed in localization of facial features and biorthogonal spline filters are used for the decomposition of segmented and normalized face images. Wavelet coefficients are zonal truncated before being vector quantized to generate multiresolution codebooks. Classified multiresolution codebooks are also generated for residual eye and mouth images to improve subjective quality of salient face features.

Paper Details

Date Published: 1 May 1998
PDF: 10 pages
Opt. Eng. 37(5) doi: 10.1117/1.601667
Published in: Optical Engineering Volume 37, Issue 5
Show Author Affiliations
Mustafa Sakalli, Univ. of Sydney (Australia)
Hong Yan, Univ. of Sydney (Hong Kong)

© SPIE. Terms of Use
Back to Top