Do mixture models in chromaticity space improve skin detection?

被引：24

作者：

Caetano, TS

Olabariaga, SD

Barone, DAC

机构：

[1] Univ Fed Rio Grande do Sul, Inst Informat, BR-91501970 Porto Alegre, RS, Brazil

[2] Univ Utrecht, Ctr Med, Image Sci Inst, NL-3584 CX Utrecht, Netherlands

来源：

PATTERN RECOGNITION | 2003年 / 36卷 / 12期

关键词：

skin color model; skin color segmentation; skin detection; Gaussian mixture model; performance evaluation;

D O I：

10.1016/S0031-3203(03)00116-X

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This note reports an experiment where a single Gaussian model and several Gaussian mixture models were used to model skin color in the rg chromaticity space. By using training and test databases containing millions of skin pixels, we show that mixture models can improve skin detection, but not always. There is a relevant operating region where no performance gain is observed. (C) 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：3019 / 3021

页数：3

共 4 条

[1]

Caetano TS, 2001, 11TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, P279, DOI 10.1109/ICIAP.2001.957022

[2] Modelling facial colour and identity with Gaussian mixtures [J].

McKenna, SJ ;

Gong, SG ;

Raja, Y .

PATTERN RECOGNITION, 1998, 31 (12) :1883-1892

[3] A real-time face tracker [J].

Yang, J ;

Waibel, A .

THIRD IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV '96, PROCEEDINGS, 1996, :142-147

[4]

YANG MH, 2002, IEEE T PATTERN ANAL, V24, P236

← 1 →