A fast algorithm for tracking human faces based on chromatic histograms

被引：85

作者：

Yoo, TW

Oh, IS

机构：

[1] Chonbuk Natl Univ, Dept Comp Sci, Chonbuk 561756, South Korea

[2] Sohae Coll, Dept Off Automat, Chonbuk 573717, South Korea

来源：

PATTERN RECOGNITION LETTERS | 1999年 / 20卷 / 10期

关键词：

color motion image; real-time face tracking; chromatic histogram; histogram backprojection;

D O I：

10.1016/S0167-8655(99)00053-7

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

For the applications like video conferencing, real-time tracking of human faces is an essential task. In this paper, we propose a fast algorithm for tracking human face regions in color motion images. This algorithm is based on chromatic histogram and histogram backprojection operation. Our experimental results show that the proposed algorithm can be used in real-time applications. Additionally it has the advantage of being insensitive to small variations of face regions. (C) 1999 Elsevier Science B.V. All rights reserved.

引用

页码：967 / 978

页数：12

共 12 条

[1]

BLACK MJ, 1995, ICCV, P374

[2] Color texture segmentation for clothing in a computer-aided fashion design system [J].