摘要
针对复杂背景下的彩色图像,提出了一种基于肤色模型、数学形态学处理、似眼物检测以及眼睛与嘴巴构成三角形特征的人脸检测算法。该方法首先根据肤色模型检测出肤色区域;快速提取肤色区域的边界并分割成一系列肤色块;用数学形态学的膨胀和腐蚀方法分别对各个肤色块进行处理,消除边界毛刺和回旋,填补空洞,同时也避免了不同肤色块的连通;用简单的圆形模板检测出似眼物,然后根据眼睛与嘴巴构成三角形的特征判断是否为人脸。
This paper presents an algorithm for face detection, which integrates a skin color model, morphological processing, eye-analog detection and isosceles triangle detection. First, skin regions are detected based on a model of skin color; Second, they are further segmented into a series of skin blocks. Each block is morphologically processed in order to smooth out the biconvex and small backdate and to fill holes. At the same time we can avoid connectivity of different blocks can be avoided in this way; At last, ira block is a face block using the features of human eyes and the isosceles triangle formed by the eyes and the mouth is determined.
出处
《计算机工程》
CAS
CSCD
北大核心
2005年第17期149-151,共3页
Computer Engineering
基金
国家自然科学基金资助项目(60172022)
关键词
人脸检测
人脸定位
似眼物检测
形态膨胀和腐蚀
模板匹配
Face detection
Face location
Eye-analog detection
Morphological dilation and erosion
Template matching