一种热红外人脸分割的新方法  

A New Method of Thermal Infrared Face Segmentation

作　　者：孙统风[1,2] 任子晖[1] 陈伟[2] 杨小冬[2] 

机构地区：[1]中国矿业大学信电学院,江苏徐州221116 [2]中国矿业大学计算机学院,江苏徐州221116

出　　处：《电子学报》2010年第B02期23-25,共3页Acta Electronica Sinica

基　　金：江苏省自然科学基金(No.BK2009093);国家“863”高技术项目(No.2006AA01Z128);中国矿业大学科技基金(No.2007A047)

摘　　要：针对热红外人脸的边缘和细节特征模糊、对比度低、人脸和背景温度分布不同等特点，提出一种新的图像分割方法.该方法使用灰度投影粗定位人脸，使用模糊连接度分割背景和确定人眼眉毛的位置，根据眉毛的中心精确定位和归一化人脸.实验结果表明，该方法消除了背景干扰，保留了更多的人脸信息。Thermal inflated faces have the characteristics of edge and detail faintness,low contast,different temperature dis- Iribution between faces and their backgrounds. Focusing on these characteristics, a new image segmentation method is proposed. Gray projection is used to coarsely locate face region. Fuzzy connectexiness is used to segment background and determine the positions of eyebrows.According to the centers of eyebrows, faces are located exactly and normalized. The expe ＇rtmental results show that the method eliminates the influence of backgrotmd, reserves more facial information and can effectively locate and segment thermal in- frared face images.

关 键 词：热红外人脸图像 灰度投影 模糊连接度 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]