一种高性能近红外光人脸检测和眼睛定位算法  

A High-Performance Algorithm of Face Detection and Eye Localization Based on Near-Infrared Image

作　　者：张昌明[1] 童卫青[1] 王燕群[1] 

机构地区：[1]华东师范大学计算机科学技术系,上海200241

出　　处：《计算机系统应用》2011年第4期96-101,共6页Computer Systems & Applications

摘　　要：提出了一种新型的近红外光人脸检测和眼睛定位算法,该算法先用AdaBoost分类器进行人脸区域定位,然后在人脸区域内进行眼镜检测:若检测为不戴眼镜,使用基于数理形态学的N-Quoit滤波器进行眼睛精确定位;若检测为戴眼镜,采用"人脸可信值最大"准则进行眼睛定位。实验结果表明,此算法检测率高而且眼睛定位准确,有效的克服了镜片反射近红外光干扰眼睛精确定位的问题,同时达到了实时性的要求。This paper proposes a novel face detection and eye localization algorithm based on near-infrared（NIR） image.Initially.The AdaBoost algorithm is introduced here to detect face,and then detection of the presence of glasses is performed in the candidate face area.If glasses are not present in face area,N-Quoit filter will be used to locate eyes.Otherwise,eye location can be determined by the ＂Faceness＂ criterion.Experimental results demonstrate that our method is capable of achieving high accuracy and real-time performance,and is an effective solution to the issue of specular reflections of NIR lights on glasses in eye localization.

关 键 词：人脸检测 眼睛定位 眼镜检测 ADABOOST N-Quoit滤波器 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]