Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (5): 202-205.

• 图形、图像、模式识别 • Previous Articles     Next Articles

Method for eyes localization in infrared image

XIE Xiuzhen,TANG Jin,CHEN Shouming,LI Qing   

  1. School of Information Science and Engineering,Central South University,Changsha 410083,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-02-11 Published:2011-02-11

一种在红外图像中定位人眼的方法

谢秀珍,唐 琎,陈守明,李 青   

  1. 中南大学 信息科学与工程学院,长沙 410083

Abstract: In order to realize accurate positioning for eyes in infrared image,a new method of eyes positioning in infrared image is put forward.In a known face image,the face region is obtained by projection.According to the features of gradient changing more heated in eyebrow-eye area,the rough region of the eyes is got.Finally,using the characteristics of the large differences in gray between the eye and pupil in infrared image,Robert edge detection and the method of maximum gradient can be used to position eyes accurately.Test proves that the method of the eyes position in infrared image has a good effect and high precision.

Key words: projection, eyes position, Robert edge detection, gradient

摘要: 为了实现红外图像人眼的精确定位,提出了一种新的定位红外图像人眼的方法。在已知的一幅红外人脸图像中,通过投影得到人脸区域,根据眉眼区域的梯度变化比较激烈的特点,来得到人眼的大致区域,最后,利用红外图像人眼瞳孔与眼球之间的灰度存在很大差异的特性,采用Robert边缘检测求梯度最大值的方法,精确地定位出人眼。实验证明,该方法对红外图像的人眼定位效果很好,精确度很高。

关键词: 投影, 人眼定位, Robert边缘检测, 梯度