摘要
提出了一种新的图像中人眼检测算法,在一幅已知的人脸图像中首先采用同态滤波算法增强图像的对比度,然后利用迭代式阈值选择法对图像进行二值化处理,根据传统的先验知识获得眼睛的候选区域。根据眼睛的构造提出了一种基于最小外接矩形的自定义模板来实现眼睛的最终定位并利用区域质心标定出了眼睛区域的中心位置。实验证明,本算法简单实用,能够有效地实施人眼的检测,具有较高的检测精度。
This paper proposed a new algorithm for eyes detection in the images. First, in a known face image, the homomorphie filter was used to enhance the contrast of the image and the iterative thresh choosing algorithm changed the gray images into binary ones. According to certain priori knowledge, it could get the candidate field of the eyes. Then this paper proposed a userefined template based on the minimum enclosing rectangle （MER） to complete the finally orientation, and found the center of the eyes using the area eentroid. According to many tests, the algorithm can easily and quickly detect the eyes.
出处
《计算机应用研究》
CSCD
北大核心
2008年第7期2223-2224,2227,共3页
Application Research of Computers
基金
教育部留学回国人员科研启动基金资助项目(2005383)
关键词
人眼检测
计算机视觉
最小外接矩形
质心
eyes detection
computer vision
minimum enclosing rectangle
eentroid
