基于改进型最大类间方差法的瞳孔定位方法_黄丽丽1_杨帆2_王东强2_唐云建2.pdfVIP

网络出版时间：2012-09-07 09:00 网络出版地址：/kcms/detail/11.2127.TP0900.012.html 1 Computer Engineering and Applications 计算机工程与应用 基于改进型最大类间方差法的瞳孔定位方法 1 2 2 2 黄丽丽 ，杨帆 ，王东强 ，唐云建 HUANG Lili1，YANG Fan2，WANG Dongqiang2，TANG Yunjian2 1.重庆邮电大学 计算机科学与技术学院，重庆市 400065 2.重庆市科学技术研究院 信息与自动化技术研究中心，重庆市 401123 1. College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China 2. Research Center for Information and Automation Technologies, Chongqing Academy of Science Technology, Chongqing 401123, China HUANG Lili, YANG Fan, WANG Dongqiang, TANG Yunjian. Pupil location method based on improved OTSU algorithm. Computer Engineering and Applications Abstract: To improve the accuracy and rapidity of pupil location in human-computer interaction, a method based on the improved OTSU algorithm is proposed in this paper. First, the image is pre-processed using light compensating and median filtering to calculate the maximum between-class variance of the pixels which exist in the image, and obtain the optimum threshold of the binary image, finally, the pupil center and radius is got by using ellipse fitting. Experiment results show that the method is quite accurate and fast, which laid a great foundation for the eye tracking. Key words: Pupil location; threshold; OTSU algorithm; Ellipse fitting 摘要：为了提高人机交互中瞳孔定位的精确性与快速性，提出一种基于改进型最大类间方差 法的瞳孔定位方法。首先，对图像进行基于光线补偿和中值滤波的预处理操作，进而根据直 方图统计出图像中未出现的像素灰度值，计算余下像素的最大类间方差，求取二值化图像的 最佳阈值，最后，采用椭圆拟合方法