A Method for Real-Time Eye Blink Detection and Its Application
A Method for Real-Time Eye Blink Detection and Its Application
复制标题
一种实时眨眼检测方法及其应用
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
T. Srinark
中科院分区：
文献类型：
--
作者：
T. Srinark
各种人类行为可以通过眨眼模式来指示。在本文中，我们提出了一种基于图像处理技术的方法，用于检测人类眨眼和生成眨眼间的时间间隔。我们采用Haar级联分类器和Camshift算法进行人脸跟踪，从而得到人脸轴信息。此外，我们应用了一个自适应Haar级联分类器从一个级联的提升分类器的基础上Haar的功能，使用之间的关系，眼睛和面部轴定位眼睛艾德。提出子一种新的眨眼检测算法和一种新的眨眼检测度量--眼睑状态检测值ESD值然后可以用于检查眼睑的张开和闭合状态。我们的算法提供了一个99.6%的整体准确性检测眨眼deteetable。我们通过两个连续的眨眼状态之间的差异来生成眨眼间隔图。这些曲线图显示人类常见的眨眼呈现短持续时间和长持续时间交替出现。
Various human behaviors can be indicated by eye blink patterns. In this paper, we present a method based on image processing techniques for detecting human eye blinks and generating inter-eye-blink intervals. We applied Haar Cascade Classifier and Camshift algorithms for face tracking and consequently getting facial axis infor mation. In addition, we applied an Adaptive Haar Cascade Classifier from a cascade of boosted classifiers ba ed on Haar-like features using the relationship between t he eyes and the facial axis for positioning the eyes. We pr oposed a new algorithm and a new measurement for eye blinkin g detection called “the eyelid’s state detecting (ESD ) value.” The ESD value can then be used for examining the op en and close states of eyelids. Our algorithm provides a 99.6% overall accuracy detection for eye blink dete ction. We generated inter-eye-blink interval graphs by differencing between two consecutive eye blink stat e . The graphs show that the common blinks of human present s short and long durations alternatively.