基于改进型抛物线Hough变换的眼睛特征提取  

Eye feature extraction based on modified parabolic Hough transforms

作　　者：李亚利[1] 王生进[1] 胡斌[1] 丁晓青[1] 

机构地区：[1]清华大学电子工程系,智能技术与系统国家重点实验室,北京100084

出　　处：《清华大学学报（自然科学版）》2010年第1期100-103,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家“八六三”高技术项目(2006AA01Z115及2006AA11Z213)

摘　　要：眼睛特征提取有广泛的应用。针对眼睛特征参数提取的需求,该文对传统的抛物线Hough变换算法进行改进,提出将抛物线的系数作为变换量,结合边缘梯度方向计算抛物线的顶点坐标并获取抛物线参数的方法。在此基础上将算法拓展到对称轴与坐标轴不平行情况下的抛物线的Hough变换,以适应旋转。实验表明:该算法可精确有效地提取眼睛特征并可应用在人机交互、驾驶员疲劳检测等领域。Many applications need efficient eye feature extraction algorithms. This paper presents a modified parabolic Hough transform where the coefficient of the parabola is used as the variant with the vertex locations changing as the coefficient changes. The gradient direction of edge feature is also combined to reduce the computational cost. The algorithm is also extended to a parabola in which the axis of symmetry is not parallel to the coordinate axes. Experimental results show that the method can extract eye feature precisely and efficiently, and can be applied in the areas such as human-computer interface and driver fatigue detection.

关 键 词：模式识别 眼睛特征提取 抛物线Hough变换 变形模板 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]