一种鲁棒的旋转不变性多姿态人眼定位方法  

Robust rotation invariant multi-view eye localization method

作　　者：傅由甲[1,2] 洪雄[1] 李见为[2] 

机构地区：[1]重庆理工大学计算机科学与工程学院,重庆400054 [2]重庆大学光电工程学院,重庆400030

出　　处：《计算机应用研究》2010年第12期4794-4797,共4页Application Research of Computers

基　　金：重庆市自然科学基金资助项目(CSTC2009BB2195)

摘　　要：提出一种新的针对平面任意旋转角度的多姿态人眼定位的鲁棒方法。使用旋转不变性多姿态(RIMV)人脸检测器定位人脸区域并划分眼睛搜索范围,利用眉眼整体特征采用交叉检测法,用大规模多姿态眉眼及眼睛样本训练的二级支持向量机搜索区域,并选择若干个SVM判别函数值最高的窗口作为候选眼睛区域,根据候选窗口重叠情况进行筛选和合并以确定眼睛的最佳位置。实验表明,该方法具有很好的精确性和鲁棒性,能适应复杂背景下表情变化的任意姿态人脸上的眼睛定位。Focused on eyes localization on multi-view face with arbitrary rotation in plane,this paper proposed a new and robust method. First,located the face by the rotation invariant multi-view （ RIMV） face detector and determined the eye searching range on the face. Then,adopted the crossing detection method to scan the searching regions,which used the brow-eye feature and the improved two-level SVM detectors trained by large scale multi-view brow-eye and eye examples. Selected the window ones with the highest values in the SVM discriminant function as the candidate eye regions. Finally,after filtering and merging the candidate eye regions based on their overlapping states,located the exact eyes. Experiments show that the method has high accuracy and strong robustness to the eye localization with arbitrary face pose and expression in the complex background.

关 键 词：眼睛检测 眼睛定位 多视角眼睛定位 旋转眼睛定位 支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]