摘要
研究眼睛特征提取过程中可变形模板中能量函数优化方法.根据能量函数中各能量项的作用区域大小,将整个优化过程分解为3个步骤.首先定位虹膜的位置和尺寸,然后调整眼睛的外轮廓,最后采用所有的能量项对眼睛特征的所有参数进行微调.每个步骤不再向下分解为多个子步骤.实验结果表明,与其他的优化过程相比,提出的优化过程在速度和精度上都有所提高.
Investigates energy function minimization process for eye feature extraction based on deformable template. The minimization process is divided into three steps, which emphasizes on local properties of energy terms. The iris is located firstly. Then the eye boundaries are adjusted. Finally, all energy terms are activated to tune the eye template. Each step needs not to be split to some sub-steps. Empirical comparison with other minimization processes shows the superiority of the proposed process in terms of both efficiency and accuracy.
出处
《北京理工大学学报》
EI
CAS
CSCD
北大核心
2009年第2期128-132,共5页
Transactions of Beijing Institute of Technology
基金
北京市优秀人才培养专项经费资助项目(20081D1600300343)
北京理工大学优秀青年教师资助计划项目(2007Y0305)
关键词
眼睛特征提取
可变形模板
优化过程
eye feature extraction
deformable template
minimization process
