基于自适应Harris角点检测的掌纹定位方法  

Fast location algorithm based on adaptive Harris corner detector

作　　者：张朝柱[1] 王鹏[1] 郑翠[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《黑龙江大学自然科学学报》2010年第2期246-250,共5页Journal of Natural Science of Heilongjiang University

基　　金：国家自然科学基金资助项目(60672034);黑龙江省高等学校青年学术骨干支持计划项目(1153G063)

摘　　要：分析Harris角点检测算子的实现原理及其应用于掌纹定位中时的不足,提出了一种基于自适应Harris角点检测的快速掌纹定位算法,该算法可以人为选择感兴趣区域进行检测,然后利用角点进行定位。有效地避免了掌纹定位过程中二值化,边缘检测等一系列复杂的过程,并且克服了检测过程中的角点簇拥,计算量大的缺点。实验结果表明,该方法进行的掌纹定位非但计算量小,处理速度快,而且检测出的角点分布均匀合理,能更好的适应图像定位等一系列的应用。The realization theory of Harris corner detector and its disadvantage in application of palmprint location are analyzed. A fast location algorithm based on adaptive Harris corner detector is proposed. The region interested can be detected artificially using this algorithm and then corner detector is used for location. This method effectively avoids binaryzation and edge detection in palmprint process. Moreover, it has overcome the clustering of corner and the disadvantage of large amount of calculation in the process of detection. The experimental result shows that this method not only has small amount of calculation and fast processing speed, but also the distribution of detected corner is reasonable, so that it can be used in image location.

关 键 词：角点检测 HARRIS算子 掌纹定位 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]