非接触式掌纹识别技术中关键点的定位方法  

Key Points Localization Methods of Contactless Palmprint Recognition Technology

作　　者：唐有宝[1] 卜巍[1,2] 邬向前[1] 王宽全[1] TANG Youbao, BU Wei, WU Xiangqian, WANG Kuanquan （1 School of Computer Science ＆ Technology,Harbin Institute of Technology, Harbin 150001,China; 2 Department of Media Technology and Art, Harbin Institute of Technology, Harbin 150001,China）

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001 [2]哈尔滨工业大学媒体技术与艺术系,哈尔滨150001

出　　处：《智能计算机与应用》2011年第1X期62-65,共4页Intelligent Computer and Applications

基　　金：基金项目：国家自然科学基金项目（60873140、61073125）,教育部新世纪优秀人才支持计划项目（NCET-08-0155）,霍英东教育基金项目（122035）.

摘　　要：在掌纹识别技术中，关键点的定位起到了至关重要的作用。为了提高用户的接受度，采用了非接触式的掌纹识别技术。针对关键点定位的准确性影响识别精度，提出基于非接触式掌纹图像的关键点定位方法，其中包括手指张开时和手指并拢时两种情况。首先通过预处理提取手形的外侧轮廓，然后采用基于角度和方向的跟踪方法来初定位手指指尖点和手指间的凹点所在区域，最后细定位指尖点和手指间的拐点。实验结果表明，提出的关键点定位方法定位精确且稳定性高。The key points localization play a crucial role in palmprint recognition technology. In order to improve the user＇s acceptance, the non-contact palmprint identification technology is used. For the precision of palmprint identification influenced by the accuracy of key points localiza- tion, a localization method of key points based on non-contact palmprint images is presented in this paper, which performs on both finger-sep- arated and finger-closed palmprint images. The boundary ofpahn is detected through preprocessing, and then fingertip points and finger valley points are located by tracing the boundary according to angle and orientation. Finally, key points that will be useful in palmprint recognition are determined. Experimental results show that the proposed method provides considerable performance in both localization accuracy and stability.

关 键 词：非接触 手指并拢 手指张开 关键点定位 掌纹识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]