首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于降维比较的指横纹定位方法
引用本文:田永梅,麻英晖,祁乐陶.基于降维比较的指横纹定位方法[J].河北科技大学学报,2012,33(5):448-452.
作者姓名:田永梅  麻英晖  祁乐陶
作者单位:1. 河北大学电子信息工程学院,河北保定,071002
2. 中国环境管理干部学院现代化教育中心,河北秦皇岛,066004
3. 爱荷华州立大学计算机科学系,爱荷华州埃姆斯50011
基金项目:国家自然科学基金资助项目(60903089,61073121);河北省自然科学基金资助项目(F2009000215);河北省科技支撑计划项目(072135188)
摘    要:针对指横纹感兴趣区域(ROI)难以准确、快速定位的问题,提出了利用降维比较进行定位的方法。该方法在图像定位阶段,对ROI特征图像在水平和垂直2个方向投影,实现了图像的降维,在保留特征信息的基础上降低了后续处理计算的时间复杂度。将降维后的2个一维向量进行比较,最终实现指横纹ROI的精准定位。相对于传统方法,本方法降低了运算的维数,算法复杂度低,速度快,实验结果验证了该方法的有效性。

关 键 词:Gabor滤波  图像投影  图像定位
收稿时间:2012/9/3 0:00:00

A location algorithm of inner-knuckle-print based on dimension reduction
TIAN Yong-mei,MA Ying-hui and QI Le-tao.A location algorithm of inner-knuckle-print based on dimension reduction[J].Journal of Hebei University of Science and Technology,2012,33(5):448-452.
Authors:TIAN Yong-mei  MA Ying-hui and QI Le-tao
Institution:1. College of Electronic and Information Engineering, Hebei University, Baoding Hebei 071002, China; 2. Modern Education Center, Environmental Management College of China, Qinhuangdao Hebei 066004, China; 3. Department of Computer Science, Iowa State University, Ames Iowa 50011, USA)
Abstract:Considering the difficulty of accurately and fast location of ROI of inner-knuckle-print, a new location algorithm is presented forward based on dimension reduction. This algorithm transforms 2-dimension image data to two 1-dimension data by projecting the binary image in vertical and horizontal direction, and then aligns ROI images through the comparison of the two 1-dimension data. This leads to rapid and efficient recognition. The experimental results verify that it is rapid and effective than traditional methods.
Keywords:Gabor filtering projection image location
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《河北科技大学学报》浏览原始摘要信息
点击此处可从《河北科技大学学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号