互联网 qkzz.net
全刊杂志网:首页 > 女性 > 文章正文
刊社推荐

小波分解与PCA方法的掌纹特征提取方法苑玮琦 黄 静 桑海峰


  (沈阳工业大学 计算机视觉检测研究所, 沈阳 110023)

  

   摘 要:

  提出了一种新的掌纹特征提取方法,其目的在于在不降低识别率的情况下,提高掌纹特征提取速度。首先将原始掌纹图像进行小波分解,获得低分辨率的掌纹图像;其次通过主成分分析(pca)方法获得一个低维子空间,即“特征掌”;最后通过将训练、测试样本在该“特征掌”上投影来提取掌纹特征。实验结果表明,所提出方法与单一pca方法比较,在同样识别率情况下,特征提取速度明显提高。

   关键词:小波分解; 主成分分析; 特征提取; 掌纹识别

   中图分类号:tp274 文献标志码: a

   文章编号:10013695(2008)12367103

   

  palmprint recognition based on wavelet decomposition and pca

  

  yuan weiqi, huang jing, sang haifeng

  

  (computer vision group, shenyang university of technology, shenyang 110023, china)

   

   abstract:

  this paper proposed a new method for feature extraction of palmprint. this method improved upon feature extraction speed of palmprint under without reducing recognition rate. first, the original palmprint images became the lower resolution images using wavelet decomposing. second, used principal components analysis, reduced the lower resolution palmprint images dimensionality. this low dimensional feature subspace was called “eigenpalms”. at last, those samples of a training set and a testing set were projected this “eigenpalms”. the experiment result shows that much training time has been saved by using this algorithm in features extracting recognition.

......
很抱歉,暂无全文,若需要阅读全文或喜欢本刊物请联系《计算机应用研究》杂志社购买。
欢迎作者提供全文,请点击编辑
分享:
 

了解更多资讯,请关注“木兰百花园”
分享:
 
精彩图文


关键字
支持中国杂志产业发展,请购买、订阅纸质杂志,欢迎杂志社提供过刊、样刊及电子版。
关于我们 | 网站声明 | 刊社管理 | 网站地图 | 联系方式 | 中图分类法 | RSS 2.0订阅 | IP查询
全刊杂志赏析网 2017