西安电子科技大学--生命科学技术学院
 
当前位置: 主页 > 研究成果 > 代表性成果 >

19、基于多层分类器的指纹分类方法

更新时间:2015-08-01 14:50 点击:
  

 由于指纹的类间差异较大类内差异较小,指纹分类是一个很难的问题。为了解决这个难题,针对指纹方向场我们提出了一种正则化方向传播模型,并使用一种多层的分类器来解决指纹分类的问题。首先,使用复数滤波器响应迅速找到大多数的拱型指纹。其次,使用针对中心点和脊线分类器来找到大多数螺旋类指纹。然后,基于方向场和复数滤波器使用K-NN分类器找到的前两类进行聚类。最后,使用脊线流分类器找到对剩余的指纹分类,并使用SVM得到最后的指纹分类结论。我们的算法在NIST SD4数据库上针对五类指纹的分类精确率达到了95.9%,四类指纹的精确率达到了97.2%。

 

Fingerprint classification by a hierarchical classifier  
Fingerprint classification is still a challenging problem due to large intra-class variability and small inter-class variability. To deal with these difficulties, we proposed a regularized orientation diffusion model for fingerprint orientation extraction and a hierarchical classifier for fingerprint classification in this paper. The first stage rapidly distinguishes a majority of Arch by using complex filter responses. The second stage distinguishes a majority of Whorl by using core points and ridgeline flow classifier. In the third stage, K-NN classifier finds the top two categories by using orientation field and complex filter responses. In the fourth stage, ridgeline flow classifier is used to distinguish Loop from other classes except Whorl. SVM was adopted to make the final classification in the last stage. The classification method has been evaluated with NIST SD4. It achieved a classification accuracy of 95.9% for five-class classification and 97.2% for four-class classification without rejection.
 

分类器参数λ和能量之间关系图,其中OI为方向图,CFRS为复数滤波器相应。

Analysis of classifier parameters λ and energy, where OI denotes the orientation image and CFRs denote complex filter responses。

 

------分隔线----------------------------
西安电子科技大学 生命科学技术学院 版权所有 2009-2016
电子工程学院网络信息中心制作维护  管理员信箱 xidianlife@163.com