基于双Gabor方向韦伯局部描述子的掌纹识别

Double Gabor Orientation Weber Local Descriptor for Palmprint Recognition

该文结合掌纹图像的纹理特点,对原始韦伯局部描述子(WLD)中的差分激励和梯度方向进行改进,提出双Gabor方向韦伯局部描述子(DGWLD),以提高掌纹识别率。在构建新的差分激励图时,通过加入邻域像素点与中心像素点间灰度差分的方向信息,扩大异类掌纹间的差异。同时,采用双Gabor方向代替原始的梯度方向,减小平移和旋转对识别的影响。此外,为了更好地衡量特征间的相似度,使用交叉匹配算法,进一步提升识别率。在PolyU,MSpalmprint和CASIA掌纹库上进行实验,识别率均达到100%。实验的结果表明,与其它局部描述子和已有改进的WLD方法相比,该文方法具有更高的识别率和更低的等错误率。

In order to improve the palmprint recognition rate, this paper improves differential excitation and gradient orientation of Weber Local Descriptor （WLD） based on the texture features of palmprint images, and proposes a Double Gabor orientation Weber Local Descriptor （DGWLD）. The directional information of the difference between the neighborhood pixels and the central pixel is considered to enlarge the difference between palmprint, when constructing the new differential excitation map. At the same time, gradient orientation is replaced by double Gabor orientation to reduce the influence of translation and rotation. In addition, a feature cross matching algorithm is used for further improve the recognition rate. Experiments on PolyU, MSpalmprint and CASIA palmprint databases show that the recognition rate is up to 100%. The experimentM results show that the proposed method is superior in terms of identification rate and equal error rate compared with other local descriptor methods and improved WLD methods.