自动指纹识别系统中指纹图像分割方法的研究

Research on Segmentation Method of Fingerprint Image in AFIS

在研究和分析传统的指纹分割方法:方差法和方向图法的基础上,介绍了一种基于最大类间方差的指纹图像分割方法,并将它和方向图法合理结合,然后提出了一种新的基于方向图和最大类间方差的复合分割方法。该复合分割方法的优点是不仅具有良好的分割效果,而且该方法在运算速度上比传统方法更快,更适合于实时处理。

After investigating and analyzing the two traditional methods： gray variance and directional image,an approach is introduced to segment the fingerprint images based on the maximum between- cluster variance （MBV）, and unit MBV and directional image reasonably, then it presents a new approach namely uses one kind based on the directional image and MBV compound segmentation method. Compared with the two traditional methods, this new method not only has the advantage in the good effect of the segmentation, but also works faster. This method is more suitable for real - time processing.