基于分段移位的虹膜匹配算法

Iris Matching Method Based on Segmentation Shifting

对于某些虹膜成像装置,同一个虹膜不同次成像的虹膜纹理可能会发生偏移,这种偏移有可能导致虹膜特征编码的偏移,从而直接影响虹膜的特征匹配结果。本文通过对归一化虹膜图像中导致虹膜纹理偏移的影响因素进行了分析,发现这种偏移是有规律的,并针对这种变化规律,提出了一种特征编码分段移位匹配的方法。实验结果表明,本文所提出的方法能够显著降低同一个虹膜不同次成像纹理偏移的特征匹配相异度。

For some iris image capture devices, the same iris texture gotten in different times may shift. This shift may lead to offset of the iris feature encoding, and thus affect the characteristic match of the iris directly. By analyzing the factors of the iris texture shift, the regularity of the shift is found and a matching method of segmentation shift is put forth. Experimental results show that the method proposed in this paper can significantly increase similarity of the same iris which is captured in different times.