基于混沌蜂群优化的指纹匹配算法

A fingerprint minutiae matching algorithm based on chaotic bee colony optimization

为了进一步加快指纹匹配算法的运算速度、提高识别效率,提出了一种基于混沌蜂群优化和可变界限盒的指纹匹配算法。首先,结合人工蜂群优化算法收敛速度快、控制参数少、能够避免局部最优等优点以及混沌策略的类随机性、高遍历性等特点,在指纹点匹配中引入混沌蜂群优化算法,并设计兼顾了匹配精度和运算时间的适应度函数;然后利用适应度函数估计出指纹特征匹配的几何变换参数并进行指纹点特征的粗匹配;最后,利用可变界限盒进行精匹配,避免指纹图像局部形变带来的影响。大量实验结果表明,与基于局部特征的指纹匹配算法、基于遗传算法优化的指纹匹配算法相比,本文提出的算法所需运算时间更短,匹配精度更高。

In order to further improve the operational speed and the recognition efficiency of fingerprint matching al- gorithms, a fingerprint matching algorithm based on chaotic bee colony activity and a variable boundary box was proposed. Firstly, by combining the advantages of artificial bee colony optimization including fast convergence times, fewer control parameters, and the lack of local optima, with the features of a chaos strategy including its random-like property and ergodicity, the chaotic bee colony activity was introduced into point pattern matching for fingerprint images. A corresponding fitness function incorporating both matching accuracy and operational time was then designed. The corresponding fitness function was then used to estimate the geometric transformation parameters for fingerprint rough matching. Finally, a variable boundary box can be used for fine matching, because it avoids any influences relating to local deformation of the fingerprint images. A large number of experimental results show that, compared with two alternative fingerprint matching algorithms （based on local features and genetic algorithm optimization, respectively） the proposed algorithm has a shorter operational time and has higher matching accuracy.