Finger Vein Image Registration Based on Genetic Algorithm

摘要

Finger vein recognition technology is an emerging biometric identification technology that utilizes the distribution structure of venous blood vessels to achieve identification. The vein recognition process is divided into two parts: registration and recognition. In the registration process, the generation of registration template is particularly important. In order to obtain the registration template more accurately, this paper proposes a finger vein image registration algorithm based on genetic algorithm. The principle of the algorithm is to use the mutual information of two finger vein images as the fitness function of the genetic algorithm, and use the genetic algorithm to search for the optimal parameters of the rigid body transformation model. The experimental results show that the algorithm is effective and can achieve the registration of finger vein images within a short iteration.