摘要
选择了一种基于模拟退火遗传算法来提取虹膜的内外轮廓。为了避免了遗传算法后期搜索效率不高,容易陷入局部最优解的情况,本文将模拟退火算法引入遗传算法,结合模拟退火算法的局部搜索能力强的优点,设定了自适应交叉概率和变异概率,提高了收敛到全局最优的概率。处理虹膜图像时,使用区域生长的方法去除光斑,各提取出虹膜内外边缘的多个边缘点,使用模拟退火遗传算法优化目标函数,寻找出最优的圆拟合虹膜内外边缘。最后选取了中科院提供的CASIA-Iris-Interval和CASIA-Iris-Twins虹膜数据库,在MATLAB2010b上与另外两种算法进行性能测试,结果证明,本文算法速度更快,准确率更优。
In this paper, a simulated annealing genetic algorithm is proposed to extract the inner and outer contours of the iris. In order to avoid the problem that the genetic algorithm is not efficient in the later search, it is easy to fall into the local optimal solution. In this paper, the simulated annealing algorithm is introduced into the genetic algorithm, and the adaptive crossover probability and mutation are set by combining the advantages of the local search ability of the simulated annealing algorithm Probability, which improves the probability of convergence to global optimum. When the iris image is processed, the regional growth method is used to remove the spot, and the edge points of the inner and outer edges of the iris are extracted. The simulated annealing genetic algorithm is used to optimize the objective function to find the optimal edge of the iris. Finally, the CASIA-Iris-Interval and CASIA-Iris- Twins iris database provided by the Chinese Academy of Sciences were selected and tested on the MATLAB2010b with two other algorithms. The results show that the proposed algorithm is faster and more accurate.
作者
王延年
赵朗月
刘会敏
WANG Yannian;ZHAO Langyue;LIU Huimin(College of electronic information Xi＇ an Polytechnic University, Xi＇ an 710048, China)
出处
《激光杂志》
北大核心
2018年第6期89-93,共5页
Laser Journal
关键词
模拟退火遗传算法
自适应交叉概率和变异概率
全局最优
虹膜定位
simulated annealing genetic algorithm
adaptive crossover probability and mutation probability
global optimal
iris location
