基于关键路径优化交叉遗传算法的掌纹识别  

PALMPRINT RECOGNITION BASED ON GENETIC ALGORITHM WITH CRITICAL PATH OPTIMISED CROSSOVER

作　　者：许爽[1] 叶恺[1] 毕新煕 

机构地区：[1]中州大学,河南郑州450044 [2]河南天冠燃料乙醇有限公司,河南南阳473000

出　　处：《计算机应用与软件》2014年第7期195-197,251,共4页Computer Applications and Software

摘　　要：传统的掌纹识别算法在大多情况下运行缓慢以致效率不高,通常会依赖昂贵的技术装备而导致成本较高。针对这一问题,提出基于关键路径优化交叉遗传算法(CGA)的掌纹识别算法。首先,利用关键路径算法找到染色体的关键路径,借助于交叉概率剔除染色体的最差候选种群;然后选择最佳候选种群进行交叉运算,有效地改善低质量掌纹图像的问题;最后,在掌纹图像上的实验验证该算法的有效性及可靠性。实验结果表明,相比18项参数总和算法,该算法取得了更高的识别率,同时大大地降低了识别所耗时间,有望运用于实时掌纹识别系统。Traditional palmprint recognition algorithms have poor efficiency in most cases due to slow operation, and usually rely on expensive technical equipment which results in higher costs. In light of this problem, we propose the palmprint recognition algorithm which is based on the genetic algorithm with critical path optimised crossover. First, we use critical path algorithm to find the critical path of chromosomes and get rid of the worst candidate population of chromosomes with the help of crossover probability. Then, we select the best candidate population for crossover operation, which effectively improves the problem of low quality palmprint image. Finally, the experiments on palmprint images verify the effectiveness and reliability of the proposed algorithm. Experimental results show that proposed algorithm achieves higher recognition rate than the algorithm of 18 parameters＇ summation and meanwhile greatly reduces the time cost of recognition, thus it can be expected to apply to real-time palmprint recognition system.

关 键 词：关键路径 交叉遗传算法 掌纹识别 交叉概率 18项参数总和 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]