CAJ | 학술논문

在本文中，我们介绍了一种基于遗传算法的指纹方向图划分方案.根据各种典型指纹类别的拓扑特性而引进了一组动态分区模板和代价函数用于引导方向图分区，并将寻找最佳匹配划分的过程转化成一个N维向量空间的函数优化问题，然后给出了该问题基于遗传算法的求解过程.最后，我们讨论了本方法在指纹分类中的应用.
재본문중，아문개소료일충기우유전산법적지문방향도화분방안.근거각충전형지문유별적탁복특성이인진료일조동태분구 모판화대개함수용우인도방향도분구，병장심조최가필배화분적과정전화성일개N유향량공간적함수우화문제，연후급출료해문제 기우유전산법적구해과정.최후，아문토론료본방법재지문분류중적응용.
In this work, we introduce a method of fingerprint directional image partitioning based on GA. According to the fingerprint topology, A set of dynamic partition masks and a cost estimating function are designed to guide the partitioning procedure. Finding best fitted mask application is converted to an functional optimizing problem, and we give out a GA solution to the problem. At last, we discuss the application of the proposed method in Fingerprint Classification.