【摘要】 指纹识别是计算机模式识别领域中一个比较活跃的课题,有着十分广泛的应用前景。对于庞大的指纹信息,人们越来越关心的是如何对其分类与储存。文章提出了一种基于BP神经网络的指纹模板分类算法,在简介指纹图像的预处理和模板建立过程的基础上,着重阐述基于黄金分割法的自适应变步长算法。仿真表明它比传统的固定步长算法有更好的收敛速度与精度。更多还原

【Abstract】 Fingerprint recognitio n is an active subject in the field of pattern recognition which has an extensiv e applied foreground.People are more and more concerned about how to classify a nd how to store the huge number of fingerprint template information.The paper p resents a classifiable algorithm of fingerprint template based on BP neural netw orks.Having simply introducing the process of image precondition and fingerprin t template building,we emphatically formulate a self-adapting and step-changi ng algorithm used gold-segmentation.At last,the simulation result indicates t hat the new algorithm is more superior in convergent rate and precision than tha t of other traditional algorithms.更多还原