首页> 外国专利> liveness detection method fingerprint using convolutional networks

liveness detection method fingerprint using convolutional networks

机译:卷积网络的活度检测方法指纹

摘要

method detection vivacity of impressions using digital networks convolutional. The present invention relates to a method for liveness detection using fingerprint feature extraction technique called convolutional network and an artificial increase in the dataset in order to improve the accuracy of the classifier system. It is also applied dimensionality reduction by principal component analysis (PCA) with whitening and a classifier support vector machine (SVM) with gaussian kernel, used to determine whether the samples are true or false. preprocessing operations such as frequency filtering, extracting the region of interest (ROI) and contrast equalization can be used to improve accuracy.
机译:方法使用数字网络卷积检测印象的活力。本发明涉及一种使用指纹特征提取技术(称为卷积网络)的活度检测方法,以及为了提高分类器系统的准确性而人为增加数据集的方法。它还通过白化的主成分分析(PCA)和高斯核的分类器支持向量机(SVM)应用于降维,用于确定样本是真还是假。诸如频率滤波,提取感兴趣区域(ROI)和对比度均衡之类的预处理操作可用于提高准确性。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号