首页> 外国专利> ANPR with Deep Learning

ANPR with Deep Learning

机译:安然学习深处

摘要

The present invention relates to a license plate recognition program using deep learning, and since it can be a base technology that can be used for smart tolling, it can be used universally, thereby solving the problem of not recognizing the existing new license plate or electric vehicle license plate well. will be. In other words, the present invention is a vehicle recognition deep learning model formed with YOLO v4 that can simultaneously recognize a vehicle and a license plate in real time in a license plate recognition program, and an OCR formed with a support vector machine to discriminate Hangul and numbers of all license plates. it is composed Therefore, the present invention has the effect of solving the problem of not recognizing the existing new license plate or electric vehicle license plate well by making it universally usable because it can be a base technology that can be used for smart tolling.
机译:本发明涉及使用深度学习的牌照识别程序,因为它可以是可以用于智能收费的基础技术,因此可以普遍使用,从而解决不识别现有的新车牌或电动的问题 车辆车牌良好。 将会。 换句话说,本发明是一种车辆识别深度学习模型,其形成与YOLO V4形成,该yolo v4可以在车牌识别程序中实时识别车辆和牌照,以及由支持向量机形成的OCR以区分刽子手 所有牌照的数量。 因此,本发明具有解决不识别现有新车牌或电动车辆牌照的问题的效果,使其普遍可用,因为它可以是可用于智能收费的基础技术。

著录项

  • 公开/公告号KR20210154516A

    专利类型

  • 公开/公告日2021-12-21

    原文格式PDF

  • 申请/专利权人 오중균;

    申请/专利号KR1020200071616

  • 发明设计人 오중균;

    申请日2020-06-12

  • 分类号G06K9/32;G06N20/10;

  • 国家 KR

  • 入库时间 2022-08-24 22:56:29

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