首页> 外国专利> COARSE-TO-FINE CASCADE ADAPTATIONS FOR LICENSE PLATE RECOGNITION WITH CONVOLUTIONAL NEURAL NETWORKS

COARSE-TO-FINE CASCADE ADAPTATIONS FOR LICENSE PLATE RECOGNITION WITH CONVOLUTIONAL NEURAL NETWORKS

机译:卷积神经网络的从粗到细级联适应

摘要

PROBLEM TO BE SOLVED: To provide a method for recognizing a license plate in an image cropped by a more correctly efficient method.SOLUTION: In methods and systems for license plate recognition utilizing a trained neural network, the neural network includes steps of iteratively training and adapting the neural network for a particular task such as text recognition in a context of a license plate recognition application. The neural network is configured to: be trained so as to perform generic text recognition utilizing a plurality of training samples; be applied to a cropped image of a license plate; and recognize text to generate a license plate transcription with respect to the license plate. An example of such the neural network is a CNN (Convolutional Neural Network).SELECTED DRAWING: Figure 1
机译:要解决的问题:提供一种在通过更正确有效的方法裁剪的图像中识别车牌的方法。解决方案:在利用训练有素的神经网络进行车牌识别的方法和系统中,神经网络包括迭代训练和使神经网络适应特定任务,例如车牌识别应用程序中的文本识别。所述神经网络被配置为:被训练以便利用多个训练样本执行通用文本识别;以及应用于车牌的裁剪图像;并识别文本以生成关于车牌的车牌转录。这种神经网络的一个例子是CNN(卷积神经网络)。

著录项

  • 公开/公告号JP2017111806A

    专利类型

  • 公开/公告日2017-06-22

    原文格式PDF

  • 申请/专利权人 XEROX CORP;

    申请/专利号JP20160233642

  • 发明设计人 ALBERT GORDO SOLDEVILA;JON ALMAZAN;

    申请日2016-11-30

  • 分类号G06K9/66;G06T7/00;

  • 国家 JP

  • 入库时间 2022-08-21 13:59:20

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