首页> 外国专利> LICENSE PLATE RECOGNITION METHOD USING DIFFERENTIAL IMAGE AND NEURAL NETWORK

LICENSE PLATE RECOGNITION METHOD USING DIFFERENTIAL IMAGE AND NEURAL NETWORK

机译:基于差分图像和神经网络的车牌识别方法

摘要

A license plate recognition method using a differential image and a nerve network is provided to divide the kind of a license plate of labeling and recognize the license plate with different reference fonts according to the divided license plate, thereby improving the speed and accuracy of the number recognition. A license plate recognition method comprises the following steps of: inputting a license plate image(211); analyzing the license plate image and dividing the license plate image by region(213); and recognizing the divided license plate image by applying differential image technique and nerve network technique to the divided image regions(230). A dividing method by region comprises the following steps of: dividing into an upper letter region and a lower letter region; labeling characters and numerals by each region; and dividing the license plate by type through the labeling.
机译:提供了一种使用差分图像和神经网络的车牌识别方法,以划分标签的车牌种类,并根据所划分的车牌识别具有不同参考字体的车牌,从而提高了数字化的速度和准确性。承认。车牌识别方法包括以下步骤:输入车牌图像(211);以及输入车牌图像(211)。分析车牌图像并将车牌图像除以区域(213);通过将差分图像技术和神经网络技术应用于分割图像区域来识别分割的车牌图像(230)。按区域划分方法包括以下步骤:分为上字母区域和下字母区域;按每个区域标记字符和数字;并通过标签按类型划分车牌。

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