首页> 外国专利> METHOD AND APPARATUS FOR DISEASE CLASSIFICATION OF PLANT LEAFS

METHOD AND APPARATUS FOR DISEASE CLASSIFICATION OF PLANT LEAFS

机译:植物叶片疾病分类的方法和装置

摘要

The present invention relates to a pest detection method and apparatus for crop images, and the pest detection method according to an embodiment of the present invention comprises the steps of: an image processing unit dividing a crop image into superpixel units; an image processing unit superpixel Creating a bounding box circumscribed to the outline of , the filtering unit removing the background area other than the superpixel included in the bounding box, the data analysis unit using a convolutional neural network (CNN) It may include the steps of classifying the boundary box from which the background area is removed based on the pest type of the crop, and the pest diagnosis unit detecting the pest for each classified boundary box.
机译:本发明涉及用于裁剪图像的害虫检测方法和装置,并且根据本发明实施例的害虫检测方法包括以下步骤:将裁剪图像分成超像素单元的图像处理单元; 图像处理单元Superpixel创建界限框,该边界盒围绕滤波单元移除除界框中包括的超顶以外的背景区域,使用卷积神经网络(CNN)的数据分析单元可以包括步骤 根据作物的害虫类型对从中移除背景区域的边界盒,以及检测每个分类边界盒的害虫诊断单元。

著录项

  • 公开/公告号KR102283452B1

    专利类型

  • 公开/公告日2021-07-30

    原文格式PDF

  • 申请/专利权人 강원대학교산학협력단;

    申请/专利号KR20190110176

  • 发明设计人 김만배;황인철;조현종;

    申请日2019-09-05

  • 分类号G06Q50/02;G06N3/04;G06T5;G06T7/11;

  • 国家 KR

  • 入库时间 2022-08-24 20:26:34

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