• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Management, Education, Information and Control >Image Matching Based on Election Campaign Algorithm
【24h】

Image Matching Based on Election Campaign Algorithm

机译：基于选举活动算法的图像匹配

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Image matching is widely used in image analysis and computer vision. Traditional Image matching method is to move the template in the reference image pixel by pixel, calculate their gray similarity. It has high computational complexity. If there is a rotation between the template and the reference map, the traditional matching method is difficult to achieve in real time. A method is proposed for matching rotated images based on gray scale feature in this paper, we use Election Campaign Algorithm detect the gray scale feature of points, then rotation invariant feature model, finally using rotation invariant feature model matching point set, image acquisition the translation and rotation parameters. The result of this method is accurate, and the computation complexity is small compared with the traditional correlation matching method, and it is easy to implement in real time.
机译：图像匹配广泛用于图像分析和计算机视觉。传统的图像匹配方法是通过像素将模板移动在参考图像像素中，计算它们的灰色相似度。它具有高计算复杂性。如果模板与参考图之间存在旋转，则传统的匹配方法难以实时实现。提出了一种方法，用于基于灰度特征匹配旋转图像，我们在本文中使用选举活动算法检测点的灰度特征，然后旋转不变特征模型，最后使用旋转不变特征模型匹配点集，图像获取了翻译和旋转参数。该方法的结果是准确的，与传统相关匹配方法相比，计算复杂性很小，并且易于实时实现。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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