首页> 外文会议>International conference on image processing, computer vision, pattern recognition;IPCV'08 >A Hybrid Registration Approach for Matching Genomic Structures in Multimodal Microscopic Images of Living Cells
【24h】

A Hybrid Registration Approach for Matching Genomic Structures in Multimodal Microscopic Images of Living Cells

机译:一种用于生物细胞多峰显微图像中基因组结构匹配的混合配准方法

获取原文

摘要

A new registration approach is presented for matching genomic structures in time lapse microscopy images of living cells which have been labeled with fluorescent protein. Registration of microscopic images is a difficult problem due to signal weakness and low resolution of structures of interest. With this in mind we have developed a hybrid approach that matches two time point images by deformation based on corresponding control points from two different microscopic modalities. This approach is robust because it can also be initialized by the point correspondences established by our previously published method [2-3]. We discuss several choices for the deformation technique and present experimental results which rank them on accuracy as evaluated by an expert user.
机译:提出了一种新的配准方法,用于匹配已用荧光蛋白标记的活细胞的延时显微镜图像中的基因组结构。由于信号弱和目标结构的分辨率低,显微图像的配准是一个难题。考虑到这一点,我们开发了一种混合方法,该方法可根据来自两个不同微观模态的相应控制点,通过变形匹配两个时间点图像。这种方法很健壮,因为它也可以通过我们先前发布的方法[2-3]建立的点对应关系进行初始化。我们讨论了变形技术的几种选择,并给出了实验结果,这些结果根据专家用户的评估在准确性上进行了排名。

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