专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08712186B2 Method for combining images and magnetic resonance scanner 有权
标题翻译：用于组合图像和磁共振扫描仪的方法
公开(公告)号：US08712186B2
公开(公告)日：2014-04-29
申请号：US12461993
申请日：2009-08-31
申请人： Benjamin Glocker , Nassir Navab , Christian Wachinger , Jochen Zeltner
发明人： Benjamin Glocker , Nassir Navab , Christian Wachinger , Jochen Zeltner
IPC分类号： G06K9/36 , G06K9/00
CPC分类号： G06T3/0068 , A61B5/055 , A61B6/5241 , G06T7/32 , G06T2207/10088 , G06T2207/30004
摘要： A method of combining a first image of a first region and a second image of a second region, having an overlapping region therebetween. The method including determining a superposed image as a weighted superposition of the first image and the second image in the overlap region, transforming the first image and the second image on the basis of a comparison of at least one of the first image and the second image with the determined superposed image; determining a further superposed image from the transformed first image and the transformed second image; and generating an overall image from the further superposed image when at least one convergence criterion is satisfied.
摘要翻译：一种组合第一区域的第一图像和第二区域的第二图像的方法，所述第二区域之间具有重叠区域。该方法包括：将重叠图像确定为重叠区域中的第一图像和第二图像的加权叠加，基于第一图像和第二图像中的至少一个的比较来变换第一图像和第二图像与确定的叠加图像; 从变换的第一图像和变换的第二图像确定另外的叠加图像; 以及当满足至少一个收敛标准时，从所述另外的叠加图像生成整体图像。

2. 发明申请

US20090046951A1 System and Method for Dense Image Registration Using Markov Random Fields and Efficient Linear Programming 有权
公开(公告)号：US20090046951A1
公开(公告)日：2009-02-19
申请号：US12169503
申请日：2008-07-08
申请人： Nikos Paragios , Benjamin Glocker , Nikos Komodakis
发明人： Nikos Paragios , Benjamin Glocker , Nikos Komodakis
IPC分类号： G06K9/32
CPC分类号： G06K9/6206 , G06K9/32 , G06T7/35 , G06T2207/30016
摘要： A method for registering digitized images using Markov Random Fields (MRFs) includes providing a source image f and a target image g, defining a deformation grid of T  ( x ) = x + ∑ p ∈ G  η  (  x - p  )  d u p , control points, defining a coordinate transformation as where x is a point on the source image, p is a position vector of control point p, dp is a displacement vector for each control point, up is a label for point p associated with displacement dp, and η( ) is a weighting function for the displacement vector, defining an MRF energy functional to be minimized by T as E t = 1  G   ∑ p ∈ G  V p t  ( u p ) + 1  E   ∑ p , q ∈ E  V pq  ( u p , u q ) , wherein |G| is a number of control points, |E| is a number of pairs of neighboring control points on a neighborhood system, t is an iteration counter, and associating the MRF with a primary linear program and solving the primary linear program using a fast primal-dual algorithm to yield a coordinate transformation that minimizes the energy functional.

3. 发明授权

US08126291B2 System and method for dense image registration using Markov Random Fields and efficient linear programming 有权
标题翻译：使用马尔科夫随机场进行密集图像配准的系统和方法以及高效的线性规划
公开(公告)号：US08126291B2
公开(公告)日：2012-02-28
申请号：US12169503
申请日：2008-07-08
申请人： Nikos Paragios , Benjamin Glocker , Nikos Komodakis
发明人： Nikos Paragios , Benjamin Glocker , Nikos Komodakis
IPC分类号： G06K9/32
CPC分类号： G06K9/6206 , G06K9/32 , G06T7/35 , G06T2207/30016
摘要： A method for registering digitized images using Markov Random Fields (MRFs) includes providing a source image f and a target image g, defining a deformation grid of control points, defining a coordinate transformation as T ⁡ ( x ) = x + ∑ p ∈ G ⁢ η ⁡ (  x - p  ) ⁢ d u p , where x is a point on the source image, p is a position vector of control point p, dp is a displacement vector for each control point, up is a label for point p associated with displacement dp, and η( ) is a weighting function for the displacement vector, defining an MRF energy functional to be minimized by T as E t = 1  G  ⁢ ∑ p ∈ G ⁢ V p t ⁡ ( u p ) + 1  E  ⁢ ∑ p , q ∈ E ⁢ V pq ⁡ ( u p , u q ) , wherein |G| is a number of control points, |E| is a number of pairs of neighboring control points on a neighborhood system, t is an iteration counter, and associating the MRF with a primary linear program and solving the primary linear program using a fast primal-dual algorithm to yield a coordinate transformation that minimizes the energy functional.
摘要翻译：使用马尔科夫随机场（MRFs）对数字化图像进行注册的方法包括提供源图像f和目标图像g，定义控制点的变形网格，定义坐标变换为T⁡（x）= x +Σp∈G ＆eegr; ⁡（x-p）dup，其中x是源图像上的点，p是控制点p的位置向量，dp是每个控制点的位移向量，up是与p相关联的点p的标签位移dp和＆eegr（（））是位移矢量的加权函数，定义了一个MRF能量函数，由T被最小化为E t = 1 G⁢Σp∈G V pt⁡（up）+ 1 E勉铺Σp，q∈E V pq⁡（up，uq），其中| G | 是一些控制点| E | 是邻域系统上的多对相邻控制点，t是迭代计数器，并且将MRF与主线性程序相关联，并且使用快速的原始 - 双重算法来求解主线性程序，以产生最小化的坐标变换能量功能。

4. 发明申请

US20100067762A1 Method for combining images and magnetic resonance scanner 有权
标题翻译：用于组合图像和磁共振扫描仪的方法
公开(公告)号：US20100067762A1
公开(公告)日：2010-03-18
申请号：US12461993
申请日：2009-08-31
申请人： Benjamin Glocker , Nassir Navab , Christian Wachinger , Jochen Zeltner
发明人： Benjamin Glocker , Nassir Navab , Christian Wachinger , Jochen Zeltner
IPC分类号： G06K9/00 , G01R33/48 , G06K9/36
CPC分类号： G06T3/0068 , A61B5/055 , A61B6/5241 , G06T7/32 , G06T2207/10088 , G06T2207/30004
摘要： A method is disclosed for combining a first image and a second image of an examination object, which images have an overlap region. A corresponding magnetic resonance scanner is also disclosed. In at least one embodiment, a superposed image is determined in the overlap region as a weighted superposition of the first image and the second image with a spatially variable weighting function. The first image and the second image are transformed on the basis of a comparison of the first image and/or the second image with the superposed image.
摘要翻译：公开了一种用于组合检查对象的第一图像和第二图像的方法，哪些图像具有重叠区域。还公开了相应的磁共振扫描器。在至少一个实施例中，在重叠区域中确定叠加图像作为具有空间可变加权函数的第一图像和第二图像的加权叠加。基于第一图像和/或第二图像与叠加图像的比较来变换第一图像和第二图像。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式