专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US08000527B2 Interactive image segmentation by precomputation 有权
标题翻译：通过预先计算的交互式图像分割
公开(公告)号：US08000527B2
公开(公告)日：2011-08-16
申请号：US11949832
申请日：2007-12-04
申请人： Leo Grady , Ali Kemal Sinop
发明人： Leo Grady , Ali Kemal Sinop
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/6224 , G06T7/11 , G06T2207/20101
摘要： A method for interactive image segmentation includes receiving an image to be segmented, performing an offline computation of eigenvectors of a Laplacian of the image without using seed points, receiving seed points, and performing an online segmentation taking the seed points and the eigenvectors of the Laplacian as input and outputting a partition of the image.
摘要翻译：一种用于交互式图像分割的方法包括接收待分割的图像，对图像的拉普拉斯算子的特征向量进行离线计算，而不使用种子点，接收种子点，并执行在线分割，获取拉普拉斯算子的种子点和特征向量作为输入并输出图像的分区。

32. 发明申请

US20100104186A1 SYSTEM AND METHOD FOR IMAGE SEGMENTATION USING CONTINUOUS VALUED MRFS WITH NORMED PAIRWISE DISTRIBUTIONS 有权
标题翻译：使用连续有价值MRFS与正态分布分布的图像分割的系统和方法
公开(公告)号：US20100104186A1
公开(公告)日：2010-04-29
申请号：US12558649
申请日：2009-09-14
申请人： Leo Grady , Dheeraj Singaraju , René Vidal
发明人： Leo Grady , Dheeraj Singaraju , René Vidal
IPC分类号： G06K9/34
CPC分类号： G06K9/469 , G06K9/6297 , G06T7/11 , G06T7/143 , G06T7/162 , G06T7/194 , G06T2207/10032 , G06T2207/10061 , G06T2207/10072 , G06T2207/10132 , G06T2207/20044 , G06T2207/20156 , G06T2207/30004
摘要： A method for segmenting a digital image includes initializing object and background seed nodes in an image, where the image is represented as a graph G=(V, E) whose nodes iεV correspond to image points and whose edges eεE connect adjacent points, where set M⊂V contains locations of nodes marked as seeds, set U⊂V contains locations of unmarked nodes, set O⊂M contains locations of object seed nodes, and set B⊂M contains locations of background seed nodes, assigning to each seed node a membership value such that ∀iεO,xi=1 and ∀iεB, xi=0, where each node iεV is associated with a membership xiε[0,1], and finding a membership vector xε, whose ith entry is given by xi that minimizes E p  ( x ) = ∑ eij ∈ E  w ij   x i - x j  pij , where each edge eijεE connecting nodes i and j in V is associated with a weight wij and an exponent pij, and ∀eijεE,1≦pij
摘要翻译：用于分割数字图像的方法包括：对图像中的对象和背景种子节点进行初始化，其中图像被表示为图形G =（V，E），其节点i＆egr; V对应于图像点，并且其边缘e连接相邻点，其中设置M⊂V包含标记为种子的节点的位置，集合U⊂V包含未标记节点的位置，集合O⊂M包含对象种子节点的位置，并且集合B⊂M包含背景种子节点的位置，分配给每个种子节点是隶属度值，使得∀i＆egr; O，xi = 1和∀i＆egr; B，xi = 0，其中每个节点i＆egr; V与隶属度xi＆egr [0,1]相关联，并且找到隶属向量 x＆egr;其第i个条目由xi给出，其最小化E p（x）=Σeij∈E，w ij，xi-xj沛pij，其中V中的每个边连接节点i和j与一个权重wij和一个指数pij，∀eij＆egr; E，1＆nlE; pij <∞，如果i＆egr; O和xi = 0，如果i＆egr; B，则xi = 1。

33. 发明授权

US07672511B2 System and method for lattice-preserving multigrid method for image segmentation and filtering 有权
标题翻译：用于图像分割和滤波的网格多维网格方法的系统和方法
公开(公告)号：US07672511B2
公开(公告)日：2010-03-02
申请号：US11472006
申请日：2006-06-21
申请人： Leo Grady
发明人： Leo Grady
IPC分类号： G06K9/34
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/10072 , G06T2207/20016
摘要： A method for segmenting a digitized image includes providing a digitized image comprising a plurality of intensities corresponding to a domain of points on an N-dimensional grid, defining a weight between each pair of adjacent points in the image based on the intensity difference of each said point pair, marking a subset of points in said image wherein each marked point is marked with one of a plurality of labels, determining the probability that an unmarked point should be marked with one of said plurality of labels using a multigrid method that uses a restriction operator to map said provided image to a coarse-level gird, and a prolongation operator to map said coarse-level image back to a fine-level grid, wherein said restriction operator is an adjoint of said prolongation operator, and wherein a fine-level segmentation is a prolongation of a coarse level segmentation.
摘要翻译：一种用于分割数字化图像的方法包括提供数字化图像，该数字化图像包括对应于N维网格上的点的区域的多个强度，基于每个所述图像的强度差定义图像中每对相邻点之间的权重点对，标记所述图像中的点的子集，其中每个标记点用多个标签中的一个标记，使用使用限制的多网格方法确定未标记点应该用所述多个标签中的一个标记的概率操作者将所述提供的图像映射到粗级网格，以及延长操作符，以将所述粗略级图像映射回精细级网格，其中所述限制操作符是所述延长操作符的伴随，并且其中精细级别分割是粗略级别分割的延长。

34. 发明申请

US20090097727A1 3D General Lesion Segmentation In CT 有权
标题翻译： CT中的三维常规病变分割
公开(公告)号：US20090097727A1
公开(公告)日：2009-04-16
申请号：US12128676
申请日：2008-05-29
申请人： Marie-Pierre Jolly , Leo Grady
发明人： Marie-Pierre Jolly , Leo Grady
IPC分类号： G06K9/80
CPC分类号： A61B6/466 , G06T7/12 , G06T7/143 , G06T7/181 , G06T2207/10081 , G06T2207/20076 , G06T2207/20096 , G06T2207/20101 , G06T2207/30096
摘要： A general purpose method to segment any kind of lesions in 3D images is provided. Based on a click or a stroke inside the lesion from the user, a distribution of intensity level properties is learned. The random walker segmentation method combines multiple 2D segmentation results to produce the final 3D segmentation of the lesion.
摘要翻译：提供了一种在3D图像中分割任何种类的病变的通用方法。基于来自用户的病变内的点击或中风，学习强度水平特性的分布。随机Walker分割方法组合了多个2D分割结果，以产生损伤的最终3D分割。

35. 发明申请

US20080260247A1 INTERACTIVE IMAGE SEGMENTATION BY PRECOMPUTATION 有权
标题翻译：通过预处理交互式图像分割
公开(公告)号：US20080260247A1
公开(公告)日：2008-10-23
申请号：US11949832
申请日：2007-12-04
申请人： Leo Grady , Ali Kemal Sinop
发明人： Leo Grady , Ali Kemal Sinop
IPC分类号： G06K9/34
CPC分类号： G06K9/342 , G06K9/6224 , G06T7/11 , G06T2207/20101
摘要： A method for interactive image segmentation includes receiving an image to be segmented, performing an offline computation of eigenvectors of a Laplacian of the image without using seed points, receiving seed points, and performing an online segmentation taking the seed points and the eigenvectors of the Laplacian as input and outputting a partition of the image.
摘要翻译：一种用于交互式图像分割的方法包括接收待分割的图像，对图像的拉普拉斯算子的特征向量进行离线计算，而不使用种子点，接收种子点，并执行在线分割，获取拉普拉斯算子的种子点和特征向量作为输入并输出图像的分区。

36. 发明申请

US20080056577A1 Seed segmentation using L-infinity minimization 有权
标题翻译：使用L-infinity最小化的种子分割
公开(公告)号：US20080056577A1
公开(公告)日：2008-03-06
申请号：US11789747
申请日：2007-04-25
申请人： Leo Grady , Ali Kemal Sinop
发明人： Leo Grady , Ali Kemal Sinop
IPC分类号： G06K9/34
CPC分类号： G06K9/469 , G06K9/6224 , G06T7/11 , G06T7/143 , G06T7/162 , G06T2207/30101
摘要： A computer readable medium embodying instructions executable by a processor to perform a method for seeded image segmentation using l∞ minimization, the method including providing an image comprising a set of pixels, wherein a foreground seed label is given for at least one pixel of the image and a background seed label is given for at least another pixel of the image, determining an affinity function for every pair of neighbor pixels, solving the l∞ minimization, which assigns a probability to each pixel, labeling each pixel as foreground pixel or background pixel according to a threshold of the probability, and outputting the image including the segmentation labels.
摘要翻译：一种计算机可读介质，其包含可由处理器执行的指令，以执行使用最小化的种子图像分割的方法，所述方法包括提供包括一组像素的图像，其中给出前景种子标签为图像的至少另一像素给出图像的至少一个像素和背景种子标签，确定每对相邻像素的亲和度函数，求解最小化，其分配一个每个像素的概率，根据概率的阈值将每个像素标记为前景像素或背景像素，并且输出包括分割标签的图像。

37. 发明申请

US20070086647A1 System and method for 3D volume segmentation using exact minimal surfaces given a boundary 有权
标题翻译：给定边界的精确最小面的3D体积分割的系统和方法
公开(公告)号：US20070086647A1
公开(公告)日：2007-04-19
申请号：US11511524
申请日：2006-08-28
申请人： Leo Grady
发明人： Leo Grady
IPC分类号： G06K9/00 , G06K9/34
CPC分类号： G06T7/162 , G06T7/12 , G06T2207/10081 , G06T2207/10108 , G06T2207/30004
摘要： A method for 3D volume segmentation in digitized medical images includes providing a digitized medical image defined on an N-dimensional lattice, obtaining an oriented closed 2-dimensional contour on one or more 2-dimensional slices from said image, defining face weights w from said image intensities by forming a dual lattice of said image lattice, minimizing summed over all faces subject to the constraint Bz=r wherein vector z is an indicator vector indicating whether a face is present in a minimum-weight surface, vector r is an indicator vector of said 2-D contour, and wherein B is an edge-face incidence matrix, and segmenting said 3-D image into distinct regions separated by the minimum-weight surface indicated by said vector z.
摘要翻译：一种用于数字化医学图像中的3D体积分割的方法包括提供在N维格子上定义的数字化医学图像，从所述图像获得一个或多个二维切片上的定向闭合2维轮廓，从所述图像定义面部加权w 通过形成所述图像晶格的双晶格的图像强度，对受约束Bz = r的所有面进行最小化求和，其中矢量z是指示面部是否存在于最小权重表面中的指示矢量，向量r是指示矢量的所述2-D轮廓，并且其中B是边缘面入射矩阵，并且将所述3-D图像分割成由所述向量z所指示的最小权重表面分隔的不同区域。

38. 发明申请

US20070047810A1 System and method for lattice-preserving multigrid method for image segmentation and filtering 有权
标题翻译：用于图像分割和滤波的网格多维网格方法的系统和方法
公开(公告)号：US20070047810A1
公开(公告)日：2007-03-01
申请号：US11472006
申请日：2006-06-21
申请人： Leo Grady
发明人： Leo Grady
IPC分类号： G06K9/00
CPC分类号： G06T7/162 , G06T7/11 , G06T2207/10072 , G06T2207/20016
摘要： A method for segmenting a digitized image includes providing a digitized image comprising a plurality of intensities corresponding to a domain of points on an N-dimensional grid, defining a weight between each pair of adjacent points in the image based on the intensity difference of each said point pair, marking a subset of points in said image wherein each marked point is marked with one of a plurality of labels, determining the probability that an unmarked point should be marked with one of said plurality of labels using a multigrid method that uses a restriction operator to map said provided image to a coarse-level gird, and a prolongation operator to map said coarse-level image back to a fine-level grid, wherein said restriction operator is an adjoint of said prolongation operator, and wherein a fine-level segmentation is a prolongation of a coarse level segmentation.
摘要翻译：一种用于分割数字化图像的方法包括提供数字化图像，该数字化图像包括对应于N维网格上的点的区域的多个强度，基于每个所述图像的强度差定义图像中每对相邻点之间的权重点对，标记所述图像中的点的子集，其中每个标记点用多个标签中的一个标记，使用使用限制的多网格方法确定未标记点应该用所述多个标签中的一个标记的概率操作者将所述提供的图像映射到粗级网格，以及延长操作符，以将所述粗略级图像映射回精细级网格，其中所述限制操作符是所述延长操作符的伴随，并且其中精细级别分割是粗略级别分割的延长。

39. 发明申请

US20070025616A1 Editing of presegemented images/volumes with the multilabel random walker or graph cut segmentations 失效
标题翻译：使用多标签随机步行器或图形剪切分割编辑预处理的图像/卷
公开(公告)号：US20070025616A1
公开(公告)日：2007-02-01
申请号：US11493315
申请日：2006-07-26
申请人： Leo Grady , Gareth Funka-Lea
发明人： Leo Grady , Gareth Funka-Lea
IPC分类号： G06K9/34
CPC分类号： G06K9/03 , G06K9/342 , G06T7/11 , G06T7/143 , G06T7/162 , G06T2207/10072 , G06T2207/20101 , G06T2207/30004
摘要： Presegmentation or prior, pre-existing segmentation of an object obtained through other means will be presented for interactive editing of a segmented object in an image or volume. Prior segmentation will be seamlessly combined with graph cuts or the random walker methods. Editing of the presegmentation is possible, while maintaining the important property of both methods that an arbitrary segmentation may be achieved with enough interaction.
摘要翻译：将呈现通过其他方式获得的对象的预分割或先前存在的分割，用于图像或体积中的分段对象的交互式编辑。先前的分割将与图形切割或随机Walker方法无缝结合。编辑预分割是可能的，同时保持两种方法的重要性质，可以通过足够的交互实现任意分割。

40. 发明申请

US20060104513A1 GPU accelerated multi-label digital photo and video editing 有权
公开(公告)号：US20060104513A1
公开(公告)日：2006-05-18
申请号：US11242549
申请日：2005-10-03
申请人： Shmuel Aharon , Leo Grady , Thomas Schiwietz
发明人： Shmuel Aharon , Leo Grady , Thomas Schiwietz
IPC分类号： G06K9/34
CPC分类号： G06T7/143 , G06T7/11 , G06T7/194 , G06T2207/10016 , G06T2207/20101
摘要： A method and system for segmenting an object in a digital image are disclosed. A user selects at least one foreground pixel or node located within the object and at least one background pixel or node located outside of the object. A random walk algorithm is performed to determine the boundaries of the object in the image. In a first step of the algorithm, a plurality of coefficients is determined. Next, a system of linear equations that include the plurality of coefficients are solved to determine a boundary of the object. The processing is performed by a graphics processing unit. The processing can be performed using the near-Euclidean LUV color space or a Lab color space. It is also preferred to use a Z-buffer in the graphics processing unit during processing. The object, once identified, can be further processed, for example, by being extracted from the image based on the determined boundary.

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