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

US07889941B2 Efficient segmentation of piecewise smooth images 有权
标题翻译：分段平滑图像的高效分割
公开(公告)号：US07889941B2
公开(公告)日：2011-02-15
申请号：US11696869
申请日：2007-04-05
申请人： Jerome Piovano , Mikael Rousson
发明人： Jerome Piovano , Mikael Rousson
IPC分类号： G06K9/44
CPC分类号： G06T7/149 , G06T7/11 , G06T2207/20161
摘要： A fast and robust segmentation model for piecewise smooth images is provided. Local statistics in an energy formulation are provided as a functional. The shape gradient of this new functional gives a contour evolution controlled by local averaging of image intensities inside and outside the contour. Fast computation is realized by expressing terms as the result of convolutions implemented via recursive filters. Results are similar to the general Mumford-Shah model but realized faster without having to solve a Poisson partial differential equation at each iteration. Examples are provided. A system to implement segmentation methods is also provided.
摘要翻译：提供了一种用于分段平滑图像的快速且鲁棒的分割模型。提供能量公式中的本地统计作为功能。这种新功能的形状梯度给出了通过轮廓内部和外部的图像强度的局部平均来控制的轮廓演化。通过表达术语作为通过递归滤波器实现的卷积的结果来实现快速计算。结果与一般的Mumford-Shah模型相似，但实现得更快，而无需在每次迭代中解决泊松偏微分方程。提供了实例。还提供了一种实现分割方法的系统。

2. 发明申请

US20080107351A1 EFFICIENT SEGMENTATION OF PIECEWISE SMOOTH IMAGES 有权
标题翻译：高分辨率图像的有效分割
公开(公告)号：US20080107351A1
公开(公告)日：2008-05-08
申请号：US11696869
申请日：2007-04-05
申请人： Jerome Piovano , Mikael Rousson
发明人： Jerome Piovano , Mikael Rousson
IPC分类号： G06K9/44
CPC分类号： G06T7/149 , G06T7/11 , G06T2207/20161
摘要： A fast and robust segmentation model for piecewise smooth images is provided. Local statistics in an energy formulation are provided as a functional. The shape gradient of this new functional gives a contour evolution controlled by local averaging of image intensities inside and outside the contour. Fast computation is realized by expressing terms as the result of convolutions implemented via recursive filters. Results are similar to the general Mumford-Shah model but realized faster without having to solve a Poisson partial differential equation at each iteration. Examples are provided. A system to implement segmentation methods is also provided.
摘要翻译：提供了一种用于分段平滑图像的快速且鲁棒的分割模型。提供能量公式中的本地统计作为功能。这种新功能的形状梯度给出了通过轮廓内部和外部的图像强度的局部平均来控制的轮廓演化。通过表达术语作为通过递归滤波器实现的卷积的结果来实现快速计算。结果与一般的Mumford-Shah模型相似，但实现得更快，而无需在每次迭代中解决泊松偏微分方程。提供了实例。还提供了一种实现分割方法的系统。

3. 发明申请

US20110081074A1 Method of Computing Global-to-Local Metrics for Recognition 有权
标题翻译：计算全球到本地度量标准的方法
公开(公告)号：US20110081074A1
公开(公告)日：2011-04-07
申请号：US12574717
申请日：2009-10-07
申请人： Mikael Rousson , Jan Erik Solem , Jerome Piovano
发明人： Mikael Rousson , Jan Erik Solem , Jerome Piovano
IPC分类号： G06K9/62
CPC分类号： G06K9/6215 , G06N99/005
摘要： A method of computing global-to-local metrics for recognition. Based on training examples with feature representations, the method automatically computes a local metric that varies over the space of feature representations to optimize discrimination and the performance of recognition systems.Given a set of points in an arbitrary features space, local metrics are learned in a hierarchical manner that give low distances between points of same class and high distances between points of different classes. Rather than considering a global metric, a class-based metric or a point-based metric, the proposed invention applies successive clustering to the data and associates a metric to each one of the clusters.
摘要翻译：计算用于识别的全局到本地度量的方法。基于具有特征表示的训练示例，该方法自动计算在特征表示空间上变化的局部度量，以优化识别系统的识别和性能。给定任意特征空间中的一组点，以分级方式学习局部度量，这样可以在不同类别的点之间提供相同类别的点和高距离之间的较低距离。所提出的发明不是考虑全局度量，基于类的度量或基于点的度量，而是将连续的聚类应用于数据并将度量与每个集群相关联。

4. 发明授权

US08488873B2 Method of computing global-to-local metrics for recognition 有权
标题翻译：计算用于识别的全局到本地度量的方法
公开(公告)号：US08488873B2
公开(公告)日：2013-07-16
申请号：US12574717
申请日：2009-10-07
申请人： Mikael Rousson , Jan Erik Solem , Jerome Piovano
发明人： Mikael Rousson , Jan Erik Solem , Jerome Piovano
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6215 , G06N99/005
摘要： A method of computing global-to-local metrics for recognition. Based on training examples with feature representations, the method automatically computes a local metric that varies over the space of feature representations to optimize discrimination and the performance of recognition systems.Given a set of points in an arbitrary features space, local metrics are learned in a hierarchical manner that give low distances between points of same class and high distances between points of different classes. Rather than considering a global metric, a class-based metric or a point-based metric, the proposed invention applies successive clustering to the data and associates a metric to each one of the clusters.
摘要翻译：计算用于识别的全局到本地度量的方法。基于具有特征表示的训练示例，该方法自动计算在特征表示空间上变化的局部度量，以优化识别系统的识别和性能。给定任意特征空间中的一组点，以分级方式学习局部度量，这样可以在不同类别的点之间提供相同类别的点和高距离之间的较低距离。所提出的发明不是考虑全局度量，基于类的度量或基于点的度量，而是将连续的聚类应用于数据并将度量与每个集群相关联。

5. 发明授权

US08131038B2 System and method for global-to-local shape matching for automatic liver segmentation in medical imaging 有权
标题翻译：用于医学成像中自动肝分割的全局到局部形状匹配的系统和方法
公开(公告)号：US08131038B2
公开(公告)日：2012-03-06
申请号：US12189276
申请日：2008-08-11
申请人： Kinda Anna Saddi , Mikael Rousson
发明人： Kinda Anna Saddi , Mikael Rousson
IPC分类号： G06K9/00
CPC分类号： G06K9/6209 , G06K2209/051 , G06T7/11 , G06T2207/20161 , G06T2207/30056
摘要： A method for automatically segmenting a liver in digital medical images includes providing a 3-dimensional (3D) digital image I and a set of N training shapes {φi}i=1, . . . , N for a liver trained from a set of manually segmented images, selecting a seed point to initialize the segmentation, representing a level set function φα(θx+h) of a liver boundary Γ in the image as ϕ α ⁡ ( x ) = ϕ 0 + ∑ i = 1 n ⁢ α i ⁢ V i ⁡ ( x ) , ⁢ where ⁢ ϕ 0 ⁡ ( x ) = 1 N ⁢ ∑ i = 1 N ⁢ ϕ i ⁡ ( x ) is a mean shape, {Vi(x)}i=1, . . . , n are eigenmodes where n
摘要翻译：用于在数字医学图像中自动分割肝脏的方法包括提供三维（3D）数字图像I和一组N个训练形状{＆phgr; i} i = 1。。。，用于从一组手动分割图像训练的肝脏，选择种子点来初始化分割，代表肝脏边界＆Ggr的水平集函数＆lt;α（＆amp; t; x + h）; 在形象与＆phis; α⁡（x）=＆phis; 0 +Σi = 1nαi V i⁡（x），where＆phis; 0⁡（x）= 1NΣi= 1 N＆phis; i⁡（x）是平均形状，{Vi（x）} i = 1，。。。，n是本征模式，其中n

6. 发明授权

US07773806B2 Efficient kernel density estimation of shape and intensity priors for level set segmentation 失效
标题翻译：用于水平集分割的形状和强度优先级的有效核密度估计
公开(公告)号：US07773806B2
公开(公告)日：2010-08-10
申请号：US11397040
申请日：2006-04-03
申请人： Daniel Cremers , Mikael Rousson
发明人： Daniel Cremers , Mikael Rousson
IPC分类号： G06K9/34 , G06K9/62
CPC分类号： G06K9/6207 , G06T7/12 , G06T7/143 , G06T7/149 , G06T2207/10132 , G06T2207/30004
摘要： Methods and systems for image segmentation are disclosed. A nonlinear statistical shape model of an image is integrated with a non-parametric intensity model to estimate characteristics of an image and create segmentations of an image based on Bayesian inference from characteristics of prior learned images based on the same models.
摘要翻译：公开了用于图像分割的方法和系统。图像的非线性统计形状模型与非参数强度模型集成以估计图像的特征，并且基于基于相同模型的先前学习图像的特征，基于贝叶斯推理创建图像的分割。

7. 发明申请

US20070127814A1 Method and system for histogram calculation using a graphics processing unit 有权
标题翻译：使用图形处理单元进行直方图计算的方法和系统
公开(公告)号：US20070127814A1
公开(公告)日：2007-06-07
申请号：US11594460
申请日：2006-11-08
申请人： Oliver Fluck , Shmuel Aharon , Mikael Rousson , Daniel Cremers
发明人： Oliver Fluck , Shmuel Aharon , Mikael Rousson , Daniel Cremers
IPC分类号： G06K9/34
CPC分类号： G06T1/20
摘要： A method for histogram calculation using a graphics processing unit (GPU), comprises storing image data in a two-dimensional (2D) texture domain; subdividing the domain into independent regions or tiles; calculating in parallel, in a GPU, a plurality of tile histograms, one for each tile; and summing up in parallel, in the GPU, the tile histograms so as to derive a final image histogram.
摘要翻译：一种使用图形处理单元（GPU）进行直方图计算的方法，包括将图像数据存储在二维（2D）纹理域中; 将域细分为独立区域或瓦片; 在GPU中并行计算多个瓦片直方图，每个瓦片一个; 并且在GPU中并行地并行地绘制瓦片直方图，以便导出最终图像直方图。

8. 发明申请

US20090052756A1 SYSTEM AND METHOD FOR GLOBAL-TO-LOCAL SHAPE MATCHING FOR AUTOMATIC LIVER SEGMENTATION IN MEDICAL IMAGING 有权
公开(公告)号：US20090052756A1
公开(公告)日：2009-02-26
申请号：US12189276
申请日：2008-08-11
申请人： Kinda Anna Saddi , Mikael Rousson
发明人： Kinda Anna Saddi , Mikael Rousson
IPC分类号： G06K9/34
CPC分类号： G06K9/6209 , G06K2209/051 , G06T7/11 , G06T2207/20161 , G06T2207/30056
摘要： A method for automatically segmenting a liver in digital medical images includes providing a 3-dimensional (3D) digital image I and a set of N training shapes {φi}i=1, . . . , N for a liver trained from a set of manually segmented images, selecting a seed point to initialize the segmentation, representing a level set function φα(θx+h) of a liver boundary Γ in the image as φ α  ( x ) = φ 0 + ∑ i = 1 n  α i  V i  ( x ) ,  where  φ 0  ( x ) = 1 N  ∑ i = 1 N  φ i  ( x ) is a mean shape, {Vi(x)}i=1, . . . , n are eigenmodes where n

9. 发明申请

US20070014462A1 Constrained surface evolutions for prostate and bladder segmentation in CT images 审中-公开
标题翻译： CT图像中前列腺和膀胱分割的约束表面演变
公开(公告)号：US20070014462A1
公开(公告)日：2007-01-18
申请号：US11452169
申请日：2006-06-13
申请人： Mikael Rousson , Ali Khamene , Mamadou Diallo
发明人： Mikael Rousson , Ali Khamene , Mamadou Diallo
IPC分类号： G06K9/00 , G06K9/34
CPC分类号： G06T7/149 , G06T7/11 , G06T7/143 , G06T2207/10081 , G06T2207/20101 , G06T2207/20161 , G06T2207/30004 , G06T2207/30081
摘要： A Bayesian formulation for coupled surface evolutions in level set methods and application to the segmentation of the prostate and the bladder in CT images are disclosed. A Bayesian framework imposing a shape constraint on the prostate is also disclosed, while coupling its shape extraction with that of the bladder. Constraining the segmentation process improves the extraction of both organs' shapes.
摘要翻译：公开了一种用于水平集方法中耦合表面演化的贝叶斯公式，用于CT图像中前列腺和膀胱分割的应用。还公开了对前列腺施加形状约束的贝叶斯框架，同时将其形状提取与膀胱的形状提取相结合。限制分割过程改善了两个器官形状的提取。

10. 发明授权

US07724954B2 Method and system for interactive image segmentation 有权
标题翻译：交互式图像分割的方法和系统
公开(公告)号：US07724954B2
公开(公告)日：2010-05-25
申请号：US11591767
申请日：2006-11-02
申请人： Oliver Fluck , Shmuel Aharon , Mikael Rousson , Daniel Cremers
发明人： Oliver Fluck , Shmuel Aharon , Mikael Rousson , Daniel Cremers
IPC分类号： G06K9/34
CPC分类号： G06K9/6226 , G06K9/38 , G06K9/6207
摘要： A method for segmentation of an image interactively with a user utilizes level set segmentation and includes selecting by user input respective areas of object and of background; initializing an embedding function implementing a segmentation boundary according to the selecting; computing intensity distributions and for the respective areas of object and of background; and performing repeatedly the steps below until convergence is reached: (a) evolving the embedding function, (b) recomputing the intensity distributions, and (c) checking for new user input and, if so: (d) updating labeling of the areas of object and background.
摘要翻译：用于与用户交互地分割图像的方法利用水平集分割，并且包括通过用户输入选择对象和背景的相应区域; 根据选择初始化实现分割边界的嵌入功能; 计算强度分布和对象和背景的各个区域; 并重复执行以下步骤直到达到融合：（a）演进嵌入功能，（b）重新计算强度分布，（c）检查新的用户输入，如果是：（d）更新标签的区域对象和背景。

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