-
1.发明申请公开(公告)号：US20130129233A1
公开(公告)日：2013-05-23
申请号：US12956996
申请日：2010-11-30
IPC分类号： G06K9/74
CPC分类号： G06T11/60 , G06K9/209 , G06K9/40 , G06K9/4647 , G06K9/6278
摘要： A blur classification module may compute the probability that a given pixel in a digital image was blurred using a given two-dimensional blur kernel, and may store the computed probability in a blur classification probability matrix that stores probability values for all combinations of image pixels and the blur kernels in a set of likely blur kernels. Computing these probabilities may include computing a frequency power spectrum for windows into the digital image and/or for the likely blur kernels. The blur classification module may generate a coherent mapping between pixels of the digital image and respective blur states, or may perform a segmentation of the image into blurry and sharp regions, dependent on values stored in the matrix. Input image data may be pre-processed. Blur classification results may be employed in image editing operations to automatically target image subjects or background regions, or to estimate the depth of image elements.
摘要翻译： 模糊分类模块可以使用给定的二维模糊核心来计算数字图像中的给定像素模糊的概率，并且可以将所计算的概率存储在模糊分类概率矩阵中，所述模糊分类概率矩阵存储图像像素的所有组合的概率值， 一组可能的模糊内核中的模糊内核。 计算这些概率可以包括计算窗口进入数字图像和/或可能的模糊内核的频率功率谱。 模糊分类模块可以产生数字图像的像素和相应的模糊状态之间的相干映射，或者可以根据存储在矩阵中的值来执行图像到模糊和锐利区域的分割。 可以预处理输入图像数据。 可以在图像编辑操作中使用模糊分类结果来自动对象图像对象或背景区域，或者估计图像元素的深度。
-
2.发明授权公开(公告)号：US08503801B2
公开(公告)日：2013-08-06
申请号：US12956996
申请日：2010-11-30
IPC分类号： G06K9/62
CPC分类号： G06T11/60 , G06K9/209 , G06K9/40 , G06K9/4647 , G06K9/6278
摘要： A blur classification module may compute the probability that a given pixel in a digital image was blurred using a given two-dimensional blur kernel, and may store the computed probability in a blur classification probability matrix that stores probability values for all combinations of image pixels and the blur kernels in a set of likely blur kernels. Computing these probabilities may include computing a frequency power spectrum for windows into the digital image and/or for the likely blur kernels. The blur classification module may generate a coherent mapping between pixels of the digital image and respective blur states, or may perform a segmentation of the image into blurry and sharp regions, dependent on values stored in the matrix. Input image data may be pre-processed. Blur classification results may be employed in image editing operations to automatically target image subjects or background regions, or to estimate the depth of image elements.
摘要翻译： 模糊分类模块可以使用给定的二维模糊核心来计算数字图像中的给定像素模糊的概率，并且可以将所计算的概率存储在模糊分类概率矩阵中，所述模糊分类概率矩阵存储图像像素的所有组合的概率值， 一组可能的模糊内核中的模糊内核。 计算这些概率可以包括计算窗口进入数字图像和/或可能的模糊内核的频率功率谱。 模糊分类模块可以产生数字图像的像素和相应的模糊状态之间的相干映射，或者可以根据存储在矩阵中的值来执行图像到模糊和锐利区域的分割。 可以预处理输入图像数据。 可以在图像编辑操作中使用模糊分类结果来自动对象图像对象或背景区域，或者估计图像元素的深度。
-
公开(公告)号：US20110194741A1
公开(公告)日：2011-08-11
申请号：US13122976
申请日：2009-09-30
申请人： Ahmet Ekin , Jingnan Wang
发明人： Ahmet Ekin , Jingnan Wang
CPC分类号： A61B5/00 , A61B5/055 , A61B5/4088 , A61B6/00 , A61B6/501 , A61B6/5217 , G06T7/0012 , G06T7/41 , G06T7/62 , G06T2200/36 , G06T2207/10072 , G06T2207/30016
摘要： A system for analyzing a brain ventricle (8) is described. The system comprises an edge detector (52) for identifying an edge point (17) on an edge of the brain ventricle. Also, a length measurer (53) is provided for establishing a length measure of a path (10) starting from a central point (5) of the brain ventricle and terminating at the edge point (17). The edge detector (52) is arranged for detecting an edge point at an end of a lobe of the brain ventricle, the length measure corresponding to an extent of the lobe.
摘要翻译： 描述了用于分析脑室（8）的系统。 该系统包括用于识别脑室边缘上的边缘点（17）的边缘检测器（52）。 另外，长度测量器（53）用于建立从脑室的中心点（5）开始并终止于边缘点（17）的路径（10）的长度测量。 边缘检测器（52）被布置用于检测在脑室的叶的末端处的边缘点，该长度测量对应于叶的程度。
-
-
搜索结果
3 条记录 (耗时 0.018 秒)
