专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US08290295B2 Multi-modal tone-mapping of images 有权
标题翻译：图像的多模式色调映射
公开(公告)号：US08290295B2
公开(公告)日：2012-10-16
申请号：US12396590
申请日：2009-03-03
申请人： Antonio Criminisi , Evgeny Salnikov , Toby Sharp
发明人： Antonio Criminisi , Evgeny Salnikov , Toby Sharp
IPC分类号： G06K9/38
CPC分类号： G06K9/38 , G06T5/009 , G06T5/40 , G06T2207/10032 , G06T2207/10081 , G06T2207/20208 , G06T2207/30004 , G06T2207/30181
摘要： A system for multi-modal mapping of images is described. Embodiments are described where the image mapping system is used for visualizing high dynamic range images such as medical images, satellite images, high dynamic range photographs and the like and also for compressing such images. In examples, high bit-depth images are tone-mapped for display on equipment of lower bit-depth without loss of detail. In embodiments, the image mapping system computes statistics describing an input image and fits a multi-modal model to those statistics efficiently. In embodiments, the multi-modal model is a Gaussian mixture model and a plurality of sigmoid functions corresponding to the multi-modal model are obtained. In an embodiment the sigmoid functions are added to form a tone-mapping function which is used to transform a high bit-depth image such as 16 or 12 bits per pixel to a low bit-depth image such as 8 bits per pixel.
摘要翻译：描述了用于图像的多模态映射的系统。描述实施例，其中图像映射系统用于可视化诸如医学图像，卫星图像，高动态范围照片等的高动态范围图像，并且还用于压缩这样的图像。在示例中，高位深图像被色调映射以便在较低位深度的设备上显示而不损失细节。在实施例中，图像映射系统计算描述输入图像的统计量，并将多模态模型有效地适应于这些统计。在实施例中，多模态模型是高斯混合模型，并且获得对应于多模态模型的多个S形函数。在一个实施例中，添加S形功能以形成色调映射功能，其用于将诸如每像素16或12位的高位深度图像变换为诸如每像素8位的低位深度图像。

42. 发明授权

US08103093B2 Image segmentation of foreground from background layers 有权
标题翻译：背景图层前景图像分割
公开(公告)号：US08103093B2
公开(公告)日：2012-01-24
申请号：US12689246
申请日：2010-01-19
申请人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
发明人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
IPC分类号： G06K9/34
CPC分类号： G06K9/00234 , G06K9/00261 , G06T7/11 , G06T7/143 , G06T7/162 , G06T7/174 , G06T7/254 , G06T2207/10016 , G06T2207/20121
摘要： Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut. Motion events in image sequences may be detected without explicit velocity computation.
摘要翻译：可以通过可以基于一个或多个因素（包括运动，颜色，对比度等）的分割过程来提供来自图像中的背景层的前景分割。颜色，运动和任选的对比度信息可以被概率地融合到准确和有效地推断前景和/或背景层。运动与非运动的可能性可以从训练数据自动学习，然后与对比度敏感色彩模型融合。然后可以通过诸如图形切割的优化算法有效地解决分割。可以在没有显式速度计算的情况下检测图像序列中的运动事件。

43. 发明申请

US20110188715A1 Automatic Identification of Image Features 审中-公开
标题翻译：图像特征的自动识别
公开(公告)号：US20110188715A1
公开(公告)日：2011-08-04
申请号：US12697785
申请日：2010-02-01
申请人： Jamie Daniel Joseph Shotton , Antonio Criminisi
发明人： Jamie Daniel Joseph Shotton , Antonio Criminisi
IPC分类号： G06K9/00
CPC分类号： G06K9/00 , G06K9/6282 , G06K2209/051 , G06T7/0012
摘要： Automatic identification of image features is described. In an embodiment, a device automatically identifies organs in a medical image using a decision forest formed of a plurality of distinct, trained decision trees. An image element from the image is applied to each of the trained decision trees to obtain a probability of the image element representing a predefined class of organ. The probabilities from each of the decision trees are aggregated and used to assign an organ classification to the image element. In another embodiment, a method of training a decision tree to identify features in an image is provided. For a selected node in the decision tree, a training image is analyzed at a plurality of locations offset from a selected image element, and one of the offsets is selected based on the results of the analysis and stored in association with the node.
摘要翻译：描述图像特征的自动识别。在一个实施例中，设备使用由多个不同的训练有素的决策树形成的决策树，自动识别医学图像中的器官。将来自图像的图像元素应用于每个经训练的决策树，以获得表示预定类别器官的图像元素的概率。来自每个决策树的概率被聚合并用于将分类器官分类给图像元素。在另一个实施例中，提供了一种训练决策树以识别图像中的特征的方法。对于决策树中的选定节点，在与所选择的图像元素偏移的多个位置处分析训练图像，并且基于分析的结果来选择偏移中的一个，并且与节点相关联地存储。

44. 发明申请

US20100226547A1 Multi-Modal Tone-Mapping of Images 有权
标题翻译：图像的多模态色调映射
公开(公告)号：US20100226547A1
公开(公告)日：2010-09-09
申请号：US12396590
申请日：2009-03-03
申请人： Antonio Criminisi , Evgeny Salnikov , Toby Sharp
发明人： Antonio Criminisi , Evgeny Salnikov , Toby Sharp
IPC分类号： G06K9/00
CPC分类号： G06K9/38 , G06T5/009 , G06T5/40 , G06T2207/10032 , G06T2207/10081 , G06T2207/20208 , G06T2207/30004 , G06T2207/30181
摘要： A system for multi-modal mapping of images is described. Embodiments are described where the image mapping system is used for visualizing high dynamic range images such as medical images, satellite images, high dynamic range photographs and the like and also for compressing such images. In examples, high bit-depth images are tone-mapped for display on equipment of lower bit-depth without loss of detail. In embodiments, the image mapping system computes statistics describing an input image and fits a multi-modal model to those statistics efficiently. In embodiments, the multi-modal model is a Gaussian mixture model and a plurality of sigmoid functions corresponding to the multi-modal model are obtained. In an embodiment the sigmoid functions are added to form a tone-mapping function which is used to transform a high bit-depth image such as 16 or 12 bits per pixel to a low bit-depth image such as 8 bits per pixel.
摘要翻译：描述了用于图像的多模态映射的系统。描述实施例，其中图像映射系统用于可视化诸如医学图像，卫星图像，高动态范围照片等的高动态范围图像，并且还用于压缩这样的图像。在示例中，高位深图像被色调映射以便在较低位深度的设备上显示而不损失细节。在实施例中，图像映射系统计算描述输入图像的统计量，并将多模态模型有效地适应于这些统计。在实施例中，多模态模型是高斯混合模型，并且获得对应于多模态模型的多个S形函数。在一个实施例中，添加S形功能以形成色调映射功能，其用于将诸如每像素16或12位的高位深度图像变换为诸如每像素8位的低位深度图像。

45. 发明申请

US20100119147A1 IMAGE SEGMENTATION 有权
标题翻译：图像分割
公开(公告)号：US20100119147A1
公开(公告)日：2010-05-13
申请号：US12689246
申请日：2010-01-19
申请人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
发明人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
IPC分类号： G06K9/34
CPC分类号： G06K9/00234 , G06K9/00261 , G06T7/11 , G06T7/143 , G06T7/162 , G06T7/174 , G06T7/254 , G06T2207/10016 , G06T2207/20121
摘要： Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut. Motion events in image sequences may be detected without explicit velocity computation.
摘要翻译：可以通过可以基于一个或多个因素（包括运动，颜色，对比度等）的分割过程来提供来自图像中的背景层的前景分割。颜色，运动和任选的对比度信息可以被概率地融合到准确和有效地推断前景和/或背景层。运动与非运动的可能性可以从训练数据自动学习，然后与对比度敏感色彩模型融合。然后可以通过诸如图形切割的优化算法有效地解决分割。可以在没有显式速度计算的情况下检测图像序列中的运动事件

46. 发明授权

US07676081B2 Image segmentation of foreground from background layers 有权
标题翻译：背景图层前景图像分割
公开(公告)号：US07676081B2
公开(公告)日：2010-03-09
申请号：US11252017
申请日：2005-10-17
申请人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
发明人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
IPC分类号： G06K9/34
CPC分类号： G06K9/00234 , G06K9/00261 , G06T7/11 , G06T7/143 , G06T7/162 , G06T7/174 , G06T7/254 , G06T2207/10016 , G06T2207/20121
摘要： Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut.
摘要翻译：可以通过可以基于一个或多个因素（包括运动，颜色，对比度等）的分割过程来提供来自图像中的背景层的前景分割。颜色，运动和任选的对比度信息可以被概率地融合到准确和有效地推断前景和/或背景层。运动与非运动的可能性可以从训练数据自动学习，然后与对比度敏感色彩模型融合。然后可以通过诸如图形切割的优化算法有效地解决分割。

47. 发明申请

US20060285747A1 Image segmentation 有权
标题翻译：图像分割
公开(公告)号：US20060285747A1
公开(公告)日：2006-12-21
申请号：US11252017
申请日：2005-10-17
申请人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
发明人： Andrew Blake , Antonio Criminisi , Geoffrey Cross , Vladimir Kolmogorov
IPC分类号： G06K9/34
CPC分类号： G06K9/00234 , G06K9/00261 , G06T7/11 , G06T7/143 , G06T7/162 , G06T7/174 , G06T7/254 , G06T2207/10016 , G06T2207/20121
摘要： Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut.
摘要翻译：可以通过可以基于一个或多个因素（包括运动，颜色，对比度等）的分割过程来提供来自图像中的背景层的前景分割。颜色，运动和任选的对比度信息可以被概率地融合到准确和有效地推断前景和/或背景层。运动与非运动的可能性可以从训练数据自动学习，然后与对比度敏感色彩模型融合。然后可以通过诸如图形切割的优化算法有效地解决分割。

48. 发明授权

US06987520B2 Image region filling by exemplar-based inpainting 失效
公开(公告)号：US06987520B2
公开(公告)日：2006-01-17
申请号：US10453404
申请日：2003-06-03
申请人： Antonio Criminisi , Patrick Perez , Kentaro Toyama , Michel Gangnet , Andrew Blake
发明人： Antonio Criminisi , Patrick Perez , Kentaro Toyama , Michel Gangnet , Andrew Blake
IPC分类号： G06K9/00
CPC分类号： G06T11/001 , G06T11/40
摘要： An example-based filling system identifies appropriate filling material to replace a destination region in an image and fills the destination region using this material, thereby alleviating or minimizing the amount of manual editing required to fill a destination region in image. Tiles of image data are borrowed from the proximity of the destination region or some other source to generate new image data to fill in the region. Destination regions may be designated by user input (e.g., selection of an image region by a user) or by other means (e.g., specification of a color or feature to be replaced). In addition, the order in which the destination region is filled by example tiles may be configured to emphasize the continuity of linear structures and composite textures using a type of isophote-driven image-sampling process.

49. 发明授权

US06968973B2 System and process for viewing and navigating through an interactive video tour 有权
公开(公告)号：US06968973B2
公开(公告)日：2005-11-29
申请号：US10449700
申请日：2003-05-31
申请人： Matthew T. Uyttendaele , Sing Bing Kang , Richard Szeliski , Antonio Criminisi
发明人： Matthew T. Uyttendaele , Sing Bing Kang , Richard Szeliski , Antonio Criminisi
IPC分类号： G06F17/00 , G06F17/30 , G07F11/00 , G09G5/00
CPC分类号： G06F17/30056 , G06F17/30855
摘要： A system and process for providing an interactive video tour of a tour site to a user is presented. In general, the system and process provides an image-based rendering system that enables users to explore remote real world locations, such as a house or a garden. The present approach is based directly on filming an environment, and then using image-based rendering techniques to replay the tour in an interactive manner. As such, the resulting experience is referred to as Interactive Video Tours. The experience is interactive in that the user can move freely along a path, choose between different directions of motion at branch points in the path, and look around in any direction. The user experience is additionally enhanced with multimedia elements such as overview maps, video textures, and sound.

50. 发明授权

US09519868B2 Semi-supervised random decision forests for machine learning using mahalanobis distance to identify geodesic paths 有权
标题翻译：使用马哈拉诺比斯距离的机器学习的半监督随机决策树来识别测地线
公开(公告)号：US09519868B2
公开(公告)日：2016-12-13
申请号：US13528876
申请日：2012-06-21
申请人： Antonio Criminisi , Jamie Daniel Joseph Shotton
发明人： Antonio Criminisi , Jamie Daniel Joseph Shotton
IPC分类号： G06N99/00 , G06N7/00 , G06N5/02
CPC分类号： G06N99/005 , G06N5/02 , G06N7/005
摘要： Semi-supervised random decision forests for machine learning are described, for example, for interactive image segmentation, medical image analysis, and many other applications. In examples, a random decision forest comprising a plurality of hierarchical data structures is trained using both unlabeled and labeled observations. In examples, a training objective is used which seeks to cluster the observations based on the labels and similarity of the observations. In an example, a transducer assigns labels to the unlabeled observations on the basis of the clusters and certainty information. In an example, an inducer forms a generic clustering function by counting examples of class labels at leaves of the trees in the forest. In an example, an active learning module identifies regions in a feature space from which the observations are drawn using the clusters and certainty information; new observations from the identified regions are used to train the random decision forest.
摘要翻译：描述了用于机器学习的半监督随机决策树，例如用于交互式图像分割，医学图像分析和许多其他应用。在示例中，使用未标记和标记的观察来训练包括多个分级数据结构的随机决策林。在实例中，使用了一个训练目标，其目的是根据观察结果的标签和相似性对观测进行聚类。在一个示例中，传感器基于集群和确定性信息将标签分配给未标记的观察。在一个例子中，诱导者通过计算森林中树的树叶上的类标签的示例来形成通用聚类函数。在一个示例中，主动学习模块识别特征空间中的区域，使用聚类和确定性信息从中绘制观察值; 来自确定地区的新观察用于训练随机决策林。

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