专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

61. 发明授权

US07996343B2 Classification via semi-riemannian spaces 有权
标题翻译：通过半黎曼空间分类
公开(公告)号：US07996343B2
公开(公告)日：2011-08-09
申请号：US12242421
申请日：2008-09-30
申请人： Deli Zhao , Zhouchen Lin , Xiaoou Tang
发明人： Deli Zhao , Zhouchen Lin , Xiaoou Tang
IPC分类号： G06F11/00
CPC分类号： G06K9/6234 , G06K9/6252
摘要： Described is using semi-Riemannian geometry in supervised learning to learn a discriminant subspace for classification, e.g., labeled samples are used to learn the geometry of a semi-Riemannian submanifold. For a given sample, the K nearest classes of that sample are determined, along with the nearest samples that are in other classes, and the nearest samples in that sample's same class. The distances between these samples are computed, and used in computing a metric matrix. The metric matrix is used to compute a projection matrix that corresponds to the discriminant subspace. In online classification, as a new sample is received, it is projected into a feature space by use of the projection matrix and classified accordingly.
摘要翻译：描述了在监督学习中使用半黎曼几何学习学习用于分类的判别子空间，例如，标记的样本用于学习半黎曼子流形歧管的几何形状。对于给定的样本，该样本的K个最近类别以及其他类别中最近的样本以及该样本同一类中最近的样本进行确定。计算这些样本之间的距离，并用于计算度量矩阵。度量矩阵用于计算与判别子空间对应的投影矩阵。在线分类中，作为收到的新样本，通过使用投影矩阵将其投影到特征空间中并进行分类。

62. 发明授权

US07974498B2 Super-resolution in periodic and aperiodic pixel imaging 有权
标题翻译：周期和非周期像素成像中的超分辨率
公开(公告)号：US07974498B2
公开(公告)日：2011-07-05
申请号：US11835625
申请日：2007-08-08
申请人： Moshe Ben-Ezra , Zhouchen Lin , Bennett Wilburn
发明人： Moshe Ben-Ezra , Zhouchen Lin , Bennett Wilburn
IPC分类号： G06K9/32
CPC分类号： H04N5/23232 , G06T3/4053 , H04N5/335
摘要： A super-resolution algorithm that explicitly and exactly models the detector pixel shape, size, location, and gaps for periodic and aperiodic tilings. The algorithm projects the low-resolution input image into high-resolution space to model the actual shapes and/or gaps of the detector pixels. By using an aperiodic pixel layout such as a Penrose tiling significant improvements in super-resolution results can be obtained. An error back-projection super-resolution algorithm makes use of the exact detector model in its back projection operator for better accuracy. Theoretically, the aperiodic detector can be based on CCD (charge-coupled device) technology, and/or more practically, CMOS (complimentary metal oxide semiconductor) technology, for example.
摘要翻译：一种超分辨率算法，用于明确和精确地建模周期性和非周期性的检测器像素形状，大小，位置和间隙。该算法将低分辨率输入图像投影到高分辨率空间中以对检测器像素的实际形状和/或间隙进行建模。通过使用非周期像素布局，如彭罗斯平铺，可以获得超分辨率结果的显着改进。误差反投影超分辨率算法利用其反投影算子中的精确检测器模型更好的精度。理论上，非周期检测器可以基于例如CCD（电荷耦合器件）技术和/或更实际的CMOS（互补金属氧化物半导体）技术。

63. 发明申请

US20100067800A1 MULTI-CLASS TRANSFORM FOR DISCRIMINANT SUBSPACE ANALYSIS 审中-公开
标题翻译：用于歧视人员分析的多级变换
公开(公告)号：US20100067800A1
公开(公告)日：2010-03-18
申请号：US12212572
申请日：2008-09-17
申请人： Zhouchen Lin , Wenming Zheng
发明人： Zhouchen Lin , Wenming Zheng
IPC分类号： G06K9/46
CPC分类号： G06K9/6234
摘要： A multi-class discriminant subspace analysis technique is described that improves the discriminant power of Linear Discriminant Analysis (LDA). In one embodiment of the multi-class discriminant subspace analysis technique, multi-class feature selection occurs as follows. A data set containing multiple classes of features is input. Discriminative information for the data set is determined from the differences of class means and the differences in class scatter matrices by computing an optimal orthogonal matrix that approximately simultaneously diagonalizes autocorrelation matrices for all classes in the data set. The discriminative information is used to extract features for different classes of features from the data set.
摘要翻译：描述了一种多级判别子空间分析技术，提高了线性判别分析（Linear Discriminant Analysis，LDA）的判别力。在多级判别子空间分析技术的一个实施例中，多类特征选择如下进行。输入包含多个要素类的数据集。通过计算数据集中所有类别的自相关矩阵大致同时对角化的最佳正交矩阵，根据类别的差异和类散布矩阵的差异来确定数据集的辨别信息。识别信息用于从数据集中提取不同类别的特征的特征。

64. 发明申请

US20090219287A1 Modeling and rendering of heterogeneous translucent materials using the diffusion equation 有权
标题翻译：使用扩散方程建模和渲染异质半透明材料
公开(公告)号：US20090219287A1
公开(公告)日：2009-09-03
申请号：US12072925
申请日：2008-02-29
申请人： Jiaping Wang , Xin Tong , Stephen S. Lin , Baining Guo , Heung-Yeung Shum , Zhouchen Lin
发明人： Jiaping Wang , Xin Tong , Stephen S. Lin , Baining Guo , Heung-Yeung Shum , Zhouchen Lin
IPC分类号： G06T15/50 , G06F3/048
CPC分类号： G06T15/506 , G01N21/47 , G01N21/4738 , G06T15/50
摘要： An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.
摘要翻译：一种示例性方法包括提供用于异质半透明材料的照明物理样品的图像数据，部分地基于扩散方程来确定材料的一种或多种材料性质，其中材料性质之一是用于辐射的扩散的扩散系数材料，并且其中确定包括扩散系数的正则化术语，将一个或多个材料属性映射到虚拟对象体积，将虚拟照明条件分配给虚拟对象体积，以及使用虚拟照明条件将虚拟对象体积呈现为虚拟物体体积扩散方程组的边界条件。还公开了其它方法，装置和系统。

65. 发明申请

US20090097772A1 Laplacian Principal Components Analysis (LPCA) 有权
标题翻译：拉普拉斯主成分分析（LPCA）
公开(公告)号：US20090097772A1
公开(公告)日：2009-04-16
申请号：US11871764
申请日：2007-10-12
申请人： Deli Zhao , Zhouchen Lin , Xiaoou Tang
发明人： Deli Zhao , Zhouchen Lin , Xiaoou Tang
IPC分类号： G06K9/40
CPC分类号： G06K9/6248
摘要： Systems and methods perform Laplacian Principal Components Analysis (LPCA). In one implementation, an exemplary system receives multidimensional data and reduces dimensionality of the data by locally optimizing a scatter of each local sample of the data. The optimization includes summing weighted distances between low dimensional representations of the data and a mean. The weights of the distances can be determined by a coding length of each local data sample. The system can globally align the locally optimized weighted scatters of the local samples and provide a global projection matrix. The LPCA improves performance of such applications as face recognition and manifold learning.
摘要翻译：系统和方法执行拉普拉斯主成分分析（LPCA）。在一个实现中，示例性系统通过局部优化数据的每个局部采样的散射来接收多维数据并且降低数据的维度。优化包括对数据的低维表示和平均值之间的加权距离求和。距离的权重可以通过每个本地数据样本的编码长度来确定。该系统可以对局部采样的局部优化加权散射进行全局对齐，并提供全局投影矩阵。 LPCA可以改善诸如面部识别和歧管学习等应用的性能。

66. 发明授权

US09122563B2 Computing minimal polynomials 有权
标题翻译：计算最小多项式
公开(公告)号：US09122563B2
公开(公告)日：2015-09-01
申请号：US12422315
申请日：2009-04-13
申请人： Xu Yang , Zhouchen Lin , Sijun Liu , Tianjun Ye , Dongmei Zhang
发明人： Xu Yang , Zhouchen Lin , Sijun Liu , Tianjun Ye , Dongmei Zhang
IPC分类号： G06F7/38 , G06F7/72 , G06F7/16 , G06F7/12
CPC分类号： G06F7/724 , G06F7/12 , G06F7/16
摘要： Described is a technology, such as implemented in a computational software program, by which a minimal polynomial is efficiently determined for a radical expression over the ring Z of integer numbers or the ring Q of rational numbers. The levels of the radical are grouped into a level permutation group that is used to find a level permutation set. An annihilation polynomial is found based upon the level permutation set. The annihilation polynomial is factored, and a selection mechanism selects the minimal polynomial based upon the annihilation polynomial's factors.
摘要翻译：描述了一种技术，例如在计算软件程序中实现的技术，通过该技术，对于整数的环Z或有理数的环Q，对于根基表达式有效地确定最小多项式。激进的级别被分组成用于找到级别置换集合的级别置换组。湮没多项式是基于层次排列集合找到的。湮灭多项式被考虑，选择机制根据湮灭多项式的因素选择最小多项式。

67. 发明授权

US08243071B2 Modeling and rendering of heterogeneous translucent materials using the diffusion equation 有权
标题翻译：使用扩散方程建模和渲染异质半透明材料
公开(公告)号：US08243071B2
公开(公告)日：2012-08-14
申请号：US12072925
申请日：2008-02-29
申请人： Jiaping Wang , Xin Tong , Stephen S. Lin , Baining Guo , Heung-Yeung Shum , Zhouchen Lin
发明人： Jiaping Wang , Xin Tong , Stephen S. Lin , Baining Guo , Heung-Yeung Shum , Zhouchen Lin
IPC分类号： G06T15/00 , G06T15/60 , G06K9/00
CPC分类号： G06T15/506 , G01N21/47 , G01N21/4738 , G06T15/50
摘要： An exemplary method includes providing image data for an illuminated physical sample of a heterogeneous translucent material, determining one or more material properties of the material based in part on a diffusion equation where one of the material properties is a diffusion coefficient for diffusion of radiation in the material and where the determining includes a regularization term for the diffusion coefficient, mapping the one or more material properties to a virtual object volume, assigning virtual illumination conditions to the virtual object volume, and rendering the virtual object volume using the virtual illumination conditions as a boundary condition for a system of diffusion equations of the virtual object volume. Other methods, devices and systems are also disclosed.
摘要翻译：一种示例性方法包括提供用于异质半透明材料的照明物理样品的图像数据，部分地基于扩散方程来确定材料的一种或多种材料性质，其中材料性质之一是用于辐射的扩散的扩散系数材料，并且其中确定包括扩散系数的正则化术语，将一个或多个材料属性映射到虚拟对象体积，将虚拟照明条件分配给虚拟对象体积，以及使用虚拟照明条件将虚拟对象体积呈现为虚拟物体体积扩散方程组的边界条件。还公开了其它方法，装置和系统。

68. 发明授权

US08238660B2 Hybrid graph model for unsupervised object segmentation 有权
标题翻译：用于无监督对象分割的混合图模型
公开(公告)号：US08238660B2
公开(公告)日：2012-08-07
申请号：US13100891
申请日：2011-05-04
申请人： Zhouchen Lin , Guangcan Liu , Xiaoou Tang
发明人： Zhouchen Lin , Guangcan Liu , Xiaoou Tang
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66
CPC分类号： G06K9/34 , G06K9/342 , G06K9/6296 , G06T7/11 , G06T7/162 , G06T7/194
摘要： This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.
摘要翻译：本公开描述了用于无人监督的对象分割的集成框架。通过以集成的方式使用算法将自上而下的约束和自下而上的对象形状约束集成在一起，进行类无监督对象分割。该算法描述了对象部分和超像素之间的关系。该过程通过对象部分形成对象形状，并将像素图像监视到超像素中，该算法与约束相结合。本公开描述了从混合图计算掩模图，将图像分割成前景对象和背景，以及从背景显示前景对象。

69. 发明授权

US07995841B2 Hybrid graph model for unsupervised object segmentation 有权
标题翻译：用于无监督对象分割的混合图模型
公开(公告)号：US07995841B2
公开(公告)日：2011-08-09
申请号：US11860428
申请日：2007-09-24
申请人： Zhouchen Lin , Guangcan Liu , Xiaoou Tang
发明人： Zhouchen Lin , Guangcan Liu , Xiaoou Tang
IPC分类号： G06K9/34 , G06K9/46 , G06K9/66 , G06K9/62 , G06K9/74
CPC分类号： G06K9/34 , G06K9/342 , G06K9/6296 , G06T7/11 , G06T7/162 , G06T7/194
摘要： This disclosure describes an integrated framework for class-unsupervised object segmentation. The class-unsupervised object segmentation occurs by integrating top-down constraints and bottom-up constraints on object shapes using an algorithm in an integrated manner. The algorithm describes a relationship among object parts and superpixels. This process forms object shapes with object parts and oversegments pixel images into the superpixels, with the algorithm in conjunction with the constraints. This disclosure describes computing a mask map from a hybrid graph, segmenting the image into a foreground object and a background, and displaying the foreground object from the background.
摘要翻译：本公开描述了用于无人监督的对象分割的集成框架。通过以集成的方式使用算法将自上而下的约束和自下而上的对象形状约束集成在一起，进行类无监督对象分割。该算法描述了对象部分和超像素之间的关系。该过程通过对象部分形成对象形状，并将像素图像监视到超像素中，该算法与约束相结合。本公开描述了从混合图计算掩模图，将图像分割成前景对象和背景，以及从背景显示前景对象。

70. 发明申请

US20100074551A1 LEARNING-BASED PARTIAL DIFFERENTIAL EQUATIONS FOR COMPUTER VISION 审中-公开
标题翻译：用于计算机视觉的基于学习的部分差分方程
公开(公告)号：US20100074551A1
公开(公告)日：2010-03-25
申请号：US12235488
申请日：2008-09-22
申请人： Zhouchen Lin , Wei Zhang
发明人： Zhouchen Lin , Wei Zhang
IPC分类号： G06K9/40
CPC分类号： G06K9/40 , G06T5/001 , G06T7/10 , G06T2207/20081
摘要： Partial differential equations (PDEs) are used in the invention for various problems in computer the vision space. The present invention provides a framework for learning a system of PDEs from real data to accomplish a specific vision task. In one embodiment, the system consists of two PDEs. One controls the evolution of the output. The other is for an indicator function that helps collect global information. Both PDEs are coupled equations between the output image and the indicator function, up to their second order partial derivatives. The way they are coupled is suggested by the shift and rotational invariance that the PDEs should hold. The coupling coefficients are learnt from real data via an optimal control technique. The invention provides learning-based PDEs that make a unified framework for handling different vision tasks, such as edge detection, denoising, segementation, and object detection.
摘要翻译：局部微分方程（PDE）用于本发明的计算机视觉空间中的各种问题。本发明提供了一种用于从实际数据学习PDE系统以完成特定视觉任务的框架。在一个实施例中，系统由两个PDE组成。一个控制输出的演变。另一个是用于帮助收集全球信息的指标功能。两个PDE是输出图像和指示符函数之间的耦合方程，直到它们的二阶偏导数。它们耦合的方式是由PDE应该保持的移动和旋转不变性来提出的。通过最优控制技术从实数数据中学习耦合系数。本发明提供了基于学习的PDE，其构成用于处理不同视觉任务的统一框架，例如边缘检测，去噪，分割和对象检测。

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