-
公开(公告)号：US07917336B2
公开(公告)日：2011-03-29
申请号：US10470498
申请日：2002-01-17
申请人： Lucas Cristobal Parra , Christopher Vincent Alvino , Clay Douglas Spence , Craig Langdale Fancourt
发明人： Lucas Cristobal Parra , Christopher Vincent Alvino , Clay Douglas Spence , Craig Langdale Fancourt
IPC分类号： G06F19/00
CPC分类号： H03H21/0027 , G06K9/624 , G10L21/0272 , G10L2021/02166 , H03H2021/0036
摘要： A computer system that processes mixtures of signals, such as speech and noise sources derived from multiple simultaneous microphone recordings, in order to separate them into their underlying sources. A source separation routine optimizes a filter structure by minimizing cross powers of multiple output channels while enforcing geometric constraints on the filter response. The geometric constraints enforce desired responses for given locations of the underlying sources, based on the assumption that the sources are localized in space.
摘要翻译： 处理来自多个同时麦克风记录的语音和噪声源的信号混合的计算机系统，以将它们分离成它们的潜在源。 源分离程序通过最小化多个输出通道的交叉功率来优化滤波器结构，同时对滤波器响应实施几何约束。 基于源在本地化的假设，几何约束对基础源的给定位置执行预期响应。
-
2.发明申请METHOD AND SYSTEM FOR FILTERING, REGISTERING, AND MATCHING 2.5D NORMAL MAPS 有权用于过滤，注册和匹配2.5D正常MAPS的方法和系统公开(公告)号：US20100172597A1
公开(公告)日：2010-07-08
申请号：US12604876
申请日：2009-10-23
IPC分类号： G06K9/64
CPC分类号： G06K9/00214 , G06T7/33 , G06T2200/04
摘要： An iterative approach to vector median filtering wherein the resulting median vector need not be a member of the original data set. The iterative vector median filtering allows for fast convergence for complex computations and an output which is approximate to the mean, particularly for small data sets.In addition, a method and system for registering and matching 2.5 normal maps is provided. Registration of two maps is performed by optimally aligning their normals through 2-D warping in the image plane in conjunction with a 3-D rotation of the normals. Once aligned, the average dot-product serves as a matching metric for automatic target recognition (ATR).
摘要翻译： 矢量中值滤波的迭代方法，其中所得到的中值向量不需要是原始数据集的成员。 迭代向量中值滤波允许复杂计算的快速收敛和近似于平均值的输出，特别是对于小数据集。 另外，提供了一种用于注册和匹配2.5法线贴图的方法和系统。 通过将图像平面中的二维翘曲与法线的3-D旋转结合来最佳地对准其法线来执行两个地图的注册。 一旦对齐，平均点积用作自动目标识别（ATR）的匹配度量。
-
3.发明授权Method and system for filtering, registering, and matching 2.5D normal maps 有权用于过滤，注册和匹配2.5D法线贴图的方法和系统公开(公告)号：US07844133B2
公开(公告)日：2010-11-30
申请号：US12604876
申请日：2009-10-23
IPC分类号： G06K9/32
CPC分类号： G06K9/00214 , G06T7/33 , G06T2200/04
摘要： An iterative approach to vector median filtering wherein the resulting median vector need not be a member of the original data set. The iterative vector median filtering allows for fast convergence for complex computations and an output which is approximate to the mean, particularly for small data sets.In addition, a method and system for registering and matching 2.5 normal maps is provided. Registration of two maps is performed by optimally aligning their normals through 2-D warping in the image plane in conjunction with a 3-D rotation of the normals. Once aligned, the average dot-product serves as a matching metric for automatic target recognition (ATR).
摘要翻译： 矢量中值滤波的迭代方法，其中所得到的中值向量不需要是原始数据集的成员。 迭代向量中值滤波允许复杂计算的快速收敛和近似于平均值的输出，特别是对于小数据集。 另外，提供了一种用于注册和匹配2.5法线贴图的方法和系统。 通过将图像平面中的二维翘曲与法线的3-D旋转结合来最佳地对准其法线来执行两个地图的注册。 一旦对齐，平均点积用作自动目标识别（ATR）的匹配度量。
-
公开(公告)号：US07747106B2
公开(公告)日：2010-06-29
申请号：US11451671
申请日：2006-06-13
IPC分类号： G06K9/32
CPC分类号： G06K9/00214 , G06T7/33 , G06T2200/04
摘要： An iterative approach to vector median filtering wherein the resulting median vector need not be a member of the original data set. The iterative vector median filtering allows for fast convergence for complex computations and an output which is approximate to the mean, particularly for small data sets.In addition, a method and system for registering and matching 2.5 normal maps is provided. Registration of two maps is performed by optimally aligning their normals through 2-D warping in the image plane in conjunction with a 3-D rotation of the normals. Once aligned, the average dot-product serves as a matching metric for automatic target recognition (ATR).
-
公开(公告)号：US06898612B1
公开(公告)日：2005-05-24
申请号：US09597105
申请日：2000-06-20
CPC分类号： G06K9/6243 , G10L21/0272 , H03H21/0012 , H03H21/0029 , H03H2021/0034
摘要： A method and apparatus is disclosed for performing blind source separation using convolutive signal decorrelation. For a first embodiment, the method accumulates a length of input signal (mixed signal) that includes a plurality of independent signals from independent signal sources. The invention then divides the length of input signal into a plurality of T-length periods (windows) and performs a discrete Fourier transform (DFT) on the, signal within each T-length period. Thereafter, estimated cross-correlation values are computed using a plurality of the averaged DFT values. A total number of K cross-correlation values are computed, where each of the K values is averaged over N of the T-length periods. Using the cross-correlation values, a gradient descent process computes the coefficients of a finite impulse response (FIR) filter that will effectively separate the source signals within the input signal. A second embodiment of the invention is directed to on-line processing of the input signal—i.e., processing the signal as soon as it arrives with no storage of the signal data. In particular, an on-line gradient algorithm is provided for application to non-stationary signals and having an adaptive step size in the frequency domain based on second derivatives of the cost function. The on-line separation methodology of this embodiment is characterized as multiple adaptive decorrelation.
摘要翻译： 公开了一种使用卷积信号去相关进行盲源分离的方法和装置。 对于第一实施例，该方法累积包括来自独立信号源的多个独立信号的输入信号（混合信号）的长度。 然后，本发明将输入信号的长度划分成多个T长度周期（窗口），并在每个T长度周期内对该信号执行离散付里叶变换（DFT）。 此后，使用多个平均DFT值来计算估计的互相关值。 计算总共K个互相关值，其中K个值中的每一个在T个长度周期的N个上被平均。 使用互相关值，梯度下降处理计算有效脉冲响应（FIR）滤波器的系数，其将有效地分离输入信号内的源信号。 本发明的第二个实施例涉及输入信号的在线处理，即，一旦信号到达就处理该信号而没有信号数据的存储。 特别地，提供在线梯度算法用于非平稳信号的应用，并且基于成本函数的二阶导数在频域中具有自适应步长。 本实施例的在线分离方法被表征为多自适应去相关。
-
公开(公告)号：US07603401B2
公开(公告)日：2009-10-13
申请号：US11095346
申请日：2005-03-31
CPC分类号： G06K9/6243 , G10L21/0272 , H03H21/0012 , H03H21/0029 , H03H2021/0034
摘要： A method and apparatus is disclosed for performing blind source separation using convolutive signal decorrelation. For a first embodiment, the method accumulates a length of input signal (mixed signal) that comprises a plurality of independent signals from independent signal sources. The invention then divides the length of input signal into a plurality of T-length periods (windows) and performs a discrete Fourier transform (DFT) on the signal within each T-length period. Thereafter, estimated cross-correlation values are computed using a plurality of the averaged DFT values. A total number of K cross-correlation values are computed, where each of the K values is averaged over N of the T-length periods. Using the cross-correlation values, a gradient descent process computes the coefficients of a FIR filter that will effectively separate the source signals within the input signal. A second embodiment of the invention is directed to on-line processing of the input signal—i.e., processing the signal as soon as it arrives with no storage of the signal data. In particular, an on-line gradient algorithm is provided for application to non-stationary signals and having an adaptive step size in the frequency domain based on second derivatives of the cost function. The on-line separation methodology of this embodiment is characterized as multiple adaptive decorrelation.
摘要翻译： 公开了一种使用卷积信号去相关进行盲源分离的方法和装置。 对于第一实施例，该方法累积包括来自独立信号源的多个独立信号的输入信号（混合信号）的长度。 然后，本发明将输入信号的长度划分成多个T长度周期（窗口），并对每个T长度周期内的信号执行离散付里叶变换（DFT）。 此后，使用多个平均DFT值来计算估计的互相关值。 计算总共K个互相关值，其中K个值中的每一个在T个长度周期的N个上被平均。 使用互相关值，梯度下降处理计算将有效地分离输入信号内的源信号的FIR滤波器的系数。 本发明的第二个实施例涉及输入信号的在线处理，即，一旦信号到达就处理该信号而没有信号数据的存储。 特别地，提供在线梯度算法用于非平稳信号的应用，并且基于成本函数的二阶导数在频域中具有自适应步长。 本实施例的在线分离方法被表征为多自适应去相关。
-
7.发明授权Method and apparatus for training and operating a neural network for detecting breast cancer 失效用于训练和操作用于检测乳腺癌的神经网络的方法和装置公开(公告)号：US06208983B1
公开(公告)日：2001-03-27
申请号：US09126341
申请日：1998-07-30
申请人： Lucas Parra , Paul Sajda , Clay Douglas Spence
发明人： Lucas Parra , Paul Sajda , Clay Douglas Spence
IPC分类号： G06F1518
CPC分类号： G06N3/0454 , G06F19/00 , G06F19/321 , G06K9/00536 , G16H50/20
摘要： A method and apparatus for training and operating a neural network using gated data. The neural network is a mixture of experts that performs “soft” partitioning of a network of experts. In a specific embodiment, the technique is used to detect malignancy by analyzing skin surface potential data. In particular, the invention uses certain patient information, such as menstrual cycle information, to “gate” the expert output data into particular populations, i.e., the network is soft partitioned into the populations. An Expectation-Maximization (EM) routine is used to train the neural network using known patient information, known measured skin potential data and correct diagnosis for the particular training data and patient information. Once trained, the neural network parameters are used in a classifier for predicting breast cancer malignancy when given the patient information and skin potentials of other patients.
摘要翻译： 一种使用门控数据训练和操作神经网络的方法和装置。 神经网络是专家组合，对专家网络进行“软”划分。 在具体实施例中，该技术用于通过分析皮肤表面电位数据来检测恶性肿瘤。 特别地，本发明使用某些患者信息，例如月经周期信息，将专家输出数据“门”到特定群体，即网络被软分割成群体。 使用期望最大化（EM）程序来训练神经网络，使用已知的患者信息，已知的测量的皮肤潜能数据和针对特定训练数据和患者信息的正确诊断。 一旦训练，当给予患者信息和其他患者的皮肤电位时，神经网络参数用于分类器中用于预测乳腺癌恶性肿瘤。
-
8.发明授权Method and apparatus for training a neural network to learn hierarchical representations of objects and to detect and classify objects with uncertain training data 失效用于训练神经网络以学习对象的分层表示并且用不确定的训练数据检测和分类对象的方法和装置
公开(公告)号：US06018728A
公开(公告)日：2000-01-25
申请号：US797497
申请日：1997-02-07
CPC分类号： G06K9/3233 , G06K9/4609 , G06K9/4628 , G06K9/66 , G06N3/0472 , G06N3/082 , G06T7/0012 , G06K2209/05
摘要： A signal processing apparatus and concomitant method for learning and integrating features from multiple resolutions for detecting and/or classifying objects are presented. Neural networks in a pattern tree structure with tree-structured descriptions of objects in terms of simple sub-patterns, are grown and trained to detect and integrate the sub-patterns. A plurality of objective functions and their approximations are presented to train the neural networks to detect sub-patterns of features of some class of objects. Objective functions for training neural networks to detect objects whose positions in the training data are uncertain and for addressing supervised learning where there are potential errors in the training data are also presented.
摘要翻译： 提出了用于学习和整合用于检测和/或分类对象的多个分辨率的特征的信号处理装置和并发方法。 生长和训练具有根据简单子模式的对象的树结构描述的模式树结构中的神经网络以检测和集成子模式。 提出了多个目标函数及其近似来训练神经网络以检测某些类别对象的特征的子模式。 还提出了用于训练神经网络以检测训练数据中的位置不确定以及训练数据中存在潜在错误的监督学习的目标函数。
-
9.发明授权Method and system for improving video metadata through the use of frame-to-frame correspondences 有权通过使用帧到帧对应来改进视频元数据的方法和系统公开(公告)号：US07313252B2
公开(公告)日：2007-12-25
申请号：US11390700
申请日：2006-03-27
申请人： Bogdan Calin Mihai Matei , Clay Douglas Spence , Arthur Robert Pope , Barbara Viviane Hanna , Michael Wade Hansen
发明人： Bogdan Calin Mihai Matei , Clay Douglas Spence , Arthur Robert Pope , Barbara Viviane Hanna , Michael Wade Hansen
摘要： A method and system for improving the accuracy and timeliness of video metadata by incorporating information related to the motion of the camera as derived from the video imagery itself. Frame-to-frame correspondences are used to accurately estimate changes in camera pose. While the method and system do not require geo-registration, geo-registration results, if available, may be considered in processing the video images and generating improved camera pose estimates.
摘要翻译： 一种用于通过结合从视频图像本身导出的与摄像机的运动相关的信息来提高视频元数据的准确性和及时性的方法和系统。 帧对帧对应用于准确估计摄像机姿态的变化。 虽然方法和系统不需要地理注册，但是在处理视频图像并产生改进的相机姿态估计时可以考虑地理注册结果（如果可用）。
-
10.发明授权Method and apparatus for training a neural network to detect objects in an image 有权用于训练神经网络以检测图像中的物体的方法和装置公开(公告)号：US06324532B1
公开(公告)日：2001-11-27
申请号：US09464506
申请日：1999-12-15
申请人： Clay Douglas Spence , Paul Sajda
发明人： Clay Douglas Spence , Paul Sajda
IPC分类号： G06F1518
CPC分类号： G06K9/3241 , G06K9/6278 , G06K9/66 , G06N3/0454 , G06N3/082
摘要： A signal processing apparatus and concomitant method for learning and integrating features from multiple resolutions for detecting and/or classifying objects. The signal processing apparatus comprises a hierarchical pyramid of neural networks (HPNN) having a “fine-to-coarse” structure or a combination of the “fine-to-coarse” and the “coarse-to-fine” structures.
摘要翻译： 一种用于学习和整合用于检测和/或分类对象的多个分辨率的特征的信号处理装置和并发方法。 该信号处理装置包括具有“细至粗”结构的神经网络（HPNN）等级金字塔或“细到粗”和“粗到细”结构的组合。
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.037 秒)
