利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

50 条记录 (耗时 0.017 秒)

    FAST AND EFFICIENT NONLINEAR CLASSIFIER GENERATED FROM A TRAINED LINEAR CLASSIFIER
    1.
    发明申请
    FAST AND EFFICIENT NONLINEAR CLASSIFIER GENERATED FROM A TRAINED LINEAR CLASSIFIER 有权
    从训练线性分类器生成的快速有效的非线性分类器

    公开(公告)号：US20100318477A1

    公开(公告)日：2010-12-16

    申请号：US12483391

    申请日：2009-06-12

    申请人： Florent Perronnin ,  Jorge Sanchez

    发明人： Florent Perronnin ,  Jorge Sanchez

    IPC分类号： G06F15/18

    CPC分类号： G06K9/6271 ,  G06N99/005

    摘要： A classifier method comprises: projecting a set of training vectors in a vector space to a comparison space defined by a set of reference vectors using a comparison function to generate a corresponding set of projected training vectors in the comparison space; training a linear classifier on the set of projected training vectors to generate a trained linear classifier operative in the comparison space; and transforming the trained linear classifier operative in the comparison space into a trained nonlinear classifier that is operative in the vector space to classify an input vector.

    摘要翻译： 分类器方法包括：使用比较函数将矢量空间中的一组训练矢量投影到由一组参考矢量定义的比较空间，以在比较空间中生成相应的一组投影训练矢量; 在所述一组投影训练矢量上训练线性分类器以产生在比较空间中操作的经训练的线性分类器; 以及将在所述比较空间中操作的经训练的线性分类器变换成在所述向量空间中操作以对输入向量进行分类的经训练的非线性分类器。

    Large scale image classification
    2.
    发明授权
    Large scale image classification 有权
    大规模图像分类

    公开(公告)号：US08532399B2

    公开(公告)日：2013-09-10

    申请号：US12859898

    申请日：2010-08-20

    申请人： Florent Perronnin ,  Jorge Sanchez ,  Thomas Mensink

    发明人： Florent Perronnin ,  Jorge Sanchez ,  Thomas Mensink

    IPC分类号： G06K9/00

    CPC分类号： G06K9/6234 ,  G06K9/6249

    摘要： An input image representation is generated based on an aggregation of local descriptors extracted from an input image, and is adjusted by performing a power normalization, an Lp normalization such as an L2 normalization, or both. In some embodiments the generating comprises modeling the extracted local descriptors using a probabilistic model to generate the input image representation comprising probabilistic model component values for a set of probabilistic model components. In some such embodiments the probabilistic model comprises a Gaussian mixture model and the probabilistic model components comprise Gaussian components of the Gaussian mixture model. The generating may include partitioning the input image into a plurality of image partitions using a spatial pyramids partitioning model, extracting local descriptors, such as Fisher vectors, from the image partitions, and concatenating the local descriptors extracted from the image partitions.

    摘要翻译： 基于从输入图像提取的局部描述符的聚合生成输入图像表示，并且通过执行功率归一化，Lp归一化（诸如L2归一化）或两者来进行调整。 在一些实施例中，生成包括使用概率模型对所提取的局部描述符进行建模，以生成包括用于一组概率模型分量的概率模型分量值的输入图像表示。 在一些这样的实施例中，概率模型包括高斯混合模型，概率模型分量包括高斯混合模型的高斯分量。 生成可以包括使用空间金字塔分割模型将输入图像划分成多个图像分区，从图像分区中提取诸如Fisher向量的局部描述符，以及连接从图像分区提取的局部描述符。

    Fast and efficient nonlinear classifier generated from a trained linear classifier
    3.
    发明授权
    Fast and efficient nonlinear classifier generated from a trained linear classifier 有权
    从训练有素的线性分类器生成的快速高效的非线性分类器

    公开(公告)号：US08280828B2

    公开(公告)日：2012-10-02

    申请号：US12483391

    申请日：2009-06-12

    申请人： Florent Perronnin ,  Jorge Sanchez

    发明人： Florent Perronnin ,  Jorge Sanchez

    IPC分类号： G06F19/24 ,  G06F17/16

    CPC分类号： G06K9/6271 ,  G06N99/005

    摘要： A classifier method comprises: projecting a set of training vectors in a vector space to a comparison space defined by a set of reference vectors using a comparison function to generate a corresponding set of projected training vectors in the comparison space; training a linear classifier on the set of projected training vectors to generate a trained linear classifier operative in the comparison space; and transforming the trained linear classifier operative in the comparison space into a trained nonlinear classifier that is operative in the vector space to classify an input vector.

    摘要翻译： 分类器方法包括：使用比较函数将矢量空间中的一组训练矢量投影到由一组参考矢量定义的比较空间，以在比较空间中生成相应的一组投影训练矢量; 在所述一组投影训练矢量上训练线性分类器以产生在比较空间中操作的经训练的线性分类器; 以及将在所述比较空间中操作的经训练的线性分类器变换成在所述向量空间中操作以对输入向量进行分类的经训练的非线性分类器。

    IMAGE CLASSIFICATION EMPLOYING IMAGE VECTORS COMPRESSED USING VECTOR QUANTIZATION
    4.
    发明申请
    IMAGE CLASSIFICATION EMPLOYING IMAGE VECTORS COMPRESSED USING VECTOR QUANTIZATION 有权
    使用矢量量化压缩的图像分类图像分类

    公开(公告)号：US20120076401A1

    公开(公告)日：2012-03-29

    申请号：US12890789

    申请日：2010-09-27

    申请人： Jorge Sanchez ,  Florent Perronnin

    发明人： Jorge Sanchez ,  Florent Perronnin

    IPC分类号： G06K9/62 ,  G06K9/48

    CPC分类号： G06K9/4676

    摘要： Local descriptors are extracted from an image. An image vector is generated having vector elements indicative of parameters of mixture model components of a mixture model representing the extracted local descriptors. The image vector is compressed using a vector quantization algorithm to generate a compressed image vector. Optionally, the compressing comprises splitting the image vector into a plurality of sub-vectors each including at least two vector elements, compressing each sub-vector independently using the vector quantization algorithm, and concatenating the compressed sub-vectors to generate the compressed image vector. Optionally, each sub-vector includes only vector elements indicative of parameters of a single mixture model component, and any sparse sub-vector whose vector elements are indicative of parameters of a mixture model component that does not represent any of the extracted local descriptors is not compressed.

    摘要翻译： 从图像中提取局部描述符。 生成具有指示表示所提取的局部描述符的混合模型的混合模型分量的参数的向量元素的图像向量。 使用矢量量化算法压缩图像矢量以生成压缩图像矢量。 可选地，压缩包括将图像向量分成多个子向量，每个子向量包括至少两个向量元素，使用向量量化算法独立地压缩每个子向量，并且连接压缩的子向量以生成压缩图像向量。 可选地，每个子向量仅包括指示单个混合模型组件的参数的向量元素，并且其向量元素指示不表示任何提取的局部描述符的混合模型组件的参数的任何稀疏子向量不是 压缩

    Image classification employing image vectors compressed using vector quantization
    5.
    发明授权
    Image classification employing image vectors compressed using vector quantization 有权
    使用矢量量化压缩的图像矢量的图像分类

    公开(公告)号：US08731317B2

    公开(公告)日：2014-05-20

    申请号：US12890789

    申请日：2010-09-27

    申请人： Jorge Sanchez ,  Florent Perronnin

    发明人： Jorge Sanchez ,  Florent Perronnin

    IPC分类号： G06K9/00

    CPC分类号： G06K9/4676

    摘要： Local descriptors are extracted from an image. An image vector is generated having vector elements indicative of parameters of mixture model components of a mixture model representing the extracted local descriptors. The image vector is compressed using a vector quantization algorithm to generate a compressed image vector. Optionally, the compressing comprises splitting the image vector into a plurality of sub-vectors each including at least two vector elements, compressing each sub-vector independently using the vector quantization algorithm, and concatenating the compressed sub-vectors to generate the compressed image vector. Optionally, each sub-vector includes only vector elements indicative of parameters of a single mixture model component, and any sparse sub-vector whose vector elements are indicative of parameters of a mixture model component that does not represent any of the extracted local descriptors is not compressed.

    摘要翻译： 从图像中提取局部描述符。 生成具有指示表示所提取的局部描述符的混合模型的混合模型分量的参数的向量元素的图像向量。 使用矢量量化算法压缩图像矢量以生成压缩图像矢量。 可选地，压缩包括将图像向量分成多个子向量，每个子向量包括至少两个向量元素，使用向量量化算法独立地压缩每个子向量，并且连接压缩的子向量以生成压缩图像向量。 可选地，每个子向量仅包括指示单个混合模型组件的参数的向量元素，并且其向量元素指示不表示任何提取的局部描述符的混合模型组件的参数的任何稀疏子向量不是 压缩

    LARGE SCALE IMAGE CLASSIFICATION
    6.
    发明申请
    LARGE SCALE IMAGE CLASSIFICATION 有权
    大规模图像分类

    公开(公告)号：US20120045134A1

    公开(公告)日：2012-02-23

    申请号：US12859898

    申请日：2010-08-20

    申请人： Florent Perronnin ,  Jorge Sanchez ,  Thomas Mensink

    发明人： Florent Perronnin ,  Jorge Sanchez ,  Thomas Mensink

    IPC分类号： G06K9/62 ,  G06K9/48 ,  G06T5/00

    CPC分类号： G06K9/6234 ,  G06K9/6249

    摘要： An input image representation is generated based on an aggregation of local descriptors extracted from an input image, and is adjusted by performing a power normalization, an Lp normalization such as an L2 normalization, or both. In some embodiments the generating comprises modeling the extracted local descriptors using a probabilistic model to generate the input image representation comprising probabilistic model component values for a set of probabilistic model components. In some such embodiments the probabilistic model comprises a Gaussian mixture model and the probabilistic model components comprise Gaussian components of the Gaussian mixture model. The generating may include partitioning the input image into a plurality of image partitions using a spatial pyramids partitioning model, extracting local descriptors, such as Fisher vectors, from the image partitions, and concatenating the local descriptors extracted from the image partitions.

    摘要翻译： 基于从输入图像提取的局部描述符的聚合生成输入图像表示，并且通过执行功率归一化，Lp归一化（诸如L2归一化）或两者来进行调整。 在一些实施例中，生成包括使用概率模型对所提取的局部描述符进行建模，以生成包括用于一组概率模型分量的概率模型分量值的输入图像表示。 在一些这样的实施例中，概率模型包括高斯混合模型，概率模型分量包括高斯混合模型的高斯分量。 生成可以包括使用空间金字塔分割模型将输入图像划分成多个图像分区，从图像分区中提取诸如Fisher向量的局部描述符，以及连接从图像分区提取的局部描述符。

    Method and firmware for controlling voltage and current in a fluorescent lamp array
    9.
    发明授权
    Method and firmware for controlling voltage and current in a fluorescent lamp array 有权
    用于控制荧光灯阵列中的电压和电流的方法和固件

    公开(公告)号：US08111013B2

    公开(公告)日：2012-02-07

    申请号：US12043070

    申请日：2008-03-05

    申请人： Jorge Sanchez

    发明人： Jorge Sanchez

    IPC分类号： H05B37/02

    CPC分类号： H02M7/53873 ,  H05B41/2828 ,  H05B41/3927 ,  Y02B20/186

    摘要： A method and firmware for controlling voltage and current in an electrical load includes steps of calculating a numerically quantized duty cycle of a pulse-width modulated, digital switch control signal by firmware in an inverter voltage microcontroller as a function of an inverter voltage and controlling the inverter voltage by adjusting the duty cycle of the digital switch control signal to generate a load current in the electrical load.

    摘要翻译： 用于控制电负载中的电压和电流的方法和固件包括以下步骤：根据逆变器电压微控制器中的固件计算脉冲宽度调制的数字开关控制信号的数字量化占空比，并且控制 逆变器电压通过调节数字开关控制信号的占空比来产生负载电流在电气负载中。