利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

1283 条记录 (耗时 0.034 秒)

    LEARNING APPARATUS FOR PATTERN DETECTOR, LEARNING METHOD AND COMPUTER-READABLE STORAGE MEDIUM
    1.
    发明申请
    LEARNING APPARATUS FOR PATTERN DETECTOR, LEARNING METHOD AND COMPUTER-READABLE STORAGE MEDIUM 有权
    模式检测器，学习方法和计算机可读存储介质的学习设备

    公开(公告)号：US20090324060A1

    公开(公告)日：2009-12-31

    申请号：US12485020

    申请日：2009-06-15

    申请人： Hiroshi Sato ,  Katsuhiko Mori ,  Masakazu Matsugu ,  Kan Torii ,  Yuji Kaneda ,  Takashi Suzuki

    发明人： Hiroshi Sato ,  Katsuhiko Mori ,  Masakazu Matsugu ,  Kan Torii ,  Yuji Kaneda ,  Takashi Suzuki

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6257 ,  G06K9/00228 ,  G06K9/4609 ,  G06K9/6282

    摘要： A learning apparatus for a pattern detector, which includes a plurality of weak classifiers and detects a specific pattern from input data by classifications of the plurality of weak classifiers, acquires a plurality of data for learning in each of which whether or not the specific pattern is included is given, makes the plurality of weak classifiers learn by making the plurality of weak classifiers detect the specific pattern from the acquired data for learning, selects a plurality of weak classifiers to be composited from the weak classifiers which have learned, and composites the plurality of weak classifiers into one composite weak classifier based on comparison between a performance of the composite weak classifier and performances of the plurality of weak classifiers.

    摘要翻译： 一种用于模式检测器的学习装置，包括多个弱分类器，并通过多个弱分类器的分类从输入数据检测特定模式，获取多个用于学习的数据，每个数据是否具体模式是 通过使多个弱分类器从所获取的学习数据中检测出特定模式，使得多个弱分类器学习，从已经学习的弱分类器中选择要合成的多个弱分类器，并且复合多个弱分类器 基于复合弱分类器的性能与多个弱分类器的性能之间的比较，将弱分类器转换为一个复合弱分类器。

    Learning apparatus for pattern detector, learning method and computer-readable storage medium
    2.
    发明授权
    Learning apparatus for pattern detector, learning method and computer-readable storage medium 有权
    用于图案检测器，学习方法和计算机可读存储介质的学习装置

    公开(公告)号：US08331655B2

    公开(公告)日：2012-12-11

    申请号：US12485020

    申请日：2009-06-15

    申请人： Hiroshi Sato ,  Katsuhiko Mori ,  Masakazu Matsugu ,  Kan Torii ,  Yuji Kaneda ,  Takashi Suzuki

    发明人： Hiroshi Sato ,  Katsuhiko Mori ,  Masakazu Matsugu ,  Kan Torii ,  Yuji Kaneda ,  Takashi Suzuki

    IPC分类号： G06K9/62 ,  G06K9/40

    CPC分类号： G06K9/6257 ,  G06K9/00228 ,  G06K9/4609 ,  G06K9/6282

    摘要： A learning apparatus for a pattern detector, which includes a plurality of weak classifiers and detects a specific pattern from input data by classifications of the plurality of weak classifiers, acquires a plurality of data for learning in each of which whether or not the specific pattern is included is given, makes the plurality of weak classifiers learn by making the plurality of weak classifiers detect the specific pattern from the acquired data for learning, selects a plurality of weak classifiers to be composited from the weak classifiers which have learned, and composites the plurality of weak classifiers into one composite weak classifier based on comparison between a performance of the composite weak classifier and performances of the plurality of weak classifiers.

    摘要翻译： 一种用于模式检测器的学习装置，包括多个弱分类器，并通过多个弱分类器的分类从输入数据检测特定模式，获取多个用于学习的数据，每个数据是否具体模式是 通过使多个弱分类器从所获取的用于学习的数据中检测到特定模式，使多个弱分类器学习，从已经学习的弱分类器中选择要合成的多个弱分类器，并且复合多个 基于复合弱分类器的性能与多个弱分类器的性能之间的比较，将弱分类器转换为一个复合弱分类器。

    PATTERN IDENTIFICATION METHOD, PARAMETER LEARNING METHOD AND APPARATUS
    3.
    发明申请
    PATTERN IDENTIFICATION METHOD, PARAMETER LEARNING METHOD AND APPARATUS 有权
    模式识别方法，参数学习方法和装置

    公开(公告)号：US20090089235A1

    公开(公告)日：2009-04-02

    申请号：US12205174

    申请日：2008-09-05

    申请人： Kan Torii ,  Katsuhiko Mori ,  Yusuke Mitarai ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

    发明人： Kan Torii ,  Katsuhiko Mori ,  Yusuke Mitarai ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

    IPC分类号： G06N5/02

    CPC分类号： G06K9/6282 ,  G06K9/68

    摘要： In a pattern identification method in which input data is classified into predetermined classes by sequentially executing a combination of a plurality of classification processes, at least one of the classification processes includes a mapping step of mapping the input data in an N (N≧2) dimensional feature space as corresponding points, a determination step of determining whether or not to execute the next classification process based on the corresponding points, and selecting step of selecting a classification process to be executed next based on the corresponding points when it is determined in the determination step that the next classification process should be executed.

    摘要翻译： 在通过顺序地执行多个分类处理的组合将输入数据分类为预定类别的模式识别方法中，至少一个分类处理包括映射步骤，其将输入数据映射到N（N> = 2 ）维特征空间作为对应点，确定步骤，基于对应点确定是否执行下一个分类处理;以及选择步骤，基于对应点选择下一个执行的分类处理 下一个分类过程应该执行的确定步骤。

    Pattern identification method, parameter learning method and apparatus
    4.
    发明授权
    Pattern identification method, parameter learning method and apparatus 有权
    模式识别方法，参数学习方法和装置

    公开(公告)号：US08527439B2

    公开(公告)日：2013-09-03

    申请号：US12205174

    申请日：2008-09-05

    申请人： Kan Torii ,  Katsuhiko Mori ,  Yusuke Mitarai ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

    发明人： Kan Torii ,  Katsuhiko Mori ,  Yusuke Mitarai ,  Hiroshi Sato ,  Yuji Kaneda ,  Takashi Suzuki

    IPC分类号： G06F17/00

    CPC分类号： G06K9/6282 ,  G06K9/68

    摘要： In a pattern identification method in which input data is classified into predetermined classes by sequentially executing a combination of a plurality of classification processes, at least one of the classification processes includes a mapping step of mapping the input data in an N (N≧2) dimensional feature space as corresponding points, a determination step of determining whether or not to execute the next classification process based on the corresponding points, and selecting step of selecting a classification process to be executed next based on the corresponding points when it is determined in the determination step that the next classification process should be executed.

    摘要翻译： 在通过顺序地执行多个分类处理的组合将输入数据分类为预定类别的模式识别方法中，至少一个分类处理包括映射步骤，其将输入数据映射到N（N> = 2 ）维特征空间作为对应点，确定步骤，基于对应点确定是否执行下一个分类处理;以及选择步骤，基于对应点选择下一个执行的分类处理 下一个分类过程应该执行的确定步骤。

    Object Recognition Method and Apparatus Therefor
    7.
    发明申请
    Object Recognition Method and Apparatus Therefor 有权
    对象识别方法及其设备

    公开(公告)号：US20070242856A1

    公开(公告)日：2007-10-18

    申请号：US11630031

    申请日：2005-06-27

    申请人： Takashi Suzuki ,  Katsuhiko Mori ,  Masakazu Matsugu

    发明人： Takashi Suzuki ,  Katsuhiko Mori ,  Masakazu Matsugu

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00281 ,  G06K9/00275 ,  G06K9/4628

    摘要： A feature extraction unit (23) extracts features of an object of interest included in an image. A local region setting unit (24) sets a local region that includes a feature group required to obtain the shape of the object and a local region that includes a feature group required to obtain the positional relationship. A feature vector generation unit (25) calculates feature vector data in the set local regions. An object recognition unit (26) determines which of different objects the object of interest is, on the basis of the feature vectors.

    摘要翻译： 特征提取单元（23）提取包括在图像中的感兴趣对象的特征。 局部区域设定单元（24）设定包含获取对象形状所需要的特征组的局部区域和包含获取位置关系所需特征组的局部区域。 特征向量生成单元（25）计算设定的局部区域中的特征向量数据。 基于特征向量，对象识别单元（26）确定感兴趣对象的哪个不同对象。

    Object recognition method and apparatus therefor
    8.
    发明授权
    Object recognition method and apparatus therefor 有权
    对象识别方法及其设备

    公开(公告)号：US07912253B2

    公开(公告)日：2011-03-22

    申请号：US11630031

    申请日：2005-06-27

    申请人： Takashi Suzuki ,  Katsuhiko Mori ,  Masakazu Matsugu

    发明人： Takashi Suzuki ,  Katsuhiko Mori ,  Masakazu Matsugu

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00281 ,  G06K9/00275 ,  G06K9/4628

    摘要： A feature extraction unit (23) extracts features of an object of interest included in an image. A local region setting unit (24) sets a local region that includes a feature group required to obtain the shape of the object and a local region that includes a feature group required to obtain the positional relationship. A feature vector generation unit (25) calculates feature vector data in the set local regions. An object recognition unit (26) determines which of different objects the object of interest is, on the basis of the feature vectors.

    摘要翻译： 特征提取单元（23）提取包括在图像中的感兴趣对象的特征。 局部区域设定单元（24）设定包含获取对象形状所需要的特征组的局部区域和包含获取位置关系所需特征组的局部区域。 特征向量生成单元（25）计算设定的局部区域中的特征向量数据。 基于特征向量，对象识别单元（26）确定感兴趣对象的哪个不同对象。

    IMAGE PROCESSING APPARATUS FOR IDENTIFYING AN INDIVIDUAL OBJECT, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM
    9.
    发明申请
    IMAGE PROCESSING APPARATUS FOR IDENTIFYING AN INDIVIDUAL OBJECT, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM 有权
    用于识别个体对象，图像处理方法和存储介质的图像处理装置

    公开(公告)号：US20080002862A1

    公开(公告)日：2008-01-03

    申请号：US11771382

    申请日：2007-06-29

    申请人： Masakazu Matsugu ,  Katsuhiko Mori ,  Takashi Suzuki

    发明人： Masakazu Matsugu ,  Katsuhiko Mori ,  Takashi Suzuki

    IPC分类号： G06K9/00

    CPC分类号： G06K9/00248 ,  G06K9/00261 ,  G06K9/00315

    摘要： An image capturing unit acquires an image including an object. A state detection unit detects the state of the object in the image. An individual recognition processing unit determines one of a plurality of individual identification process modules in correspondence with the state detected by the state detection unit. The individual recognition processing unit executes, for the object in the image, an individual identification process by the determined individual identification process module.

    摘要翻译： 图像拍摄单元获取包括对象的图像。 状态检测单元检测图像中物体的状态。 个体识别处理单元根据由状态检测单元检测到的状态确定多个个体识别处理模块中的一个。 个体识别处理单元对图像中的对象执行由确定的个体识别处理模块进行的个体识别处理。

    Image processing apparatus for identifying an individual object, image processing method, and storage medium
    10.
    发明授权
    Image processing apparatus for identifying an individual object, image processing method, and storage medium 有权
    用于识别单个物体的图像处理装置，图像处理方法和存储介质

    公开(公告)号：US08311272B2

    公开(公告)日：2012-11-13

    申请号：US11771382

    申请日：2007-06-29

    申请人： Masakazu Matsugu ,  Katsuhiko Mori ,  Takashi Suzuki

    发明人： Masakazu Matsugu ,  Katsuhiko Mori ,  Takashi Suzuki

    IPC分类号： G06K9/00 ,  G06K9/62

    CPC分类号： G06K9/00248 ,  G06K9/00261 ,  G06K9/00315

    摘要： An image capturing unit acquires an image including an object. A state detection unit detects the state of the object in the image. An individual recognition processing unit determines one of a plurality of individual identification process modules in correspondence with the state detected by the state detection unit. The individual recognition processing unit executes, for the object in the image, an individual identification process by the determined individual identification process module.

    摘要翻译： 图像拍摄单元获取包括对象的图像。 状态检测单元检测图像中物体的状态。 个体识别处理单元根据由状态检测单元检测到的状态确定多个个体识别处理模块中的一个。 个体识别处理单元对图像中的对象执行由确定的个体识别处理模块进行的个体识别处理。