利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

200 条记录 (耗时 0.033 秒)

    LEARNING APPARATUS FOR PATTERN DETECTOR, LEARNING METHOD AND COMPUTER-READABLE STORAGE MEDIUM
    3.
    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。

    METHOD AND APPARATUS FOR DETECTING AND PROCESSING SPECIFIC PATTERN FROM IMAGE
    5.
    发明申请
    METHOD AND APPARATUS FOR DETECTING AND PROCESSING SPECIFIC PATTERN FROM IMAGE 有权
    用于从图像中检测和处理特定图案的方法和装置

    公开(公告)号：US20080212879A1

    公开(公告)日：2008-09-04

    申请号：US11951809

    申请日：2007-12-06

    申请人： Kan Torii ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Hiroshi Sato ,  Yusuke Mitarai

    发明人： Kan Torii ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Hiroshi Sato ,  Yusuke Mitarai

    IPC分类号： G06K9/46

    CPC分类号： G06K9/00234 ,  G06K2209/011 ,  H04N5/23219

    摘要： In an image within which a face pattern is detected, when a ratio of a skin color pixel is equal to or smaller than a first threshold value in a first region and a ratio of a skin color pixel is equal to or greater than a second threshold value in a second r region, the vicinity of the first region is determined to be a face candidate position at which the face pattern can exist. Face detection is carried out on the face candidate position. The second region is arranged in a predetermined position relative to the first region.

    摘要翻译： 在其中检测到面部图案的图像中，当皮肤颜色像素的比例在第一区域中等于或小于第一阈值并且皮肤颜色像素的比率等于或大于第二阈值时 在第二r区域中，第一区域附近被确定为可以存在脸部图案的面部候选位置。 脸部检测在脸部候选位置进行。 第二区域相对于第一区域布置在预定位置。

    Parameter learning method, parameter learning apparatus, pattern classification method, and pattern classification apparatus
    6.
    发明授权
    Parameter learning method, parameter learning apparatus, pattern classification method, and pattern classification apparatus 有权
    参数学习方法，参数学习装置，模式分类方法和模式分类装置

    公开(公告)号：US07958070B2

    公开(公告)日：2011-06-07

    申请号：US11769143

    申请日：2007-06-27

    申请人： Yusuke Mitarai ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Kan Torii ,  Hiroshi Sato

    发明人： Yusuke Mitarai ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Kan Torii ,  Hiroshi Sato

    IPC分类号： G06F15/18

    CPC分类号： G06K9/00288 ,  G06K9/00228 ,  G06K9/00248 ,  G06K9/6232 ,  G06K9/6256 ,  G06K9/6269

    摘要： A plurality of pieces of learning data, each associated with a class to which the piece of the learning data belong, are input. In each piece of the learning data, a statistical amount of attribute values of elements in each of specific k parts, k being equal to or larger than 1, is calculated. Each piece of the learning data is mapped in a k-dimensional feature space as a vector having the calculated k statistics amounts as elements. Based on each piece of the mapped learning data and the classes to which the pieces of learning data belong, parameters for classifying input data into one of the plurality of classes are learned in the k-dimensional feature space. By using the parameters, pattern classification can be performed with high speed and high accuracy.

    摘要翻译： 输入与学习数据所属的类别相关联的多条学习数据。 在每个学习数据中，计算k个等于或大于1的特定k个部分中的每个元素的属性值的统计量。 每个学习数据被映射到k维特征空间中，作为具有计算的k个统计量的向量作为元素。 基于映射的学习数据和学习数据所属的类别，在k维特征空间中学习用于将输入数据分类为多个类中的一个的参数。 通过使用参数，可以高速，高精度地执行模式分类。

    Learning apparatus for pattern detector, learning method and computer-readable storage medium
    8.
    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。

    METHOD AND APPARATUS FOR DETECTING AND PROCESSING SPECIFIC PATTERN FROM IMAGE
    9.
    发明申请
    METHOD AND APPARATUS FOR DETECTING AND PROCESSING SPECIFIC PATTERN FROM IMAGE 审中-公开
    用于从图像中检测和处理特定图案的方法和装置

    公开(公告)号：US20120275650A1

    公开(公告)日：2012-11-01

    申请号：US13546355

    申请日：2012-07-11

    申请人： Kan Torii ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Hiroshi Sato ,  Yusuke Mitarai

    发明人： Kan Torii ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Hiroshi Sato ,  Yusuke Mitarai

    IPC分类号： G06K9/46 ,  G06K9/00

    CPC分类号： G06K9/00234 ,  G06K2209/011 ,  H04N5/23219

    摘要： In an image within which a face pattern is detected, when a ratio of a skin color pixel is equal to or smaller than a first threshold value in a first region and a ratio of a skin color pixel is equal to or greater than a second threshold value in a second r region, the vicinity of the first region is determined to be a face candidate position at which the face pattern can exist. Face detection is carried out on the face candidate position. The second region is arranged in a predetermined position relative to the first region.

    摘要翻译： 在其中检测到面部图案的图像中，当皮肤颜色像素的比例在第一区域中等于或小于第一阈值并且皮肤颜色像素的比率等于或大于第二阈值时 在第二r区域中，第一区域附近被确定为可以存在脸部图案的面部候选位置。 脸部检测在脸部候选位置进行。 第二区域相对于第一区域布置在预定位置。

    Method and apparatus for detecting and processing specific pattern from image
    10.
    发明授权
    Method and apparatus for detecting and processing specific pattern from image 有权
    用于从图像中检测和处理特定图案的方法和装置

    公开(公告)号：US08265350B2

    公开(公告)日：2012-09-11

    申请号：US11951809

    申请日：2007-12-06

    申请人： Kan Torii ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Hiroshi Sato ,  Yusuke Mitarai

    发明人： Kan Torii ,  Masakazu Matsugu ,  Katsuhiko Mori ,  Hiroshi Sato ,  Yusuke Mitarai

    IPC分类号： G06K9/00 ,  G06K9/46 ,  G06K9/66

    CPC分类号： G06K9/00234 ,  G06K2209/011 ,  H04N5/23219

    摘要： In an image within which a face pattern is detected, when a ratio of a skin color pixel is equal to or smaller than a first threshold value in a first region and a ratio of a skin color pixel is equal to or greater than a second threshold value in a second r region, the vicinity of the first region is determined to be a face candidate position at which the face pattern can exist. Face detection is carried out on the face candidate position. The second region is arranged in a predetermined position relative to the first region.

    摘要翻译： 在其中检测到面部图案的图像中，当皮肤颜色像素的比例在第一区域中等于或小于第一阈值并且皮肤颜色像素的比率等于或大于第二阈值时 在第二r区域中，第一区域附近被确定为可以存在脸部图案的面部候选位置。 脸部检测在脸部候选位置进行。 第二区域相对于第一区域布置在预定位置。