公开(公告)号：US08401313B2

公开(公告)日：2013-03-19

申请号：US12262052

申请日：2008-10-30

申请人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito ,  Katsuhiko Mori

发明人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito ,  Katsuhiko Mori

IPC分类号： G06K9/68 ,  G06K9/70

CPC分类号： G06K9/00228 ,  G06K9/6256 ,  G06K9/6282

摘要： An image processing method is provided for an image processing apparatus which executes processing by allocating a plurality of weak discriminators to form a tree structure having branches corresponding to types of objects so as to detect objects included in image data. Each weak discriminator calculates a feature amount to be used in a calculation of an evaluation value of the image data, and discriminates whether or not the object is included in the image data by using the evaluation value. The weak discriminator allocated to a branch point in the tree structure further selects a branch destination using at least some of the feature amounts calculated by weak discriminators included in each branch destination.

摘要翻译： 为图像处理装置提供一种图像处理方法，该图像处理装置通过分配多个弱鉴别器来形成具有与对象类型相对应的分支的​​树结构，从而检测包括在图像数据中的对象来执行处理。 每个弱识别器计算要在图像数据的评估值的计算中使用的特征量，并且通过使用评估值来区分对象是否包括在图像数据中。 分配给树结构中的分支点的弱鉴别器还使用由每个分支目的地中包括的弱鉴别器计算的特征量中的至少一些特征量来选择分支目的地。

公开(公告)号：US08385649B2

公开(公告)日：2013-02-26

申请号：US12765190

申请日：2010-04-22

申请人： Masami Kato ,  Yoshinori Ito ,  Osamu Nomura ,  Takahisa Yamamoto

发明人： Masami Kato ,  Yoshinori Ito ,  Osamu Nomura ,  Takahisa Yamamoto

IPC分类号： G06K9/62

CPC分类号： G06K9/6257 ,  G06K9/00986 ,  G06K9/4604 ,  G06K9/4614

摘要： Learning is sequentially executed with respect to weak discriminators based on learning data held in a storage device. Upon learning, an evaluation value for the weak discriminator is calculated. It is discriminated, based on a shift of the evaluation value, whether or not the learning is overlearning. If it is discriminated that the learning is overlearning, new learning data is added. Thus, the overlearning is easily detected and the learning is efficiently executed.

摘要翻译： 基于保存在存储装置中的学习数据，相对于弱识别器依次执行学习。 在学习时，计算弱鉴别器的评估值。 基于评估值的转移，是否对学习过度学习进行歧视。 如果歧视学习过度学习，则添加新的学习数据。 因此，容易检测到过度学习，并且有效地执行学习。

公开(公告)号：US20110150341A1

公开(公告)日：2011-06-23

申请号：US12966725

申请日：2010-12-13

申请人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito

发明人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito

IPC分类号： G06K9/46

CPC分类号： G06K9/4604 ,  G06K2009/4666

摘要： An image processing apparatus includes a comparison unit that selects a pixel of interest in a processing image, and compare magnitudes of luminance value of the pixel of interest and luminance value of each of a plurality of neighboring pixels having a predetermined positional relationship with the pixel of interest; a calculation unit that calculates a feature amount of the pixel of interest based on the predetermined positional relationship between the pixel of interest and each of the plurality of neighboring pixels and a comparison result obtained by the comparison unit. For two neighboring pixels at positions which are point symmetrical with respect to the pixel of interest, the comparison unit sets that only one of the two neighboring pixels has the predetermined positional relationship.

摘要翻译： 一种图像处理装置，包括：比较单元，其选择处理图像中的感兴趣像素，并将感兴趣像素的亮度值的大小与具有预定位置关系的多个相邻像素的亮度值与 利益; 计算单元，其基于所述关注像素和所述多个相邻像素中的每一个之间的预定位置关系以及由所述比较单元获得的比较结果来计算所述感兴趣像素的特征量。 对于相对于感兴趣像素点对称的位置处的两个相邻像素，比较单元设置两个相邻像素中只有一个具有预定的位置关系。

公开(公告)号：US20110081089A1

公开(公告)日：2011-04-07

申请号：US12963568

申请日：2010-12-08

申请人： Katsuhiko Mori ,  Masami Kato ,  Yoshinori Ito ,  Takahisa Yamamoto

发明人： Katsuhiko Mori ,  Masami Kato ,  Yoshinori Ito ,  Takahisa Yamamoto

IPC分类号： G06K9/68

CPC分类号： G06K9/00281

摘要： Even when a local area is varied, degradation in recognition accuracy and detection accuracy is suppressed. To that end, a pattern processing apparatus includes a reference local area setting portion 1802 for setting a reference local area based on the detection result of a feature point by a face organ feature point detecting portion 101, a varied local area generating portion 1803 for generating a plurality of varied local area patterns by referring to an image area near the reference local area, a similarity calculating portion 106 for calculating similarities in the reference local areas and in the varied local area patterns between the input pattern and the registered pattern, a representative similarity calculating portion 107 for calculating representative similarity from among the similarities, and a classifying portion 109 for determining a class to which the input pattern belongs.

摘要翻译： 即使局部区域变化，也能够抑制识别精度和检测精度的劣化。 为此，图案处理装置包括：基准局部区域设定部1802，用于基于面部特征点检测部101的特征点的检测结果来设定基准局部区域;变化的局部区域生成部1803， 通过参考参考局部区域附近的图像区域的多个变化的局部区域图案，计算参考局部区域和输入图案与登记图案之间的变化的局部区域图案中的相似度的相似度计算部分106， 相似度计算部分107，用于从相似度中计算代表性相似度;以及分类部分109，用于确定输入模式所属的类别。

公开(公告)号：US20100209010A1

公开(公告)日：2010-08-19

申请号：US12682028

申请日：2008-10-29

申请人： Masami Kato ,  Takahisa Yamamoto ,  Yoshinori Ito

发明人： Masami Kato ,  Takahisa Yamamoto ,  Yoshinori Ito

IPC分类号： G06K9/68

CPC分类号： G06K9/6257 ,  G06K9/00973

摘要： In an information processing apparatus that processes data using cascade-connected weak classifiers, processing specification information specifying the processing content of each of the weak classifiers is stored. The weak classifiers to be used in processing the data are selected from the weak classifiers by referring to a table in which is specified information for determining the weak classifiers to be used based on a condition for processing the data. The data is then processed by the selected weak classifiers based on the processing specification information that corresponds to those weak classifiers, and an object is extracted from the data using an obtained evaluation value. Through this, a combination of extraction process speed and extraction accuracy can be changed in a flexible manner when extracting a specific object from image data.

摘要翻译： 在使用级联连接的弱分类器处理数据的信息处理装置中，存储指定每个弱分类器的处理内容的处理规范信息。 用于处理数据的弱分类器通过参照其中指定的用于确定用于处理数据的条件的弱分类器的指定信息的表，从弱分类器中选择。 然后基于与这些弱分类器对应的处理规范信息，由所选择的弱分类器处理数据，并且使用获得的评估值从数据中提取对象。 通过这种方式，当从图像数据中提取特定对象时，提取处理速度和提取精度的组合可以灵活地改变。

公开(公告)号：US08655057B2

公开(公告)日：2014-02-18

申请号：US12682028

申请日：2008-10-29

申请人： Masami Kato ,  Takahisa Yamamoto ,  Yoshinori Ito

发明人： Masami Kato ,  Takahisa Yamamoto ,  Yoshinori Ito

IPC分类号： G06K9/46 ,  G06K9/62 ,  G06E1/00

CPC分类号： G06K9/6257 ,  G06K9/00973

摘要： In an information processing apparatus that processes data using cascade-connected weak classifiers, processing specification information specifying the processing content of each of the weak classifiers is stored. The weak classifiers to be used in processing the data are selected from the weak classifiers by referring to a table in which is specified information for determining the weak classifiers to be used based on a condition for processing the data. The data is then processed by the selected weak classifiers based on the processing specification information that corresponds to those weak classifiers, and an object is extracted from the data using an obtained evaluation value. Through this, a combination of extraction process speed and extraction accuracy can be changed in a flexible manner when extracting a specific object from image data.

摘要翻译： 在使用级联连接的弱分类器处理数据的信息处理装置中，存储指定每个弱分类器的处理内容的处理规范信息。 用于处理数据的弱分类器通过参照其中指定的用于确定用于处理数据的条件的弱分类器的指定信息的表，从弱分类器中选择。 然后基于与这些弱分类器对应的处理规范信息，由所选择的弱分类器处理数据，并且使用获得的评估值从数据中提取对象。 通过这种方式，当从图像数据中提取特定对象时，提取处理速度和提取精度的组合可以灵活地改变。

公开(公告)号：US08515180B2

公开(公告)日：2013-08-20

申请号：US12974633

申请日：2010-12-21

申请人： Masami Kato ,  Yoshinori Ito ,  Takahisa Yamamoto

发明人： Masami Kato ,  Yoshinori Ito ,  Takahisa Yamamoto

IPC分类号： G06K9/46

CPC分类号： G06K9/00281 ,  G06K9/03 ,  G06T1/00

摘要： A data correction apparatus which corrects data associated with an image of an object projects vector data obtained by connecting data to be corrected to each other onto a subspace to generate a dimensionally reduced projection vector, and executes dimension restoration processing in which the dimensionality of the projection vector is restored to generate dimensionally restored vector data, thereby generating a plurality of dimensionally restored vector data for each type of fluctuation. The data correction apparatus determines the fluctuation of the object based on the projection vector, integrates the plurality of dimensionally restored vector data with each other based on the determination result, and outputs the integration result as corrected data.

摘要翻译： 一种数据校正装置，其校正与对象的图像相关联的数据，通过将要被校正的数据相互连接获得的向量数据投射到子空间上，以生成尺寸减小的投影向量，并执行尺寸恢复处理，其中投影的维度 向量被恢复以生成尺寸恢复的矢量数据，从而为每种类型的波动产生多个维度恢复的矢量数据。 数据校正装置基于投影向量来确定对象的波动，基于确定结果将多个尺寸恢复的矢量数据相互积分，并将积分结果作为校正数据输出。

公开(公告)号：US08385631B2

公开(公告)日：2013-02-26

申请号：US13155640

申请日：2011-06-08

申请人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito

发明人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito

IPC分类号： G06K9/62

CPC分类号： G06N3/08

摘要： A calculation processing apparatus, which executes calculation processing based on a network composed by hierarchically connecting a plurality of processing nodes, assigns a partial area of a memory to each of the plurality of processing nodes, stores a calculation result of a processing node in a storable area of the partial area assigned to that processing node, and sets, as storable areas, areas that store the calculation results whose reference by all processing nodes connected to the subsequent stage of that processing node is complete. The apparatus determines, based on the storage states of calculation results in partial areas of the memory assigned to the processing node designated to execute the calculation processing of the processing nodes, and to processing nodes connected to the previous stage of the designated processing node, whether or not to execute a calculation of the designated processing node.

摘要翻译： 执行基于通过分层连接多个处理节点组成的网络的计算处理的计算处理装置，将多个处理节点中的每个处理节点的存储器的部分区域分配，将处理节点的计算结果存储在可存储 分配给该处理节点的部分区域的区域，并且存储存储连接到该处理节点的后续阶段的所有处理节点的参考的计算结果的存储区域。 该装置基于分配给指定用于执行处理节点的计算处理的处理节点的存储器的部分区域中的计算结果的存储状态以及连接到指定处理节点的前一级的处理节点，确定是否 或者不执行指定的处理节点的计算。

公开(公告)号：US20110239224A1

公开(公告)日：2011-09-29

申请号：US13155640

申请日：2011-06-08

申请人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito

发明人： Takahisa Yamamoto ,  Masami Kato ,  Yoshinori Ito

IPC分类号： G06F9/46

CPC分类号： G06N3/08

摘要： A calculation processing apparatus, which executes calculation processing based on a network composed by hierarchically connecting a plurality of processing nodes, assigns a partial area of a memory to each of the plurality of processing nodes, stores a calculation result of a processing node in a storable area of the partial area assigned to that processing node, and sets, as storable areas, areas that store the calculation results whose reference by all processing nodes connected to the subsequent stage of that processing node is complete. The apparatus determines, based on the storage states of calculation results in partial areas of the memory assigned to the processing node designated to execute the calculation processing of the processing nodes, and to processing nodes connected to the previous stage of the designated processing node, whether or not to execute a calculation of the designated processing node.

摘要翻译： 执行基于通过分层连接多个处理节点组成的网络的计算处理的计算处理装置，将多个处理节点中的每个处理节点的存储器的部分区域分配，将处理节点的计算结果存储在可存储 分配给该处理节点的部分区域的区域，并且存储存储连接到该处理节点的后续阶段的所有处理节点的参考的计算结果的存储区域。 该装置基于分配给指定用于执行处理节点的计算处理的处理节点的存储器的部分区域中的计算结果的存储状态以及连接到指定处理节点的前一级的处理节点，确定是否 或者不执行指定的处理节点的计算。

公开(公告)号：US20110239032A1

公开(公告)日：2011-09-29

申请号：US13132316

申请日：2009-12-03

申请人： Masami Kato ,  Takahisa Yamamoto ,  Yoshinori Ito

发明人： Masami Kato ,  Takahisa Yamamoto ,  Yoshinori Ito

IPC分类号： G06F1/14

CPC分类号： G06N3/06 ,  G06F17/15 ,  G06K9/00281 ,  G06K9/6217 ,  G06N3/063 ,  G06N5/02 ,  G06T1/00

摘要： In a convolution operation circuit, a first and a second shift registers provide data to a first and a second inputs of a plurality of multipliers, a first and a second storage units store data to be supplied to the first and the second shift registers, a plurality of cumulative adders accumulate output from the plurality of multipliers, a third storage unit latches output from the plurality of cumulative adders at predetermined timing, a fourth storage unit stores data to be stored in the first and the second storage units and data output from the third storage unit, and a control unit sets data stored in the first and the second storage units to the first and the second shift registers at predetermined timing, causes the first and the second shift registers to perform shift operations in synchronization with an operation of the cumulative adder.

摘要翻译： 在卷积运算电路中，第一和第二移位寄存器向多个乘法器的第一和第二输入提供数据，第一和第二存储单元存储要提供给第一和第二移位寄存器的数据， 多个累积加法器累积来自多个乘法器的输出，第三存储单元以预定定时锁存多个累积加法器的输出，第四存储单元存储要存储在第一和第二存储单元中的数据以及从 第三存储单元和控制单元以预定定时将存储在第一和第二存储单元中的数据设置到第一和第二移位寄存器，使得第一和第二移位寄存器与第一和第二移位寄存器的操作同步地执行移位操作 累加器。