专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US07672920B2 Apparatus and method for embedding recurrent neural networks into the nodes of a self-organizing map 有权
标题翻译：将循环神经网络嵌入到自组织图的节点中的装置和方法
公开(公告)号：US07672920B2
公开(公告)日：2010-03-02
申请号：US11699428
申请日：2007-01-30
申请人： Masato Ito , Katsuki Minamino , Yukiko Yoshiike , Hirotaka Suzuki , Kenta Kawamoto
发明人： Masato Ito , Katsuki Minamino , Yukiko Yoshiike , Hirotaka Suzuki , Kenta Kawamoto
IPC分类号： G06N5/00
CPC分类号： G06K9/00536 , G06K9/00335 , G06N3/0445 , G06N99/005
摘要： A learning system is provided, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics; and learning means for self-organizationally updating the dynamics of the network on the basis of measured time-series data.
摘要翻译：提供了一种学习系统，其包括用于存储包括多个节点的网络的网络存储装置，每个节点保持动态; 以及基于测量的时间序列数据自组织地更新网络动态的学习手段。

52. 发明授权

US07627178B2 Image recognition device using feature points, method for recognizing images using feature points, and robot device which recognizes images using feature points 有权
标题翻译：使用特征点的图像识别装置，使用特征点识别图像的方法，以及使用特征点识别图像的机器人装置
公开(公告)号：US07627178B2
公开(公告)日：2009-12-01
申请号：US10517615
申请日：2004-04-22
申请人： Hirotaka Suzuki , Kohtaro Sabe , Masahiro Fujita
发明人： Hirotaka Suzuki , Kohtaro Sabe , Masahiro Fujita
IPC分类号： G06K9/46
CPC分类号： G06K9/6212 , G06K9/4609 , G06K9/6211 , G06T7/73
摘要： In an image recognition apparatus, feature point extraction sections and extract feature points from a model image and an object image. Feature quantity retention sections extract a feature quantity for each of the feature points and retain them along with positional information of the feature points. A feature quantity comparison section compares the feature quantities with each other to calculate the similarity or the dissimilarity and generates a candidate-associated feature point pair having a high possibility of correspondence. A model attitude estimation section repeats an operation of projecting an affine transformation parameter determined by three pairs randomly selected from the candidate-associated feature point pair group onto a parameter space. The model attitude estimation section assumes each member in a cluster having the largest number of members formed in the parameter space to be an inlier. The model attitude estimation section finds the affine transformation parameter according to the least squares estimation using the inlier and outputs a model attitude determined by this affine transformation parameter.
摘要翻译：在图像识别装置中，特征点提取部分并从模型图像和对象图像中提取特征点。特征量保留部分提取每个特征点的特征量，并将其与特征点的位置信息一起保留。特征量比较部分将特征量彼此进行比较以计算相似度或相似性，并生成具有高对应可能性的候选相关特征点对。模型姿态估计部重复将从候选关联特征点对组中随机选择的三对决定的仿射变换参数投影到参数空间的动作。模型姿态估计部分假设在参数空间中形成的具有最大数量的成员的群组中的每个成员是一个较早的。模型姿态估计部根据使用该误差的最小二乘估计求出仿射变换参数，并输出由该仿射变换参数确定的模型姿态。

53. 发明申请

US20090041340A1 Image Processing System, Learning Device and Method, and Program 有权
标题翻译：图像处理系统，学习装置和方法以及程序
公开(公告)号：US20090041340A1
公开(公告)日：2009-02-12
申请号：US11813404
申请日：2005-12-26
申请人： Hirotaka Suzuki , Akira Nakamura , Takayuki Yoshigahara , Kohtaro Sabe , Masahiro Fujita
发明人： Hirotaka Suzuki , Akira Nakamura , Takayuki Yoshigahara , Kohtaro Sabe , Masahiro Fujita
IPC分类号： G06K9/46
CPC分类号： G06K9/00288 , G06K9/6211 , G06K9/623 , G06T7/00
摘要： The present invention relates to an image processing system, a learning device and method, and a program which enable easy extraction of feature amounts to be used in a recognition process. Feature points are extracted from a learning-use model image, feature amounts are extracted based on the feature points, and the feature amounts are registered in a learning-use model dictionary registration section 23. Similarly, feature points are extracted from a learning-use input image containing a model object contained in the learning-use model image, feature amounts are extracted based on these feature points, and these feature amounts are compared with the feature amounts registered in a learning-use model registration section 23. A feature amount that has formed a pair the greatest number of times as a result of the comparison is registered in the model dictionary registration section 12 as the feature amount to be used in the recognition process. The present invention is applicable to a robot.
摘要翻译：本发明涉及图像处理系统，学习装置和方法以及能够容易地提取在识别处理中使用的特征量的程序。从学习用模型图像提取特征点，基于特征点提取特征量，并且将特征量登记在学习用模型字典注册部23中。同样，从学习用途中提取特征点基于这些特征点提取含有包含在学习用模型图像中的模型对象的输入图像，并将这些特征量与在学习用模型登记部23中登记的特征量进行比较。特征量作为比较的结果，在模型字典登记部12中登记了作为识别处理中使用的特征量的最大次数的对。本发明可应用于机器人。

54. 发明申请

US20070239644A1 Learning apparatus, learning method, and program 失效
标题翻译：学习机器，学习方法和程序
公开(公告)号：US20070239644A1
公开(公告)日：2007-10-11
申请号：US11732773
申请日：2007-04-04
申请人： Katsuki Minamino , Masato Ito , Kenta Kawamoto , Yukiko Yoshiike , Hirotaka Suzuki
发明人： Katsuki Minamino , Masato Ito , Kenta Kawamoto , Yukiko Yoshiike , Hirotaka Suzuki
IPC分类号： G06N3/00
CPC分类号： G06N99/005 , G06N3/0445 , G06N3/0454 , G06N3/084
摘要： A learning apparatus includes a storage unit configured to store a network formed by a plurality of nodes each holding dynamics; a learning unit configured to learn the dynamics of the network in a self-organizing manner on the basis of observed time-series data; a winner-node determiner configured to determine a winner node, the winner node being a node having dynamics that best match the time-series data; and a weight determiner configured to determine learning weights for the dynamics held by the individual nodes according to distances of the individual nodes from the winner node. The learning unit is configured to learn the dynamics of the network in a self-organizing manner by degrees corresponding to the learning weights.
摘要翻译：学习装置包括：存储单元，被配置为存储由保持动态的多个节点形成的网络; 学习单元，被配置为基于观察到的时间序列数据以自组织的方式学习网络的动态; 获胜者节点确定器，被配置为确定胜者节点，胜者节点是具有与时间序列数据最佳匹配的动态的节点; 以及权重确定器，被配置为根据各个节点与胜利者节点的距离来确定由各个节点保持的动态的学习权重。学习单元被配置为以自组织的方式以对应于学习权重的度学习网络的动态。

55. 发明授权

US06696541B1 Method for crystallization of low molecular weight polycarbonate and method for preparing polycarbonate resin from it 失效
标题翻译：低分子量聚碳酸酯的结晶方法及其制备聚碳酸酯树脂的方法
公开(公告)号：US06696541B1
公开(公告)日：2004-02-24
申请号：US10088590
申请日：2002-03-21
申请人： Tomonori Sakurai , Nobuaki Kido , Shunichi Matsumura , Toyoaki Ishiwata , Kazuteru Kohno , Hirotaka Suzuki , Hironori Haga , Toru Hikosaka
发明人： Tomonori Sakurai , Nobuaki Kido , Shunichi Matsumura , Toyoaki Ishiwata , Kazuteru Kohno , Hirotaka Suzuki , Hironori Haga , Toru Hikosaka
IPC分类号： C08G6400
CPC分类号： C08G64/20 , C08G64/40
摘要： A method for crystallizing a low molecular weight aromatic polycarbonate effectively and a method for preparing a polycarbonate resin having a desired intrinsic viscosity by using the polycarbonate crystallized with the above method of crystallization. A low molecular weight aromatic polycarbonate (preferably, the one produced by melt polycondensation) is crystallized by bringing it into contact with an aromatic monohydroxy compound or a mixture of said compound and water. Or, a low molecular weight aromatic polycarbonate is melt mixed with at least one or more kinds of compounds selected from the group consisting of aromatic monohydroxy compounds, carbonic acid diester compounds and aromatic dihydroxy compounds to crystallize the low molecular weight aromatic polycarbonate. The crystallized product is heated at a temperature lower than its melting point under reduced pressure or in an inert gas flow to convert it into a high polymerized state. Thus, a polycarbonate resin having a desired intrinsic viscosity is prepared.
摘要翻译：一种低分子量芳族聚碳酸酯的有效结晶方法以及通过使用通过上述结晶方法结晶的聚碳酸酯制备具有所需特性粘度的聚碳酸酯树脂的方法。低分子量芳族聚碳酸酯（优选通过熔体缩聚）通过使其与芳族单羟基化合物或所述化合物和水的混合物接触而结晶。或者，将低分子量芳族聚碳酸酯与至少一种选自芳族单羟基化合物，碳酸二酯化合物和芳族二羟基化合物的化合物熔融混合，以使低分子量芳族聚碳酸酯结晶。将结晶产物在低于其熔点的温度下在减压或惰性气体流中加热以将其转化为高聚合状态。因此，制备具有所需特性粘度的聚碳酸酯树脂。

56. 发明授权

US6085279A Interrupt control system provided in a computer 失效
标题翻译：计算机中提供的中断控制系统
公开(公告)号：US6085279A
公开(公告)日：2000-07-04
申请号：US33629
申请日：1998-03-04
申请人： Hirotaka Suzuki
发明人： Hirotaka Suzuki
IPC分类号： G06F9/46 , G06F9/48 , G06F13/24 , G06F13/26
CPC分类号： G06F13/24
摘要： An interrupt control system is provided in a computer having a processor, a PCI bus, an ISA bus, and a serial transfer line. An interrupt controller outputs interrupt requests to the processor according to the priority levels of signals received from the PCI bus and the ISA bus. Interrupt signals supplied to the interrupt controller from the PCI bus and ISA bus are mapped to a level appropriate for the interrupt controller.
摘要翻译：在具有处理器，PCI总线，ISA总线和串行传输线的计算机中提供中断控制系统。中断控制器根据从PCI总线和ISA总线接收到的信号的优先级别向处理器输出中断请求。从PCI总线和ISA总线提供给中断控制器的中断信号映射到适合中断控制器的电平。

57. 发明授权

US08582887B2 Image processing system, learning device and method, and program 有权
标题翻译：图像处理系统，学习装置和方法，程序
公开(公告)号：US08582887B2
公开(公告)日：2013-11-12
申请号：US11813404
申请日：2005-12-26
申请人： Hirotaka Suzuki , Akira Nakamura , Takayuki Yoshigahara , Kohtaro Sabe , Masahiro Fujita
发明人： Hirotaka Suzuki , Akira Nakamura , Takayuki Yoshigahara , Kohtaro Sabe , Masahiro Fujita
IPC分类号： G06K9/00
CPC分类号： G06K9/00288 , G06K9/6211 , G06K9/623 , G06T7/00
摘要： The present invention relates to an image processing system, a learning device and method, and a program which enable easy extraction of feature amounts to be used in a recognition process. Feature points are extracted from a learning-use model image, feature amounts are extracted based on the feature points, and the feature amounts are registered in a learning-use model dictionary registration section 23. Similarly, feature points are extracted from a learning-use input image containing a model object contained in the learning-use model image, feature amounts are extracted based on these feature points, and these feature amounts are compared with the feature amounts registered in a learning-use model registration section 23. A feature amount that has formed a pair the greatest number of times as a result of the comparison is registered in the model dictionary registration section 12 as the feature amount to be used in the recognition process. The present invention is applicable to a robot.
摘要翻译：本发明涉及图像处理系统，学习装置和方法以及能够容易地提取在识别处理中使用的特征量的程序。从学习用模型图像提取特征点，基于特征点提取特征量，并且将特征量登记在学习用模型字典注册部23中。同样，从学习用途中提取特征点基于这些特征点提取含有包含在学习用模型图像中的模型对象的输入图像，并将这些特征量与在学习用模型登记部23中登记的特征量进行比较。特征量作为比较的结果，在模型字典登记部12中登记了作为识别处理中使用的特征量的最大次数的对。本发明可应用于机器人。

58. 发明申请

US20130163860A1 Information Processing Device, Information Processing Method and Program 有权
标题翻译：信息处理装置，信息处理方法和程序
公开(公告)号：US20130163860A1
公开(公告)日：2013-06-27
申请号：US13814170
申请日：2011-08-02
申请人： Hirotaka Suzuki , Masato Ito
发明人： Hirotaka Suzuki , Masato Ito
IPC分类号： G06K9/18
CPC分类号： G06K9/00718 , G06F17/30796 , G06F17/30843 , G06F17/30852 , G06K9/18 , G06K2209/27
摘要： The present invention relates to an information processing device, an information processing method, and a program capable of easily adding an annotation to content.A feature amount extracting unit 21 extracts an image feature amount of each frame of an image of learning content and extracts word frequency information regarding frequency of appearance of each word in a description text describing a content of the image of the learning content (for example, a text of a caption) as a text feature amount of the description text. A model learning unit 22 learns an annotation model, which is a multi-stream HMM, by using an annotation sequence for annotation, which is a multi-stream including the image feature amount of each frame and the text feature amount. The present invention may be applied when adding the annotation to the content such as a television broadcast program, for example.
摘要翻译：本发明涉及一种信息处理设备，信息处理方法和能够容易地向内容添加注释的程序。特征量提取单元21提取学习内容的图像的每帧的图像特征量，并且提取关于描述学习内容的图像的内容的描述文本中的每个单词的出现频率的词频信息（例如，文字的文本）作为描述文本的文本特征量。模型学习单元22通过使用注释的注释序列来学习作为多流HMM的注释模型，注释序列是包括每个帧的图像特征量和文本特征量的多流。例如，当将注释添加到诸如电视广播节目的内容时，可以应用本发明。

59. 发明授权

US08457469B2 Display control device, display control method, and program 有权
标题翻译：显示控制装置，显示控制方式和程序
公开(公告)号：US08457469B2
公开(公告)日：2013-06-04
申请号：US13000803
申请日：2010-04-22
申请人： Hirotaka Suzuki
发明人： Hirotaka Suzuki
IPC分类号： H04N9/80
CPC分类号： G06K9/00711 , G11B27/105 , G11B27/28 , H04N5/765
摘要： The present invention relates to a display control device, a display method, and a program, whereby a new thumbnail method can be provided.A clustering unit 611 subjects each frame of a content to clustering into any cluster of a plurality of clusters, and a scene classifying unit 612 classifies, regarding each of a plurality of clusters, a frame belonging to a cluster into a scene that is a group of one or more frames that temporally continue. A thumbnail creating unit 613 creates the thumbnail of a scene, and a display control unit 614 displays the thumbnail thereof on a display device 603.
摘要翻译：显示控制装置，显示方法和程序技术领域本发明涉及一种可以提供新的缩略图方法的显示控制装置，显示方法和程序。聚类单元611使内容的每一帧对多个聚类中的任何一个聚类进行聚类，并且场景分类单元612将属于聚类的每一个集合中的每一个分类为作为组的场景一个或多个帧暂时继续。缩略图创建单元613创建场景的缩略图，并且显示控制单元614将其缩略图显示在显示设备603上。

60. 发明申请

US20130054166A1 INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM 审中-公开
标题翻译：信息处理设备，信息处理方法和程序
公开(公告)号：US20130054166A1
公开(公告)日：2013-02-28
申请号：US13571719
申请日：2012-08-10
申请人： Hirotaka Suzuki , Kenta Kawamoto
发明人： Hirotaka Suzuki , Kenta Kawamoto
IPC分类号： G06F19/00 , G01R21/00
CPC分类号： G06Q50/06 , H02J2003/007 , Y02E60/76 , Y04S40/22
摘要： In some embodiments, a system comprising a first and a second computing device is disclosed. The first computing device, comprising at least one processor, is configured to obtain, from a second computing device, data related to power consumption by at least a first electrical device located in a first region of a plurality of regions, and classify the first region, based at least in part on the obtained data, into a first group of regions of a plurality of groups of regions. The second computing device, comprising at least another processor, is configured to transmit, to the first computing device, the data related to power consumption by at least the first electrical device, and receive, from the first computing device information related to power consumption by a second electrical device located in a second region, wherein the second region is in the first group of regions.
摘要翻译：在一些实施例中，公开了包括第一和第二计算设备的系统。包括至少一个处理器的第一计算设备被配置为从第二计算设备获得与位于多个区域的第一区域中的至少第一电气设备相关的功耗的数据，并且将第一区域至少部分地基于所获得的数据，转换成多组区域的第一组区域。包括至少另一个处理器的第二计算设备经配置以向至少第一电气设备向第一计算设备发送与功耗有关的数据，并且从第一计算设备接收与功率消耗相关的信息，位于第二区域中的第二电气设备，其中所述第二区域处于所述第一组区域中。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式