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。

公开(公告)号：US08405712B2

公开(公告)日：2013-03-26

申请号：US12233693

申请日：2008-09-19

申请人： Tsukasa Ike ,  Yasukazu Okamoto ,  Satoru Ishigaki ,  Kei Sakamoto ,  Masahiro Fujita ,  Hisashi Kazama

发明人： Tsukasa Ike ,  Yasukazu Okamoto ,  Satoru Ishigaki ,  Kei Sakamoto ,  Masahiro Fujita ,  Hisashi Kazama

IPC分类号： H04N7/18 ,  G06K9/00

CPC分类号： G06F3/017 ,  G06F3/012 ,  G06K9/00355

摘要： A gesture recognition apparatus including a detector, a controller and a gesture recognizer, and is able to detect a portion to be detected using an image captured at a first resolution without reducing the number of images to be entered per unit of time to an object detector by detecting an auxiliary portion instead when the portion to be detected is not detected at a second resolution, estimating the position of the auxiliary portion based on the position of the auxiliary portion, and extracting the periphery thereof from the image captured at the first resolution.

摘要翻译： 一种手势识别装置，包括检测器，控制器和手势识别器，并且能够使用以第一分辨率捕获的图像来检测要检测的部分，而不会将每单位时间输入的图像数量减少到对象检测器 通过在第二分辨率下未检测到要检测的部分的情况下检测辅助部分，基于辅助部分的位置估计辅助部分的位置，并且从以第一分辨率捕获的图像中提取其外围。

公开(公告)号：US08185336B2

公开(公告)日：2012-05-22

申请号：US12261062

申请日：2008-10-30

申请人： Yasuo Furukawa ,  Goerschwin Fey ,  Satoshi Komatsu ,  Masahiro Fujita

发明人： Yasuo Furukawa ,  Goerschwin Fey ,  Satoshi Komatsu ,  Masahiro Fujita

IPC分类号： G01R31/00 ,  G01R31/14 ,  G01R31/28

CPC分类号： G01R31/318307 ,  G01R31/3008 ,  G01R31/318342

摘要： Provided is a test apparatus that tests a device under test, including a vector expanding section that sequentially generates a plurality of test vectors; a predicting section that calculates a predicted value for each test vector by simulating an operation of the device under test, the predicted value indicating a prescribed characteristic value of the device under test to be measured while the device under test is supplied with a test signal corresponding to the test vector; a measuring section that obtains a measured value for each test vector by measuring the prescribed characteristic value of the device under test each time the device under test is supplied with a test vector; and a judging section that judges whether the device under test is defective based on a ratio between the predicted value and the measured value corresponding to each test vector.

摘要翻译： 提供了一种测试被测设备的测试设备，包括顺序地产生多个测试向量的向量扩展部分; 预测部，其通过模拟被测设备的动作来计算各测试矢量的预测值，所述预测值表示被测设备被测试设备的规定特征值，所述预测值被提供有对应的测试信号 到测试矢量; 测量部，其通过在每次向被测试装置供给测试矢量时，测量被测设备的规定特征值，求出各测试矢量的测量值; 以及判断部，其基于预测值和与各测试矢量对应的测量值之间的比率来判定被测设备是否有缺陷。

公开(公告)号：US07251606B2

公开(公告)日：2007-07-31

申请号：US10296403

申请日：2002-03-26

申请人： Rika Horinaka ,  Masahiro Fujita ,  Atsushi Okubo ,  Kenta Kawamoto ,  Gabriel Costa ,  Masaki Fukuchi ,  Osamu Hanagata ,  Kotaro Sabe

发明人： Rika Horinaka ,  Masahiro Fujita ,  Atsushi Okubo ,  Kenta Kawamoto ,  Gabriel Costa ,  Masaki Fukuchi ,  Osamu Hanagata ,  Kotaro Sabe

IPC分类号： G10L15/22

CPC分类号： G06N3/008 ,  B25J13/003 ,  G10L15/22 ,  G10L17/26

摘要： Sentences corresponding to internal statuses of a robot device or the like are created and uttered, thereby expressing the internal statuses. The robot device or the like comprise means for recognizing an external status, and means for generating an emotion based on the internals status, whereby a change in the emotion is reflected upon a dialogue. The internal status is not associated with a sentence, but it exists independently of the system and is always varied depending on various external inputs and internal changes of the system. Accordingly, even when the same question is made on the robot device or the like, the contents of a reply are changed depending on the internal status at that time, and a manner of providing a reply also differs depending on the internal status.

摘要翻译： 创建并发出对应于机器人装置等的内部状态的句子，从而表示内部状态。 机器人装置等包括用于识别外部状态的装置，以及用于基于内部状态产生情绪的装置，由此在对话中反映情绪的改变。 内部状态与句子不相关，但它与系统无关，并且总是根据系统的各种外部输入和内部变化而变化。 因此，即使在机器人装置等上进行同样的问题时，答复的内容根据当时的内部状态而变化，提供答复的方式也根据内部状态而不同。

公开(公告)号：US07216082B2

公开(公告)日：2007-05-08

申请号：US10296269

申请日：2002-03-26

申请人： Atsushi Okubo ,  Gabriel Costa ,  Kenta Kawamoto ,  Rika Horinaka ,  Masaki Fukuchi ,  Masahiro Fujita

发明人： Atsushi Okubo ,  Gabriel Costa ,  Kenta Kawamoto ,  Rika Horinaka ,  Masaki Fukuchi ,  Masahiro Fujita

IPC分类号： G10L15/22

CPC分类号： B25J13/003 ,  G10L15/26 ,  G10L2015/088 ,  G10L2015/223

摘要： A robot system includes a speech recognition unit for converting speech information into text information, and a database retrieval unit for extracting a keyword included in the text information from a database. By designating a plurality of basic actions on a speech basis, and storing an action record, a combined action formed by combining the plurality of basic actions in time-series order can be named as a new action only in voice-based interaction. A user can designate complicated continuous actions by using only one word, and can easily have a conversation with the robot.

摘要翻译： 机器人系统包括用于将语音信息转换为文本信息的语音识别单元，以及用于从数据库中提取包含在文本信息中的关键字的数据库检索单元。 通过在语音基础上指定多个基本动作，并且存储动作记录，通过以时间序列顺序组合多个基本动作形成的组合动作可以仅在基于语音的交互中被命名为新动作。 用户可以通过仅使用一个字来指定复杂的连续动作，并且可以容易地与机器人通话。

公开(公告)号：US06983231B2

公开(公告)日：2006-01-03

申请号：US09958244

申请日：2001-02-09

申请人： Hideki Noma ,  Masahiro Fujita ,  Makoto Inoue ,  Noritoshi Inoue ,  Katsuya Muramatsu ,  Masashi Takeda

发明人： Hideki Noma ,  Masahiro Fujita ,  Makoto Inoue ,  Noritoshi Inoue ,  Katsuya Muramatsu ,  Masashi Takeda

IPC分类号： G06G7/48

CPC分类号： G06N3/006 ,  G06N3/126

摘要： In an information processing device and method, and programs, firstly, new second inheritance data is created based on first inheritance data regulating the shape and/or behaviors of a virtual creature and secondly, the gene data of the virtual creature is diagnosed and a given value added is applied to the virtual creature when it is determined based on the diagnostic result that the gene data satisfies predetermined conditions and thirdly, information on parents of virtual creatures which are sequentially created by mixing and registered, is stored and a pedigree of a designated virtual creature is inquired into based on the information. On the other hand, a data storing device is provided with a first storage means for storing inheritance data to regulate the shape and/or behaviors of a virtual creature, a communication means for transmitting/receiving inheritance data to/from the outside, and a second storing means for storing the inheritance data of other virtual creatures via the communication means.

公开(公告)号：US20050240412A1

公开(公告)日：2005-10-27

申请号：US11101257

申请日：2005-04-06

申请人： Masahiro Fujita

发明人： Masahiro Fujita

IPC分类号： A63H11/00 ,  G06F3/16 ,  G06N3/00 ,  G10L13/00 ,  G10L13/04 ,  G10L13/08 ,  G10L15/00 ,  G10L15/02 ,  G10L15/16 ,  G10L19/14

CPC分类号： G10L15/16 ,  G10L13/00 ,  G10L2015/025

摘要： A behavior control system of a robot for learning a phoneme sequence includes a sound inputting device inputting a phoneme sequence, a sound signal learning unit operable to convert the phoneme sequence into a sound synthesis parameter and to learn or evaluate a relationship between a sound synthesis parameter of a phoneme sequence that is generated by the robot and a sound synthesis parameter used for sound imitation, and a sound synthesizer operable to generate a phoneme sequence based on the sound synthesis parameter obtained by the sound signal learning unit.

摘要翻译： 用于学习音素序列的机器人的行为控制系统包括输入音素序列的声音输入装置，声音信号学习单元，其可操作以将音素序列转换成声音合成参数，并且学习或评估声音合成参数 由机器人产生的音素序列和用于声音模拟的声音合成参数;以及声音合成器，其可操作以基于由声音信号学习单元获得的声音合成参数产生音素序列。

公开(公告)号：US20050187662A1

公开(公告)日：2005-08-25

申请号：US11099139

申请日：2005-04-04

申请人： Kotaro Sabe ,  Masahiro Fujita

发明人： Kotaro Sabe ,  Masahiro Fujita

IPC分类号： A63F13/00 ,  A63H11/00 ,  B25J5/00 ,  B25J9/18 ,  B25J13/00 ,  B25J13/08 ,  G06N3/00 ,  G06F19/00

CPC分类号： G06N3/008 ,  A63H11/00 ,  B25J11/0005

摘要： A robot apparatus is provided. A CPU 15 determines an output of a feeling model based on signals supplied from a touch sensor 20. The CPU 15 also deciphers whether or not an output value of the feeling model exceeds a pre-set threshold value. If the CPU finds that the output value exceeds the pre-set threshold value, it verifies whether or not there is any vacant area in a memory card 13. If the CPU finds that there is any vacant area in a memory card 13, it causes the picture data captured from the CCD video camera 11 to be stored in the vacant area in the memory card 13. At this time, the CPU 15 causes the time and date data and the feeling parameter in the memory card 13 in association with the picture data. The CPU 15 also re-arrays the picture data stored in the memory card 13 in the sequence of the decreasing magnitude of the feeling model output.

摘要翻译： 提供了一种机器人装置。 CPU15基于从触摸传感器20提供的信号确定感觉模型的输出。 CPU15还解密感觉模型的输出值是否超过预先设定的阈值。 如果CPU发现输出值超过预定阈值，则验证存储卡13中是否有空的区域。 如果CPU发现存储卡13中存在任何空闲区域，则将从CCD摄像机11捕获的图像数据存储在存储卡13的空闲区域中。 此时，CPU15与图像数据相关联地导致存储卡13中的时间和日期数据和感觉参数。 CPU15还按照感觉模型输出的衰减幅度的顺序重新排列存储在存储卡13中的图像数据。

公开(公告)号：US20050177278A1

公开(公告)日：2005-08-11

申请号：US11099394

申请日：2005-04-05

申请人： Kotaro Sabe ,  Masahiro Fujita

发明人： Kotaro Sabe ,  Masahiro Fujita

IPC分类号： A63F13/00 ,  A63H11/00 ,  B25J5/00 ,  B25J9/18 ,  B25J13/00 ,  B25J13/08 ,  G06N3/00 ,  G06F19/00

CPC分类号： G06N3/008 ,  A63H11/00 ,  B25J11/0005

摘要： A robot apparatus is provided. A CPU 15 determines an output of a feeling model based on signals supplied from a touch sensor 20. The CPU 15 also deciphers whether or not an output value of the feeling model exceeds a pre-set threshold value. If the CPU finds that the output value exceeds the pre-set threshold value, it verifies whether or not there is any vacant area in a memory card 13. If the CPU finds that there is any vacant area in a memory card 13, it causes the picture data captured from the CCD video camera 11 to be stored in the vacant area in the memory card 13. At this time, the CPU 15 causes the time and date data and the feeling parameter in the memory card 13 in association with the picture data. The CPU 15 also re-arrays the picture data stored in the memory card 13 in the sequence of the decreasing magnitude of the feeling model output.

公开(公告)号：US20050171643A1

公开(公告)日：2005-08-04

申请号：US11098933

申请日：2005-04-05

申请人： Kotaro Sabe ,  Masahiro Fujita

发明人： Kotaro Sabe ,  Masahiro Fujita

IPC分类号： A63F13/00 ,  A63H11/00 ,  B25J5/00 ,  B25J9/18 ,  B25J13/00 ,  B25J13/08 ,  G06N3/00 ,  G06F19/00

CPC分类号： G06N3/008 ,  A63H11/00 ,  B25J11/0005

摘要： A robot apparatus is provided. A CPU 15 determines an output of a feeling model based on signals supplied from a touch sensor 20. The CPU 15 also deciphers whether or not an output value of the feeling model exceeds a pre-set threshold value. If the CPU finds that the output value exceeds the pre-set threshold value, it verifies whether or not there is any vacant area in a memory card 13. If the CPU finds that there is any vacant area in a memory card 13, it causes the picture data captured from the CCD video camera 11 to be stored in the vacant area in the memory card 13. At this time, the CPU 15 causes the time and date data and the feeling parameter in the memory card 13 in association with the picture data. The CPU 15 also re-arrays the picture data stored in the memory card 13 in the sequence of the decreasing magnitude of the feeling model output.