公开(公告)号：US20110299731A1

公开(公告)日：2011-12-08

申请号：US13116412

申请日：2011-05-26

申请人： Jun Yokono ,  Kohtaro Sabe

发明人： Jun Yokono ,  Kohtaro Sabe

IPC分类号： G06K9/00

CPC分类号： G06K9/6257 ,  G06K9/00791 ,  G06K2009/4666

摘要： An information processing device includes a first calculation unit which calculates a score of each sample image including a positive image in which an object as an identification object is present and a negative image in which the object as the identification object is not present, for each weak identifier of an identifier including a plurality of weak identifiers, a second calculation unit which calculates the number of scores when the negative image is processed, which are scores less than a minimum score among scores when the positive image is processed; and an realignment unit which realigns the weak identifiers in order from a weak identifier in which the number calculated by the second calculation unit is a maximum.

摘要翻译： 一种信息处理设备，包括：第一计算单元，其计算包含其中存在作为识别对象的对象的正图像和不存在作为识别对象的对象的负图像的每个样本图像的得分，对于每个弱 标识符包括多个弱标识符的标识符;第二计算单元，当处理正图像时，计算负图像处理时的得分数，该分数小于分数中的最小得分; 以及重新排列单元，其从由第二计算单元计算的数量最大的弱识别符依次重新排列弱标识符。

公开(公告)号：US07849033B2

公开(公告)日：2010-12-07

申请号：US11350048

申请日：2006-02-09

申请人： Kohtaro Sabe ,  Kenichi Hidai

发明人： Kohtaro Sabe ,  Kenichi Hidai

IPC分类号： G06F15/18 ,  G06N3/08

CPC分类号： G05B13/0265

摘要： A learning control apparatus for controlling a learning operation of an apparatus sensing a state of an environment and selecting a behavior based on the sensed content, includes a predictor for learning the behavior and a change in the state of the environment, and predicting a change in the state of the environment in response to a predetermined behavior, a goal state setting unit for setting a goal state in the behavior, a planner for planning a behavior sequence from a current state to the goal state set by the goal state setting unit based on a prediction of the predictor, and a controller for controlling the behavior in the behavior sequence planned by the planning unit and learning an input and output relationship in the behavior.

摘要翻译： 一种学习控制装置，用于控制感测环境状态的装置的学习操作，并且基于感测到的内容选择行为，包括用于学习行为和环境状态变化的预测器，以及预测变化 响应于预定行为的环境状态，用于设置行为中的目标状态的目标状态设置单元，用于根据目标状态设置单元基于目标状态设置单元设置的目标状态来规划行为序列的计划器 预测器的预测，以及用于控制由规划单元计划的行为序列中的行为并且学习行为中的输入和输出关系的控制器。

公开(公告)号：US20080235165A1

公开(公告)日：2008-09-25

申请号：US12074931

申请日：2008-03-07

申请人： Javier R. Movellan ,  Marian S. Bartlett ,  Gwendolen C. Littlewort ,  John Hershey ,  Ian R. Fasel ,  Eric C. Carlson ,  Josh Susskind ,  Kohtaro Sabe ,  Kenta Kawamoto ,  Kenichi Hidai

发明人： Javier R. Movellan ,  Marian S. Bartlett ,  Gwendolen C. Littlewort ,  John Hershey ,  Ian R. Fasel ,  Eric C. Carlson ,  Josh Susskind ,  Kohtaro Sabe ,  Kenta Kawamoto ,  Kenichi Hidai

IPC分类号： G06F15/18 ,  G06F17/00 ,  G06N5/02

CPC分类号： G06K9/00248 ,  G06K9/00308 ,  G06K9/6256 ,  G06N3/004

摘要： A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

摘要翻译： 一种面部表情识别系统，其使用面部检测装置，当检测到表示检测对象的区域时，基于整体学习实现有效的学习和高速检测处理，并且对于包括在图像中的面部位置的移动是鲁棒的，并且能够高度准确地表达 识别和系统的学习方法。 当通过Adaboost的面部检测装置学习数据时，从所有弱假设中选择高性能弱假设的处理，然后根据统计特征从这些高性能弱假设产生新的弱假设，并选择一个弱 重复具有这些弱假设的最高判别性能的假设，以依次产生弱假设，从而获得最终假设。 在检测中，使用预先学习的中止阈值，每当一个弱假设输出鉴别结果时，确定提供的数据是否可以被明确地判断为非面。 如果可以判断，则处理中止。 通过Adaboost技术从检测到的脸部图像中选择预定的Gabor滤波器，并且仅学习由所选择的滤波器提取的特征量的支持向量，从而执行表达式识别。

公开(公告)号：US07346430B2

公开(公告)日：2008-03-18

申请号：US11133403

申请日：2005-05-19

申请人： Masaki Fukuchi ,  Takayuki Yoshigahara ,  Kohtaro Sabe ,  Takeshi Ohashi

发明人： Masaki Fukuchi ,  Takayuki Yoshigahara ,  Kohtaro Sabe ,  Takeshi Ohashi

IPC分类号： G06F19/00

CPC分类号： H04N21/4345 ,  H04L29/06027 ,  H04L65/602 ,  H04L65/604 ,  H04N21/2187 ,  H04N21/2362 ,  H04N21/2365 ,  H04N21/4347 ,  Y10S707/99945 ,  Y10S707/99948

摘要： An image transmission device and method, a transmitting device and method, a receiving device and method, and robot apparatus are capable of effectively transmitting the image data of multiple channels by using the existing systems which are formed on the premise of transmitting and receiving of the image data through single transmission line. At a transmitting side, the image data of multiple channels to be input is multiplexed with switching the channels by frame, and prescribed image information is added to each of the multiplexed image data of each frame. At a receiving side, the image information added to each of the image data for each frame respectively transmitted from the transmitting device are analyzed, and dividing device for dividing for each frame and outputting the multiplexed image data transmitted from the transmitting device to the corresponding channels is provided based on the analysis result.

摘要翻译： 图像传输装置和方法，发送装置和方法，接收装置和方法以及机器人装置能够通过使用在发送和接收的方式形成的现有系统来有效地发送多个信道的图像数据 图像数据通过单一传输线。 在发送侧，将要输入的多个信道的图像数据通过逐帧切换而多路复用，并且将规定的图像信息添加到每帧的多路复用图像数据中。 在接收侧，对从发送装置分别发送的每帧的每个图像数据中添加的图像信息进行分析，并且对每个帧进行分割，并将从发送装置发送的复用图像数据输出到对应的信道 是基于分析结果提供的。

公开(公告)号：US07317817B2

公开(公告)日：2008-01-08

申请号：US11656115

申请日：2007-01-22

申请人： Atsushi Okubo ,  Kohtaro Sabe ,  Kenta Kawamoto ,  Masaki Fukuchi

发明人： Atsushi Okubo ,  Kohtaro Sabe ,  Kenta Kawamoto ,  Masaki Fukuchi

IPC分类号： G06K9/00

CPC分类号： G06K9/00228 ,  G06K9/00221 ,  G06T7/246 ,  G06T7/90

摘要： A robot apparatus includes face includes a face tracking module (M2) for tracking a face in an image photographed by a CCD camera, a face detecting module (M1) for detecting face data of the face in the image photographed by the image pickup device, based on the face tracking information by the face tracking module (M2) and a face identification module (M3) for identifying a specified face based on the face data as detected by the face data detecting module (M1).

摘要翻译： 一种机器人装置，包括面部跟踪模块（M 2），用于跟踪由CCD照相机拍摄的图像中的脸部，面部检测模块（M 1），用于检测由图像拾取器拍摄的图像中的脸部的脸部数据 基于面部追踪模块（M 2）的脸部跟踪信息和面部识别模块（M 3），根据脸部数据检测模块（M 1）检测到的脸部数据，识别指定脸部的装置。

公开(公告)号：US20070217688A1

公开(公告)日：2007-09-20

申请号：US11717019

申请日：2007-03-13

申请人： Kohtaro Sabe ,  Kenichi Hidai ,  Kei Koya

发明人： Kohtaro Sabe ,  Kenichi Hidai ,  Kei Koya

IPC分类号： G06K9/68 ,  G06K9/62

CPC分类号： G06K9/00228 ,  G06K9/6202 ,  G06K9/6257

摘要： An information processing apparatus includes a higher node having a plurality of weak discriminators that have learned a learning sample of a first label and a learning sample of a second label that has a predetermined coordinate relationship with the learning sample of the first label, a first lower node having a plurality of weak discriminators that have learned the learning sample of the first label based on the discrimination result of the higher node and a second lower node that has no weak discriminator.

摘要翻译： 信息处理装置包括具有多个弱识别器的较高节点，所述多个弱识别器已经学习了第一标签的学习样本和与第一标签的学习样本具有预定坐标关系的第二标签的学习样本，第一下部 节点具有基于较高节点的识别结果和不具有弱鉴别器的第二较低节点已经学习了第一标签的学习样本的多个弱鉴别器。

公开(公告)号：US07269478B2

公开(公告)日：2007-09-11

申请号：US11137081

申请日：2005-05-25

申请人： Masaki Fukuchi ,  Takayuki Yoshigahara ,  Kohtaro Sabe ,  Takeshi Ohashi

发明人： Masaki Fukuchi ,  Takayuki Yoshigahara ,  Kohtaro Sabe ,  Takeshi Ohashi

IPC分类号： G06F19/00

CPC分类号： H04N21/4345 ,  H04L29/06027 ,  H04L65/602 ,  H04L65/604 ,  H04N21/2187 ,  H04N21/2362 ,  H04N21/2365 ,  H04N21/4347 ,  Y10S707/99945 ,  Y10S707/99948

摘要： An image transmission device and method, a transmitting device and method, a receiving device and method, and robot apparatus are capable of effectively transmitting the image data of multiple channels by using the existing systems which are formed on the premise of transmitting and receiving of the image data through single transmission line. At a transmitting side, the image data of multiple channels to be input is multiplexed with switching the channels by frame, and prescribed image information is added to each of the multiplexed image data of each frame. At a receiving side, the image information added to each of the image data for each frame respectively transmitted from the transmitting are analyzed, and dividing for dividing for each frame and outputting the multiplexed image data transmitted from the transmitting to the corresponding channels is provided based on the analysis result.

摘要翻译： 图像传输装置和方法，发送装置和方法，接收装置和方法以及机器人装置能够通过使用在发送和接收的方式形成的现有系统来有效地发送多个信道的图像数据 图像数据通过单一传输线。 在发送侧，将要输入的多个信道的图像数据通过逐帧切换而多路复用，并且将规定的图像信息添加到每帧的多路复用图像数据中。 在接收侧，分别添加到从发送分别发送的每帧的每个图像数据中的图像信息，并且基于每个帧划分并将从发送发送的多路复用图像数据输出到相应的信道，基于 对分析结果。

公开(公告)号：US07200249B2

公开(公告)日：2007-04-03

申请号：US10181279

申请日：2001-11-19

申请人： Atsushi Okubo ,  Kohtaro Sabe ,  Kenta Kawamoto ,  Masaki Fukuchi

发明人： Atsushi Okubo ,  Kohtaro Sabe ,  Kenta Kawamoto ,  Masaki Fukuchi

IPC分类号： G06K9/00

CPC分类号： G06K9/00228 ,  G06K9/00221 ,  G06T7/246 ,  G06T7/90

摘要： A robot apparatus includes face includes a face tracking module (M2) for tracking a face in an image photographed by a CCD camera, a face detecting module (M1) for detecting face data of the face in the image photographed by the image pickup device, based on the face tracking information by the face tracking module (M2) and a face identification module (M3) for identifying a specified face based on the face data as detected by the face data detecting module (M1).

摘要翻译： 一种机器人装置，包括面部跟踪模块（M 2），用于跟踪由CCD照相机拍摄的图像中的脸部，面部检测模块（M 1），用于检测由图像拾取器拍摄的图像中的脸部的脸部数据 基于面部追踪模块（M 2）的脸部跟踪信息和面部识别模块（M 3），根据脸部数据检测模块（M 1）检测到的脸部数据，识别指定脸部的装置。

公开(公告)号：US07117190B2

公开(公告)日：2006-10-03

申请号：US09890231

申请日：2000-11-30

申请人： Kohtaro Sabe ,  Rika Hasegawa ,  Makoto Inoue

发明人： Kohtaro Sabe ,  Rika Hasegawa ,  Makoto Inoue

IPC分类号： A63H7/00 ,  B25J13/00 ,  G05B13/04

CPC分类号： G06N3/008 ,  G05B2219/39162

摘要： In a robot apparatus and a control method therefor, firstly, partial or whole state space of a behavioral model is expanded or reduced, secondly, transition to a predetermined node in the behavioral model is described as transition to a virtual node and a node group to be allotted to the virtual node is sequentially changed, thirdly, the number of emotions and/or desires which are used for generating actions is gradually increased, and fourthly, an environment is evaluated to update each sensitivity corresponding to each emotion and desire, on the basis of the evaluated. In the robot apparatus and the character discriminating method for the robot apparatus, a pet robot is provided with: detecting means for detecting outputs from other pet robots; character discriminating means for discriminating characters of the pet robots on the basis of the result detected by the detecting means; and character changing means for changing the character on the basis of the result judged by the character discriminating means.

公开(公告)号：US06912449B2

公开(公告)日：2005-06-28

申请号：US10023625

申请日：2001-12-18

申请人： Kohtaro Sabe ,  Takayuki Sakamoto

发明人： Kohtaro Sabe ,  Takayuki Sakamoto

IPC分类号： G06T1/60 ,  G05B15/00 ,  G05B19/00

CPC分类号： G06T1/60

摘要： Each of plural image processing means is informed of address information of storage means in which image data to be read is stored upon request of the image data to be read by each of the plural image processing means. Consequently, each of the image processing means can read each of image data to be read directly from the storage means based on the informed address information so as to subject it to predetermined image processing. Thus, it is possible to perform plural independent image processing in parallel at a high speed with the simple configuration.

摘要翻译： 向多个图像处理装置中的每一个通知存储装置的地址信息，其中根据要由多个图像处理装置中的每一个读取的图像数据的要求存储要读取的图像数据。 因此，每个图像处理装置可以基于所通知的地址信息来读取从存储装置直接读取的每个图像数据，以便对其进行预定的图像处理。 因此，可以以简单的结构高速并行地执行多个独立的图像处理。