公开(公告)号：US20130064455A1

公开(公告)日：2013-03-14

申请号：US13421278

申请日：2012-03-15

申请人： Masao Yamanaka ,  Masakazu Matsugu

发明人： Masao Yamanaka ,  Masakazu Matsugu

IPC分类号： G06K9/46

CPC分类号： G06K9/46 ,  G06T7/11 ,  G06T7/136 ,  G06T7/143 ,  G06T2207/20021 ,  G06T2207/20076

摘要： An information processing apparatus comprising a setting unit configured to set a plurality of local regions on an image; an extraction unit configured to extract feature amounts from the respective local regions; a calculation unit configured to calculate dissimilarities between the local regions based on probability densities for the respective feature amounts; and an integration unit configured to integrate the plurality of local regions as region groups based on the dissimilarities.

摘要翻译： 一种信息处理设备，包括：设置单元，被配置为在图像上设置多个局部区域; 提取单元，被配置为从各个局部区域提取特征量; 计算单元，被配置为基于各个特征量的概率密度来计算局部区域之间的不相似性; 以及集成单元，其被配置为基于所述不相似性将所述多个局部区域作为区域组合。

公开(公告)号：US20120327224A1

公开(公告)日：2012-12-27

申请号：US13582116

申请日：2011-03-07

申请人： Osamu Nomura ,  Masakazu Matsugu

发明人： Osamu Nomura ,  Masakazu Matsugu

IPC分类号： H04N7/18

CPC分类号： B25J9/1671

摘要： An information processing apparatus includes an imaging unit and is capable of setting arrangement of a structural member of a robot system which works based on an image captured by the imaging unit. The information processing apparatus includes an arrangement unit configured to arrange a virtual object corresponding to the structural member in a virtual space corresponding to a working space of the robot system, a first acquisition unit configured to acquire a virtual space image in the virtual space which corresponds to the captured image and in which the virtual object is arranged, and a second acquisition unit configured to acquire an evaluation value indicating adaptation of arrangement of the virtual object to the work of the robot system based on the virtual space image.

摘要翻译： 信息处理设备包括成像单元，并且能够基于由成像单元捕获的图像来设置机器人系统的结构构件的布置。 该信息处理装置包括：配置单元，被配置为将与结构构件相对应的虚拟对象布置在与机器人系统的工作空间对应的虚拟空间中;第一获取单元，被配置为获取虚拟空间中的虚拟空间图像 以及第二获取单元，被配置为基于虚拟空间图像获取指示虚拟对象的布置适应于机器人系统的工作的评估值。

公开(公告)号：US08274646B2

公开(公告)日：2012-09-25

申请号：US12816069

申请日：2010-06-15

申请人： Kazuyuki Ota ,  Masakazu Matsugu ,  Kenji Saitoh

发明人： Kazuyuki Ota ,  Masakazu Matsugu ,  Kenji Saitoh

IPC分类号： G01N21/00

CPC分类号： G01B11/25

摘要： This invention is directed to extract the scattering characteristic of a measurement target together when measuring the surface shape in a measurement system, which measures the surface shape of a measurement target, by the pattern projection method. To accomplish this, the measurement system includes an illumination unit which irradiates a measurement target with dot pattern light, a reflected light measurement unit which receives the reflected light at a reflection angle almost equal to a incident angle, and a reflected light extraction unit which extracts the inclination of the surface of the measurement target, based on the shift amount between the light receiving position of the received reflected light and a predetermined reference position, and extracts the luminance value of the reflected light and the dot diameter of the dot pattern light as information about the scattering characteristic.

摘要翻译： 本发明旨在通过图案投影法在测量测量对象的表面形状的测量系统中测量表面形状时，将测量对象的散射特性一起提取。 为了实现这一点，测量系统包括用点阵图形光照射测量对象的照明单元，以几乎等于入射角的反射角接收反射光的反射光测量单元和提取出的反射光提取单元 基于接收到的反射光的光接收位置与预定的基准位置之间的偏移量，测量对象的表面的倾斜度，并将点阵图案光的反射光的亮度值和点直径提取为 关于散射特性的信息。

公开(公告)号：US07743004B2

公开(公告)日：2010-06-22

申请号：US12164719

申请日：2008-06-30

申请人： Masakazu Matsugu

发明人： Masakazu Matsugu

IPC分类号： G06E3/00 ,  G06G7/00 ,  G06N3/02 ,  G06K9/62

CPC分类号： G06N3/049 ,  G06K9/00973 ,  G06K9/4628 ,  G06N3/063

摘要： A pulse signal processing circuit, a parallel processing circuit, and a pattern recognition system including a plurality of arithmetic elements for outputting pulse signals and at least one modulation circuit, synaptic connection element(s), or synaptic connection means for modulating the pulse signals, the modulated pulse signals then being separately or exclusively output to corresponding signal lines.

摘要翻译： 脉冲信号处理电路，并行处理电路和模式识别系统，包括用于输出脉冲信号的多个运算元件和用于调制脉冲信号的至少一个调制电路，突触连接元件或突触连接装置， 然后将调制的脉冲信号单独或排他地输出到对应的信号线。

公开(公告)号：US07085749B2

公开(公告)日：2006-08-01

申请号：US10155478

申请日：2002-05-28

申请人： Masakazu Matsugu

发明人： Masakazu Matsugu

IPC分类号： G06N3/04 ,  G06G7/161 ,  G06F15/18

CPC分类号： G06N3/049 ,  G06K9/00973 ,  G06K9/4628 ,  G06N3/063

摘要： A synaptic connection element for connecting neuron elements inputs a plurality of pulsed signals from different neuron elements N1 through N4, effects a common modulation (time window integration or pulse phase/width modulation) on a plurality of predetermined signals among the plurality of pulse signals, and outputs the modulated pulse signals to different signal lines to a neuron element M1. A neural network for representing and processing pattern information by the pulse modulation is thereby downsized in scale.

摘要翻译： 用于连接神经元元件的突触连接元件输入来自不同神经元元件N 1至N 4的多个脉冲信号，对多个脉冲中的多个预定信号实现共同调制（时间窗积分或脉冲相位/宽度调制） 信号，并且将调制的脉冲信号输出到不同的信号线到神经元元素M 1。由此，通过脉冲调制来表示和处理图案信息的神经网络的尺寸被缩小。

公开(公告)号：US20050185835A1

公开(公告)日：2005-08-25

申请号：US11044188

申请日：2005-01-28

申请人： Masakazu Matsugu ,  Pierre Cardon

发明人： Masakazu Matsugu ,  Pierre Cardon

IPC分类号： G06T1/00 ,  G06K9/46 ,  G06K9/62 ,  G06N3/00 ,  G06T1/40 ,  G06T7/00

CPC分类号： G06K9/4619

摘要： In learning for pattern recognition, an aggregation of different types of object image data is inputted, and local features having given geometric structures are detected from each object image data inputted. The detected local features are put through clustering, plural representative local features are selected based on results of the clustering, and a learning data set containing the selected representative local features as supervisor data is used to recognize or detect an object that corresponds to the object image data. The learning thus makes it possible to appropriately extract, from an aggregation of images, local features useful for detection and recognition of subjects of different categories.

摘要翻译： 在学习图形识别时，输入不同类型的对象图像数据的聚合，并且从输入的每个对象图像数据检测具有给定几何结构的局部特征。 检测到的本地特征通过聚类进行，基于聚类的结果选择多个代表性的局部特征，并且使用包含所选择的代表性局部特征作为监督数据的学习数据集来识别或检测与对象图像相对应的对象 数据。 因此，该学习使得可以从图像的聚集中适当地提取对于不同类别的对象的检测和识别有用的局部特征。

公开(公告)号：US06728400B1

公开(公告)日：2004-04-27

申请号：US09628024

申请日：2000-07-28

申请人： Masakazu Matsugu

发明人： Masakazu Matsugu

IPC分类号： G06K900

CPC分类号： G06T7/11 ,  G06T7/187 ,  G06T7/194 ,  G06T2207/10016 ,  G06T2207/20101

摘要： An initial core setting device sets the point or area designated by a indication selecting device as a core of area growth. A characteristic amount extraction device extracts a color component value of each pixel of an input image, edge strength value regarding density (lightness), contrast component regarding lightness or texture characteristic amount. A representative color extraction device extracts the color component characteristic amount of the representative color from a point on the initial core. An area dividing device labels as a continuous area the pixel with small difference between one of representative colors and the color component, and generates image dividing data designating individual areas. An area growth/reduction device, in accordance with user's indication, merges into or excludes from an attention area the set initial core area or each point in the area neighbouring the boundary in the area whose shape is changed, based on image characteristic amount or image dividing data. A shape display data generation device generates data for display showing the shape of area which is obtained In the process of (or as a result of) area growth. An image based on generated data for display is superimposed on the input image to be displayed.

摘要翻译： 初始核心设置装置将由指示选择装置指定的点或区域设置为区域增长的核心。 特征量提取装置提取输入图像的每个像素的颜色分量值，关于密度（亮度），关于亮度或纹理特征量的对比度分量的边缘强度值。 代表性颜色提取装置从初始核心上的点提取代表颜色的颜色分量特征量。 区域分割装置将代表颜色和颜色分量之间的差异小的像素标记为连续区域，并且生成指定各个区域的图像分割数据。 根据用户的指示，区域增长/减少装置基于图像特征量或图像将设置的初始核心区域或其形状改变的区域中的边界附近的区域中的每个点合并到或排除注意区域 划分数据 形状显示数据生成装置生成用于显示在区域生长的（或作为结果）的过程中获得的区域的形状的显示数据。 基于用于显示的生成数据的图像叠加在要显示的输入图像上。

公开(公告)号：US06674905B1

公开(公告)日：2004-01-06

申请号：US09488792

申请日：2000-01-21

申请人： Masakazu Matsugu ,  Toshiaki Kondo ,  Fumiaki Takahashi

发明人： Masakazu Matsugu ,  Toshiaki Kondo ,  Fumiaki Takahashi

IPC分类号： G06K948

CPC分类号： G06T7/11 ,  G06T7/187 ,  G06T2207/10016 ,  G06T2207/20064 ,  G06T2207/20096

摘要： When a dispersion value of a shading value is equal to or more than a threshold value in the neighborhood of a standard point, it is determined that an image pattern has a texture dominant characteristic. When the value is less than the threshold value, a change of the shading value is determined to be moderate (S11). When the dispersion value is equal to or more than the threshold value (S11), a texture characteristic amount is loaded (S12), a characteristic amount suitable for area growth (e.g., texture energy) is calculated (S13), and a distance DT concerning the texture characteristic amount is obtained (S14). When the dispersion value is less than the threshold value (S11), a color component characteristic amount is loaded (S16), a characteristic amount suitable for the area growth (e.g., a characteristic vector obtained from a local histogram concerning a color component or a list of representative color components) is extracted (S17), and a distance DC concerning the color component is obtained (S18). The area is grown based on the corresponding characteristic amount (S15, S19), and a renewal position is determined based on a new borderline of a core area obtained by unifying area growth results from standard points (S20).

摘要翻译： 当阴影值的色散值等于或大于标准点附近的阈值时，确定图像图案具有纹理主导特性。 当该值小于阈值时，阴影值的变化被确定为适度（S11）。 当色散值等于或大于阈值（S11）时，加载纹理特征量（S12），计算适合于面积生长的特征量（例如，纹理能量）（S13），并且距离DT 获得关于纹理特征量的数据（S14）。 当色散值小于阈值（S11）时，加载颜色分量特征量（S16），适合于区域增长的特征量（例如，从关于颜色分量的局部直方图获得的特征向量 提取代表性颜色分量的列表）（S17），并且获得关于颜色分量的距离DC（S18）。 基于对应的特征量生长区域（S15，S19），并且基于通过从标准点统一区域增长结果而获得的核心区域的新的边界线来确定更新位置（S20）。

公开(公告)号：US06621921B1

公开(公告)日：2003-09-16

申请号：US08767018

申请日：1996-12-16

申请人： Masakazu Matsugu ,  Katsumi Iijima ,  Kotaro Yano ,  Sunao Kurahashi ,  Toshiaki Kondo ,  Motohiro Ishikawa

发明人： Masakazu Matsugu ,  Katsumi Iijima ,  Kotaro Yano ,  Sunao Kurahashi ,  Toshiaki Kondo ,  Motohiro Ishikawa

IPC分类号： G06K900

CPC分类号： G06T7/55 ,  G06T7/73

摘要： An image processing apparatus in which a plurality of images obtained by photographing a three-dimensional object from a plurality of viewpoints are integrated by using image-pickup parameters such as position, pose, focal lengths, and aberration information of a camera at these viewpoints, thereby integrating shapes at arbitrary viewpoints of the three-dimensional object.

摘要翻译： 一种图像处理装置，其中通过在这些视点处使用诸如位置，姿势，焦距和相机的像差信息的摄像参数来将通过从多个视点拍摄三维物体而获得的多个图像集成， 从而在三维物体的任意视点处整合形状。

公开(公告)号：US5625408A

公开(公告)日：1997-04-29

申请号：US575332

申请日：1995-12-20

申请人： Masakazu Matsugu ,  Katsumi Iijima

发明人： Masakazu Matsugu ,  Katsumi Iijima

IPC分类号： H04N13/00 ,  H04N13/02 ,  H04N13/04

CPC分类号： H04N13/0296 ,  G06T7/0022 ,  H04N13/0239 ,  G06T2207/10012 ,  H04N13/0055 ,  H04N19/597 ,  H04N2013/0081

摘要： In order to reproduce a stereoscopic image even when the base length or convergence angle between two cameras upon phototaking is difference from that between the naked eyes of an observer upon reproducing, means for extracting parallax information between images obtained by a plurality of cameras, means for symbolizing and recording discriminating information between a double area and single eye areas, intensity information of pixels, and parallax information on the double area in images obtained by the extracting means on a recording medium, and means for storing optical configuration information of the cameras are arranged, and images are reproduced on the basis of the recorded information, the optical disposal information, and optical configuration information upon reproducing.

摘要翻译： 为了再现立体图像，即使在拍摄时两个照相机之间的基准长度或会聚角与再现时观察者的裸眼之间的基准长度或会聚角度不同，也可以在多个照相机获得的图像之间提取视差信息的装置， 在双面区域和单眼区域之间的识别和记录鉴别信息，像素的强度信息和由提取装置在记录介质上获得的图像中的双重区域上的视差信息，以及用于存储照相机的光学配置信息的装置 ，并且根据再现时的记录信息，光学处理信息和光学配置信息来再现图像。