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：US20130243289A1

公开(公告)日：2013-09-19

申请号：US13423211

申请日：2012-03-17

申请人： Su Wang ,  Shengyang Dai ,  Xun Xu ,  Akira Nakamura

发明人： Su Wang ,  Shengyang Dai ,  Xun Xu ,  Akira Nakamura

IPC分类号： G06K9/00

CPC分类号： G06T7/162 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10081 ,  G06T2207/20041 ,  G06T2207/20096 ,  G06T2207/30036

摘要： An interactive segmentation framework for 3-D teeth CT volumetric data enables a user to segment an entire dental region or individual teeth depending upon the types of user input. Graph cuts-based interactive segmentation utilizes a user's scribbles which are collected on several 2-D representative CT slices and are expanded on those slices. Then, a 3-D distance transform is applied to the entire CT volume based on the expanded scribbles. Bony tissue enhancement is added before feeding 3-D CT raw image data into the graph cuts pipeline. The segmented teeth area is able to be directly utilized to reconstruct a 3-D virtual teeth model.

摘要翻译： 用于3D牙齿CT体积数据的交互式分割框架使用户能够根据用户输入的类型来分割整个牙齿区域或单个牙齿。 基于图切割的交互式分割利用用户的涂鸦，这些涂鸦被收集在几个二维代表性的CT切片上，并在这些切片上展开。 然后，基于扩展的涂鸦将3-D距离变换应用于整个CT体积。 在将3-D CT原始图像数据提供给图形切割管道之前，添加骨组织增强。 分段牙齿区域能够直接用于重建3-D虚拟牙齿模型。

公开(公告)号：US20130230338A1

公开(公告)日：2013-09-05

申请号：US13881636

申请日：2011-11-10

申请人： Daisuke Kubo ,  Keiichi Yano ,  Akira Nakamura ,  Yoko Arai

发明人： Daisuke Kubo ,  Keiichi Yano ,  Akira Nakamura ,  Yoko Arai

IPC分类号： G03G15/00 ,  G03G21/18

CPC分类号： G03G21/18 ,  G03G15/751 ,  G03G15/757

摘要： A disclosed flange member includes a press-fitted portion to be press-fitted in an axial end-opening portion of a hollow and cylindrical sleeve member; an axle opening portion including an axle opening into which a shaft member is inserted when the press-fitted portion is press-fitted in the end-opening portion; and a linking portion extending in a direction parallel to a circular cross section of the sleeve member and connecting the axle opening portion to the press-fitted portion. The linking portion includes a stress-absorbing portion that is deformed so as to absorb stress to which an outer peripheral surface of the press-fitted portion is subjected upon contact with an inner peripheral surface of the sleeve member when the press-fitted portion is press-fitted in the end-opening portion, thus preventing the stress from being transmitted to the axle opening portion via the linking portion.

摘要翻译： 所公开的凸缘构件包括压配合部分，该压配部分压配合在中空和圆柱形套筒构件的轴向端部开口部分中; 所述车轴开口部包括车轴开口，当所述压配合部压配合在所述端部开口部时，所述轴构件插入到所述轴孔中; 以及连接部，其在与所述套筒构件的圆形截面平行的方向上延伸并将所述车轴开口部连接到所述压入部。 连接部分包括应力吸收部分，该压力部分被变形以吸收当按压配合部分被按压时压配部分的外周面与套筒部件的内周面接触时受到的应力 设置在端部开口部分，从而防止应力通过连接部分传递到车轴开口部分。

公开(公告)号：US08419493B2

公开(公告)日：2013-04-16

申请号：US13441229

申请日：2012-04-06

申请人： Shinichi Oe ,  Kazutaka Ikeda ,  Akira Nakamura ,  Motoaki Tamaya

发明人： Shinichi Oe ,  Kazutaka Ikeda ,  Akira Nakamura ,  Motoaki Tamaya

IPC分类号： H01J9/24

CPC分类号： H01S5/02252 ,  G02F1/377 ,  H01S5/0092 ,  H01S5/02415 ,  H01S5/06837 ,  Y10T29/49826

摘要： An apparatus for manufacturing a light source and a method therefor are provided that enables a high efficient light source to be manufactured even when an optical element whose characteristic significantly varies is used. After maintaining temperatures of a laser device and a wavelength conversion element at a temperature where an output of light emitted from each of the device and the element is equal to or greater than a predetermined rate of the maximum output, the laser device and the wavelength conversion element whose temperatures have been maintained are joined together so that the output of the light emitted from the wavelength conversion element is equal to or greater than a predetermined value.

摘要翻译： 提供了一种用于制造光源的装置及其方法，即使使用其特性显着变化的光学元件，也能够制造高效光源。 在将激光装置和波长转换元件的温度维持在从装置和元件中的每一个发射的光的输出等于或大于最大输出的预定速率的温度下，激光装置和波长转换 将其温度保持的元件连接在一起，使得从波长转换元件发射的光的输出等于或大于预定值。

公开(公告)号：US08374437B2

公开(公告)日：2013-02-12

申请号：US12261190

申请日：2008-10-30

申请人： Akira Nakamura ,  Yoshiaki Iwai ,  Takayuki Yoshigahara

发明人： Akira Nakamura ,  Yoshiaki Iwai ,  Takayuki Yoshigahara

IPC分类号： G06K9/46

CPC分类号： G06K9/6228 ,  G06K9/6211

摘要： An information processing apparatus includes a model image obtaining unit configured to obtain a plurality of model images; a model image feature quantity extracting unit configured to extract feature quantities of the model images obtained by the model image obtaining unit; a matching unit configured to perform matching on the feature quantities of the model images extracted by the model image feature quantity extracting unit; and an identifying feature point extracting unit configured to extract, as a result of the matching performed by the matching unit, feature points having a low correlation with a predetermined model image in similar model images that are the model images having a predetermined number or more of the feature quantities that match feature quantities of the predetermined model image, the extracted feature points being regarded as identifying feature points used for identification of the respective similar model images.

摘要翻译： 信息处理设备包括：模型图像获取单元，被配置为获得多个模型图像; 模型图像特征量提取单元，被配置为提取由模型图像获取单元获得的模型图像的特征量; 配置为对由模型图像特征量提取单元提取的模型图像的特征量进行匹配的匹配单元; 以及识别特征点提取单元，被配置为作为所述匹配单元执行的匹配的结果，提取具有与预定数量或更多个的模型图像相似的模型图像中与预定模型图像具有低相关性的特征点 与预定模型图像的特征量匹配的特征量，所提取的特征点被认为是用于识别各个相似模型图像的识别特征点。

公开(公告)号：US08270707B2

公开(公告)日：2012-09-18

申请号：US12704001

申请日：2010-02-11

申请人： Yoshiaki Iwai ,  Akira Nakamura ,  Takayuki Yoshigahara

发明人： Yoshiaki Iwai ,  Akira Nakamura ,  Takayuki Yoshigahara

IPC分类号： G06K9/00 ,  G06F15/18 ,  G06F21/00

CPC分类号： G06K9/4671 ,  G06K9/00228

摘要： A learning device includes a feature-point extracting section extracting feature points from a generation image, a feature-point feature-quantity extracting section extracting feature-point feature-quantities representing features of the feature points, a total-feature-quantity generating section generating a total feature quantity represented by a multi-dimensional vector, and an identifier generating section generating an identifier using the total feature quantity and a true label indicating whether or not the generation image is a positive image or a negative image.

摘要翻译： 学习装置包括从生成图像提取特征点的特征点提取部，特征点特征量提取部，提取表示特征点的特征的特征量特征量，生成全部特征量生成部 由多维向量表示的总特征量，以及使用总特征量生成标识符的标识符生成部以及指示生成图像是正图像还是负图像的真实标签。

公开(公告)号：US08265111B2

公开(公告)日：2012-09-11

申请号：US12921822

申请日：2008-03-18

申请人： Motoaki Tamaya ,  Chise Nanba ,  Akira Nakamura ,  Keiichi Fukuda ,  Koji Funaoka ,  Manabu Kawakami ,  Masamitsu Okamura

发明人： Motoaki Tamaya ,  Chise Nanba ,  Akira Nakamura ,  Keiichi Fukuda ,  Koji Funaoka ,  Manabu Kawakami ,  Masamitsu Okamura

IPC分类号： H01S3/04

CPC分类号： H01S3/025 ,  G02F1/37 ,  H01S3/0092 ,  H01S3/042 ,  H01S3/09415

摘要： When a laser light source module includes a heat sink in which a solid laser element, an excitation light source, and a wavelength conversion element are arranged and a stem that supports the heat sink, wherein the heat sink is separated into three blocks, namely a first block including a laser oscillating unit for the solid laser element is arranged, a second block including a semiconductor laser element that emits excitation light for the laser oscillating unit and a first temperature sensor are arranged and on a specific surface of which the first heater is arranged, and a third block including the wavelength conversion element that converts the wavelength of the fundamental laser beam and a second temperature sensor are arranged and on a specific surface of which a second heater is arranged, enabling thus downsizing of the module and improvement of the positioning accuracy of the elements.

摘要翻译： 当激光光源模块包括其中布置有固体激光元件，激发光源和波长转换元件的散热器和支撑散热器的灯杆时，其中散热器被分成三块，即 布置包括用于固体激光元件的激光振荡单元的第一块，布置包括发射用于激光振荡单元的激发光的半导体激光元件的第二块和第一温度传感器，并且其特定表面上的第一加热器 并且配置有包括转换基波激光束的波长的波长转换元件和第二温度传感器的第三块，并且在其特定表面上布置有第二加热器，从而能够实现模块的小型化和改进 元素的定位精度。

公开(公告)号：US08009879B2

公开(公告)日：2011-08-30

申请号：US11693614

申请日：2007-03-29

申请人： Yoshiaki Iwai ,  Akira Nakamura ,  Weiguo Wu ,  Takayuki Yoshigahara

发明人： Yoshiaki Iwai ,  Akira Nakamura ,  Weiguo Wu ,  Takayuki Yoshigahara

IPC分类号： G06K9/62

CPC分类号： G06K9/50 ,  G06K9/6211

摘要： Disclosed herein is an object recognition device for recognition of an object that exists in an image, the device including: an edge image creator configured to create an edge image from a target image; a local feature extractor configured to extract a feature of each edge point on an edge image, and determine a base point and a support point from edge points in a local area defined for the edge image; a feature matching unit configured to implement, with reference to a memory, feature matching of a base point and a support point to thereby acquire a matching pair; and a matching pair determiner configured to determine final matching pairs by employing matching pairs having a highest matching cost among matching pairs obtained by the feature matching unit, wherein an object in a target image is identified based on matching pairs determined by the matching pair determiner.

摘要翻译： 这里公开了一种用于识别存在于图像中的对象的对象识别装置，该装置包括：边缘图像创建器，被配置为从目标图像创建边缘图像; 局部特征提取器，被配置为提取边缘图像上的每个边缘点的特征，并且从为边缘图像定义的局部区域中的边缘点确定基点和支持点; 特征匹配单元，被配置为参照存储器实现基点和支持点的特征匹配，从而获取匹配对; 以及匹配对确定器，被配置为通过使用由所述特征匹配单元获得的匹配对中具有最高匹配成本的匹配对来确定最终匹配对，其中，基于由所述匹配对确定器确定的匹配对来识别目标图像中的对象。

公开(公告)号：US20110128612A1

公开(公告)日：2011-06-02

申请号：US12952367

申请日：2010-11-23

申请人： Chise Namba ,  Takayuki Yanagisawa ,  Motoaki Tamaya ,  Takashi Shirase ,  Akira Nakamura

发明人： Chise Namba ,  Takayuki Yanagisawa ,  Motoaki Tamaya ,  Takashi Shirase ,  Akira Nakamura

IPC分类号： G02F1/35

CPC分类号： G02F1/3775 ,  G02F2203/21

摘要： In a wavelength conversion element in which a periodic poled crystal that converts an input laser light into a laser light of a predetermined wavelength is provided on a thick-film resistance substrate including a heating unit, a heat spreader having a predetermined thermal conductivity, which equalizes a temperature distribution of the periodic poled crystal, is provided between the thick-film resistance substrate and the periodic poled crystal, and the thick-film resistance substrate and the heat spreader, and the heat spreader and the periodic poled crystal are adhered by an adhesive member having a predetermined thermal conductivity.

摘要翻译： 在包括加热单元的厚膜电阻基板上设置有将输入激光转换为预定波长的激光的周期性极化晶体的波长转换元件，具有预定热传导率的散热器 在厚膜电阻基板和周期极化晶体之间设置周期极化晶体的温度分布，并且通过粘合剂粘附厚膜电阻基板和散热器，散热器和周期性极化晶体 构件具有预定的导热性。

公开(公告)号：US07909469B2

公开(公告)日：2011-03-22

申请号：US12080904

申请日：2008-04-07

申请人： Izushi Kobayashi ,  Yutaka Sugawara ,  Akihiro Kojima ,  Akira Nakamura ,  Katsuhisa Ito

发明人： Izushi Kobayashi ,  Yutaka Sugawara ,  Akihiro Kojima ,  Akira Nakamura ,  Katsuhisa Ito

IPC分类号： G03B21/28 ,  G02B26/08

CPC分类号： G02B26/12 ,  G03B21/28

摘要： Disclosed herein is an image projecting apparatus, including: a one-dimension type light modulating device for modulating a light in accordance with image information; a projection optical system; and a light deflecting device for deflecting an image light in a direction approximately perpendicular to an extension direction of a one-dimensional image light emitted from the one-dimensional light modulating device; wherein the light deflecting device is composed of a first light deflecting device arranged between the projection optical system and the one-dimension type light modulating device, and a second light deflecting device arranged on an emission side of the projection optical system; the second light deflecting device is detachably mounted.

摘要翻译： 这里公开了一种图像投影装置，包括：一维型光调制装置，用于根据图像信息调制光; 投影光学系统; 以及光偏转装置，用于使图像光沿与所述一维光调制装置发射的一维图像光的延伸方向大致垂直的方向偏转; 其中所述光偏转装置由布置在所述投影光学系统和所述一维型光调制装置之间的第一光偏转装置和布置在所述投影光学系统的发射侧的第二光偏转装置构成; 第二光偏转装置可拆卸地安装。