会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • FACE POSE ESTIMATION DEVICE, FACE POSE ESTIMATION METHOD AND FACE POSE ESTIMATION PROGRAM
    • 脸谱估计装置,脸谱估计方法和脸谱预测方案
    • US20110052013A1
    • 2011-03-03
    • US12863132
    • 2009-01-16
    • Hideaki SasaharaYoshihiro NoguchiKeiji Shimada
    • Hideaki SasaharaYoshihiro NoguchiKeiji Shimada
    • G06K9/00
    • G06K9/00248G06T7/11G06T7/149G06T7/75G06T2207/10016G06T2207/30201G06T2207/30268
    • An object is to provide a face pose estimating device, a face pose estimating method, and a face pose estimating program that allow high accuracy estimation of a face pose even if a face organ cannot be detected from an image. A face organ detector 11 of the face pose estimating device 10 detects a face organ from an image frame. A face pose candidate set generator 16 generates a face pose candidate set. A first similarity estimator 12 computes 3D-model-based similarities. A second similarity estimator 13 computes appearance-based similarities. A first likelihood estimator 141 computes a first likelihood corresponding to the 3D-model-based similarity. A second likelihood estimator 142 computes a second likelihood corresponding to the appearance-based similarities. An integrated likelihood estimator 143 computes an integrated likelihood by using the first and second likelihoods. A face pose estimator 15 estimates the face pose by using the integrated likelihood.
    • 目的是提供即使不能从图像中检测到脸部器官,也能够提供脸部姿态估计装置,脸部姿势估计方法和面部姿势估计程序,其允许对脸部姿势的高精度估计。 面部姿势估计装置10的面部器官检测器11从图像帧检测面部器官。 面部姿势候选组发生器16生成面部姿势候选组。 第一相似度估计器12计算基于3D模型的相似度。 第二相似度估计器13计算基于外观的相似度。 第一似然估计器141计算与基于3D模型的相似性相对应的第一似然。 第二似然估计器142计算与基于外观的相似度相对应的第二似然。 综合似然估计器143通过使用第一和第二可能性来计算积分似然。 面部姿势估计器15通过使用综合似然估计面部姿势。
    • 2. 发明授权
    • Face pose estimation device, face pose estimation method and face pose estimation program
    • 面部姿态估计装置,面部姿态估计方法和面部姿态估计程序
    • US08401251B2
    • 2013-03-19
    • US12863132
    • 2009-01-16
    • Hideaki SasaharaYoshihiro NoguchiKeiji Shimada
    • Hideaki SasaharaYoshihiro NoguchiKeiji Shimada
    • G06K9/00G06K9/34
    • G06K9/00248G06T7/11G06T7/149G06T7/75G06T2207/10016G06T2207/30201G06T2207/30268
    • An object is to provide a face pose estimating device, a face pose estimating method, and a face pose estimating program that allow high accuracy estimation of a face pose even if a face organ cannot be detected from an image. A face organ detector 11 of the face pose estimating device 10 detects a face organ from an image frame. A face pose candidate set generator 16 generates a face pose candidate set. A first similarity estimator 12 computes 3D-model-based similarities. A second similarity estimator 13 computes appearance-based similarities. A first likelihood estimator 141 computes a first likelihood corresponding to the 3D-model-based similarity. A second likelihood estimator 142 computes a second likelihood corresponding to the appearance-based similarities. An integrated likelihood estimator 143 computes an integrated likelihood by using the first and second likelihoods. A face pose estimator 15 estimates the face pose by using the integrated likelihood.
    • 目的是提供即使不能从图像中检测到脸部器官,也能够提供脸部姿态估计装置,脸部姿势估计方法和面部姿势估计程序,其允许对脸部姿势的高精度估计。 面部姿势估计装置10的面部器官检测器11从图像帧检测面部器官。 面部姿势候选组发生器16生成面部姿势候选组。 第一相似度估计器12计算基于3D模型的相似度。 第二相似度估计器13计算基于外观的相似度。 第一似然估计器141计算与基于3D模型的相似性相对应的第一似然。 第二似然估计器142计算与基于外观的相似度相对应的第二似然。 综合似然估计器143通过使用第一和第二可能性来计算积分似然。 面部姿势估计器15通过使用综合似然估计面部姿势。
    • 3. 发明授权
    • Device, program, and method for classifying behavior content of an object person
    • 用于分类对象人物行为内容的设备,程序和方法
    • US07894637B2
    • 2011-02-22
    • US11596258
    • 2005-05-23
    • Yoshihiro NoguchiKeiji ShimadaKen Ishihara
    • Yoshihiro NoguchiKeiji ShimadaKen Ishihara
    • G06K9/00
    • G06K9/6297G06K9/00335G06K9/00624G06K9/00832G10L15/25G10L25/78
    • A face portion detection device, a behavior content classification device, a speech content classification device, a car navigation system, a face direction classification device, a face portion detection device control program, a behavior content classification device control program, a face portion detection device control method, and a behavior content classification device control method are provided for appropriately classifying a behavior content of the object person from a captured image including the face of the object person. A speech section detection device 1 includes an image capturing unit 10, a data storage unit 11, an image processing unit 12, a lip region detection unit 13, feature extraction unit 14, and a speech section detection unit 15. The lip region detection unit 13 uses a dedicated SVM to detect a lip region from a captured image, and the speech section detection unit 15 uses features of an image of a detected lip region and a dedicated HMM to detect a speech section.
    • 面部检测装置,行为内容分类装置,语音内容分类装置,汽车导航系统,面部方向分类装置,面部检测装置控制程序,行为内容分类装置控制程序,面部检测装置 提供控制方法和行为内容分类装置控制方法,用于从包括对象人物的脸部的拍摄图像适当地分类对象人物的行为内容。 语音部分检测装置1包括图像拍摄单元10,数据存储单元11,图像处理单元12,唇部区域检测单元13,特征提取单元14和语音区段检测单元15.唇部区域检测单元 13使用专用SVM从拍摄图像检测唇部区域,语音区间检测单元15使用检测到的唇区域和专用HMM的图像的特征来检测语音区段。
    • 4. 发明申请
    • Behavior Content Classification Device
    • 行为内容分类设备
    • US20080037837A1
    • 2008-02-14
    • US11596258
    • 2005-05-23
    • Yoshihiro NoguchiKeiji ShimadaKen Ishihara
    • Yoshihiro NoguchiKeiji ShimadaKen Ishihara
    • G06K9/00
    • G06K9/6297G06K9/00335G06K9/00624G06K9/00832G10L15/25G10L25/78
    • A face portion detection device, a behavior content classification device, a speech content classification device, a car navigation system, a face direction classification device, a face portion detection device control program, a behavior content classification device control program, a face portion detection device control method, and a behavior content classification device control method are provided for appropriately classifying a behavior content of the object person from a captured image including the face of the object person. A speech section detection device 1 includes an image capturing unit 10, a data storage unit 11, an image processing unit 12, a lip region detection unit 13, feature extraction unit 14, and a speech section detection unit 15. The lip region detection unit 13 uses a dedicated SVM to detect a lip region from a captured image, and the speech section detection unit 15 uses features of an image of a detected lip region and a dedicated HMM to detect a speech section.
    • 面部检测装置,行为内容分类装置,语音内容分类装置,汽车导航系统,面部方向分类装置,面部检测装置控制程序,行为内容分类装置控制程序,面部检测装置 提供控制方法和行为内容分类装置控制方法,用于从包括对象人物的脸部的拍摄图像适当地分类对象人物的行为内容。 语音部分检测装置1包括图像捕获单元10,数据存储单元11,图像处理单元12,唇部区域检测单元13,特征提取单元14和语音区段检测单元15。 唇区域检测单元13使用专用SVM从捕获图像中检测唇部区域,并且语音区段检测单元15使用检测到的唇区域和专用HMM的图像的特征来检测语音区段。
    • 9. 发明授权
    • Rotary stencil printer having gear train for synchronizing inner press
roller with printing drum and including clutch for press bias control
    • 旋转模版印刷机具有用于使内压辊与印版滚筒同步的齿轮系,并包括用于压偏偏压控制的离合器
    • US5603260A
    • 1997-02-18
    • US567164
    • 1995-12-05
    • Yoshiharu OhinataYasuhiro TakahashiYoshihiro Noguchi
    • Yoshiharu OhinataYasuhiro TakahashiYoshihiro Noguchi
    • B41L13/04B41L13/16B41L13/18B41M1/12
    • B41L13/04
    • The rotation of the inner press roller 16 is synchronized with the rotation of the printing drum 10 by the gear train including a gear wheel 22 coaxial with the printing drum, a gear wheel 24 meshing with the gear wheel 22 and rotatably supported by an arm 26 swingable about the central axis of the printing drum, and a gear wheel 28 meshing with the gear wheel 24 and coaxially connected with the inner press roller 16 to rotate therewith and rotatably supported by an arm 18 swingable about a pivot axis Ob parallel with and distant from the central axis Oa of the printing drum. A clutch 86 is provided to apply a torque from the printing drum when driven to the arm 26 to control the biasing out operation of the inner press roller 12 against the circumferential wall 12 of the printing drum. The clutch may be replaced by the linear actuator 96. The clutch or linear actuator may be temporarily actuated stronger during a starting up of the printing operation. The distance between the axes of the gear wheels 24 and 28 may desirably be restricted not to increase beyond a predetermined distance.
    • 内压辊16的旋转与印刷鼓10的旋转同步,齿轮系包括与印刷鼓同轴的齿轮22,与齿轮22啮合并由臂26可旋转地支撑的齿轮24 可绕着印刷鼓的中心轴线摆动,齿轮28与齿轮24啮合并与内压辊16同轴连接,以便与其一起旋转并由臂18可旋转地支撑,该臂18围绕平行于和远离的枢转轴线 从印刷鼓的中心轴线Oa。 离合器86设置成当被驱动到臂26时施加来自印刷鼓的转矩,以控制内压辊12抵靠印版滚筒的周壁12的偏压操作。 离合器可以由线性致动器96代替。离合器或线性致动器可以在打印操作的启动期间被暂时地致动。 齿轮24和28的轴线之间的距离可以期望地被限制为不增加超过预定距离。
    • 10. 发明授权
    • Track jumping control apparatus
    • 轨道跳跃控制装置
    • US5216650A
    • 1993-06-01
    • US718675
    • 1991-06-21
    • Yoshihiro Noguchi
    • Yoshihiro Noguchi
    • G11B7/085
    • G11B7/08541
    • Clock pulses are generated at a frequency having a fixed relation with a rotation of an information recording disk formed with a track. The clock pulses are counted. A first kick pulse is generated when the counting of the clock pulses starts. A tracking error signal is generated. A detection is made as to whether the tracking error signal crosses a zero level after the first kick pulse is generated. A brake pulse is generated when the tracking error signal crosses the zero level. A second kick pulse is generated when a number of the counted clock pulses reaches a predetermined number.
    • 以与形成有轨道的信息记录盘的旋转具有固定关系的频率产生时钟脉冲。 时钟脉冲被计数。 当时钟脉冲的计数开始时,产生第一个脉冲。 产生跟踪误差信号。 在产生第一个反冲脉冲之后,检测跟踪误差信号是否超过零电平。 当跟踪误差信号越过零电平时,产生制动脉冲。 当多个计数的时钟脉冲达到预定数量时,产生第二反冲脉冲。