知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

18 条记录 (耗时 0.013 秒)

    Method and system for similarity-based image classification
    1.
    发明授权
    Method and system for similarity-based image classification 失效
    基于相似度图像分类的方法和系统

    公开(公告)号：US06240424B1

    公开(公告)日：2001-05-29

    申请号：US09064086

    申请日：1998-04-22

    申请人： Kyoji Hirata

    发明人： Kyoji Hirata

    IPC分类号： G06F1730

    CPC分类号： G06F17/30253 ,  Y10S707/915 ,  Y10S707/99931 ,  Y10S707/99945

    摘要： A method and apparatus for classifying and querying a database of images, in which the images in the database are classified using primary objects as a clustering center. A query interface is presented to the user allowing the user to use the primary objects to formulate queries to be applied to the classified database of images.

    摘要翻译： 一种用于对图像数据库进行分类和查询的方法和装置，其中使用主对象作为聚类中心对数据库中的图像进行分类。 向用户呈现查询界面，允许用户使用主要对象来制定要应用于图像分类数据库的查询。

    Method and system for image querying using region based and boundary based image matching
    2.
    发明授权
    Method and system for image querying using region based and boundary based image matching 失效
    使用基于区域和边界的图像匹配的图像查询的方法和系统

    公开(公告)号：US06240423B1

    公开(公告)日：2001-05-29

    申请号：US09064061

    申请日：1998-04-22

    申请人： Kyoji Hirata

    发明人： Kyoji Hirata

    IPC分类号： G06F1700

    CPC分类号： G06F17/30274 ,  G06F17/30259 ,  Y10S707/99931 ,  Y10S707/99945 ,  Y10S707/99948

    摘要： A method and apparatus for querying a database of images, in which the results of the query are based upon a combination of region based image matching and boundary based image matching. Additionally similarity calculations are made between individual results of the query so that the results may be clustered based upon similarity.

    摘要翻译： 一种用于查询图像数据库的方法和装置，其中查询的结果基于基于区域的图像匹配和基于边界的图像匹配的组合。 另外，在查询的各个结果之间进行相似性计算，使得结果可以基于相似性进行聚类。

    Documentation browsing method, documentation browsing apparatus, documentation browsing robot, and documentation browsing program
    4.
    发明授权
    Documentation browsing method, documentation browsing apparatus, documentation browsing robot, and documentation browsing program 失效
    文档浏览方法，文档浏览设备，文档浏览机器人和文档浏览程序

    公开(公告)号：US07734996B2

    公开(公告)日：2010-06-08

    申请号：US10570755

    申请日：2004-08-31

    申请人： Kyoji Hirata

    发明人： Kyoji Hirata

    IPC分类号： G06N3/00

    CPC分类号： G10L15/26

    摘要： To enable a person to effectively create a document based on image data or audio data of a recorded meeting or a recorded lecture and also a person who creates the minutes of a meeting or a participant to browse a summarized document with images or voices so that a plurality of persons can effectively perform documentation.The audio/image inputting means 10 generates image data by recording a meeting and audio data by recording the contents of the meeting. The document inputting means 20 generates document data including a drafted minutes of a meeting or the like inputted by a person who creates the minutes of a meeting. The relationship deriving means 50 generates correspondence table data by deriving relationship between voices or images and a document based on audio data or image data and document data. The relationship presenting means 60 displays voices or images and a document in association with each other based on the correspondence table data.

    摘要翻译： 为了使人能够基于记录的会议或录音讲座的图像数据或音频数据以及创建会议记录或参与者的图像或语音来浏览汇总的文档而有效地创建文档，使得 多个人可以有效地执行文件。 音频/图像输入装置10通过记录会议的内容来记录会议和音频数据来生成图像数据。 文档输入装置20生成包括由创建会议记录的人输入的会议等的草稿分钟的文档数据。 关系导出装置50通过基于音频数据或图像数据和文档数据导出语音或图像与文档之间的关系来生成对应表数据。 关系呈现装置60基于对应表数据彼此相关联地显示语音或图像和文档。

    PROTOCOL MISMATCH DETECTION SYSTEM, PROTOCOL MISMATCH DETECTION METHOD, AND PROTOCOL MISMATCH DETECTION PROGRAM
    5.
    发明申请
    PROTOCOL MISMATCH DETECTION SYSTEM, PROTOCOL MISMATCH DETECTION METHOD, AND PROTOCOL MISMATCH DETECTION PROGRAM 审中-公开
    协议错误匹配检测系统，协议错误匹配检测方法和协议错误检测程序

    公开(公告)号：US20100076938A1

    公开(公告)日：2010-03-25

    申请号：US12448820

    申请日：2007-12-26

    申请人： Ken HANAZAWA ,  Kyoji HIRATA ,  MASAHIRO IWADARE

    发明人： Ken HANAZAWA ,  Kyoji HIRATA ,  MASAHIRO IWADARE

    IPC分类号： G06F17/30 ,  G06F17/00 ,  G06F17/27

    CPC分类号： G06F17/2735 ,  G06F17/2795

    摘要： A protocol mismatch detection system (1) includes: a protocol database (10); input means (11) for inputting data to be accumulated in the protocol database (10); protocol data accumulation means (12) for accumulating the inputted data in the protocol database (10); announced content reception means (13) for receiving an announced content from outside; a protocol mismatch detection means (14) for referencing the protocol database (10) to detect a portion of the announced content received which does not coincide with the protocol of a user in the protocol mismatch detection system (1); and output means (15) for outputting the detected protocol mismatch and the protocol mismatch portion.

    摘要翻译： 协议失配检测系统（1）包括：协议数据库（10）; 用于输入要在协议数据库（10）中累积的数据的输入装置（11）; 用于在所述协议数据库（10）中累积输入的数据的协议数据累积装置（12）。 宣布的从外部接收宣告的内容的内容接收装置（13） 用于引用所述协议数据库（10）以检测在所述协议失配检测系统（1）中与所述用户的协议不一致的所接收的所述已宣告内容的一部分的协议失配检测装置（14）。 以及用于输出检测到的协议失配和协议失配部分的输出装置（15）。

    Video object recognition device and recognition method, video annotation giving device and giving method, and program
    6.
    发明申请
    Video object recognition device and recognition method, video annotation giving device and giving method, and program 审中-公开
    视频对象识别装置和识别方法，视频注释给出装置和给出方法以及程序

    公开(公告)号：US20060195858A1

    公开(公告)日：2006-08-31

    申请号：US10553431

    申请日：2004-04-15

    申请人： Yusuke Takahashi ,  Kyoji Hirata

    发明人： Yusuke Takahashi ,  Kyoji Hirata

    IPC分类号： H04H9/00 ,  H04N7/16 ,  G06K9/00

    CPC分类号： G06K9/00664 ,  G01C21/3602 ,  G01C21/3647

    摘要： Visual feature information which is information representing a numerical value of a visual feature of an object and additional information which is information added to the object are stored in association with each other. Partial image data which is image data of a partial area of a video image is extracted. Visual feature information of the extracted partial image data is generated. The visual feature information of the extracted partial image data and visual feature information of an object which is stored are compared with each other to calculate a similarity therebetween. Based on the calculated similarity, an object contained in the video image data is identified. An annotation made up of additional information of the identified object is displayed in superposing relation to the video image on a display device.

    摘要翻译： 作为对象的视觉特征的数值的信息的视觉特征信息和作为​​添加到对象的信息的附加信息彼此关联地存储。 提取作为视频图像的局部区域的图像数据的部分图像数据。 生成提取的部分图像数据的视觉特征信息。 将所提取的部分图像数据的视觉特征信息和存储的对象的视觉特征信息彼此进行比较，以计算它们之间的相似度。 基于计算的相似度，识别包含在视频图像数据中的对象。 由识别对象的附加信息构成的注释以与显示设备上的视频图像重叠的关系显示。

    Image index production method and image index production system for image storage and management system
    8.
    发明授权
    Image index production method and image index production system for image storage and management system 失效
    图像索引生产方法和图像存储和管理系统的图像索引生产系统

    公开(公告)号：US5781899A

    公开(公告)日：1998-07-14

    申请号：US548728

    申请日：1995-10-26

    申请人： Kyoji Hirata

    发明人： Kyoji Hirata

    IPC分类号： G06F17/30 ,  G06T1/00 ,  G06T7/60

    CPC分类号： G06F17/3025 ,  G06F17/30259 ,  Y10S707/915 ,  Y10S707/99936 ,  Y10S707/99943

    摘要： The similarity between zones which consist of one or plural pixels in an original image is measured, the similarity between the measured zones and the threshold of the similarity for integrating the zones consisting of one or plural pixels in the original image are received, and the original image is divided to make the similarity between respective zones lower than the threshold. The size of the zone-divided image for the image index is determined to make the number of total zones of the current divided image equal to the number of zones to be finally divided as an index. Attribute information on the zones of the zone-divided image is calculated to produce an index.

    摘要翻译： 测量由原始图像中的一个或多个像素构成的区域之间的相似度，接收测量区域之间的相似度和用于对由原始图像中的一个或多个像素组成的区域进行积分的相似度阈值，并且原始图像 图像被划分以使各个区域之间的相似度低于阈值。 确定图像索引的区域分割图像的大小，使得当前分割图像的总区域数量等于最终被划分的区域的数量作为索引。 计算区域分割图像区域的属性信息，以产生索引。

    INFORMATION DISPLAY SYSTEM, INFORMATION DISPLAY METHOD, AND RECORDING MEDIUM
    9.
    发明申请
    INFORMATION DISPLAY SYSTEM, INFORMATION DISPLAY METHOD, AND RECORDING MEDIUM 有权
    信息显示系统，信息显示方法和记录介质

    公开(公告)号：US20140292653A1

    公开(公告)日：2014-10-02

    申请号：US14241812

    申请日：2012-09-05

    申请人： Tomonari Kamba ,  Kyoji Hirata

    发明人： Tomonari Kamba ,  Kyoji Hirata

    IPC分类号： G06F3/0346 ,  G06T19/00

    CPC分类号： G06F3/0346 ,  G02B27/017 ,  G02B2027/014 ,  G02B2027/0187 ,  G06F3/011 ,  G06F3/0304 ,  G06F3/03545 ,  G06F3/0488 ,  G06T19/006

    摘要： In an AR device, when display control of additional information is performed for an object, a display device acquires a picture including an object in real space. An pointing device outputs, when pointing the object in real space by an operation of a user, information showing a feature for identifying the pointed object. A control device analyzes the picture by the display device and identifies objects in the picture. The control device outputs position information in the picture for the identified object. The control device outputs position information in the picture for the pointed object based on the outputted information from the pointing device. The control device extracts additional information of a target object from an additional information group of objects in real space. The control device performs display control of the additional information based on the calculated position information. The display device displays the additional information.

    摘要翻译： 在AR装置中，当对对象执行附加信息的显示控制时，显示装置获取包含实际空间中的对象的图像。 当通过用户的操作将对象指向实际空间时，指示装置输出显示用于识别所指向的对象的特征的信息。 控制装置通过显示装置分析图像并识别图像中的对象。 控制装置输出用于识别对象的图像中的位置信息。 控制装置基于来自指示装置的输出信息，输出针对对象的画面中的位置信息。 控制装置从实际空间中的对象的附加信息组提取目标对象的附加信息。 控制装置基于计算出的位置信息来执行附加信息的显示控制。 显示设备显示附加信息。