专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2011107795A Image retrieval system 有权
标题翻译：图像检索系统
公开(公告)号：JP2011107795A
公开(公告)日：2011-06-02
申请号：JP2009259427
申请日：2009-11-13
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： HIROIKE ATSUSHI , AKIRA NAOTO , MATSUBARA DAISUKE
IPC分类号： G06T1/00 , G06F17/30
摘要： PROBLEM TO BE SOLVED: To achieve efficient retrieval by summarizing a plurality of retrieval queries corresponding to similar vector retrieval by clustering. SOLUTION: A system is provided with: a means for generating a plurality of image featured value vectors from a single image; a means for summarizing a plurality of generated image featured value vectors into a small number of representative vectors by clustering processing; and a means for performing similar vector retrieval by using each of the summarized representative vectors as a retrieval query, and for acquiring the maximum proximity data of each of pre-generated image featured value vectors. COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：通过总结与通过聚类相似的向量检索相对应的多个检索查询来实现有效的检索。解决方案：一种系统设置有：用于从单个图像生成多个图像特征值向量的装置; 用于通过聚类处理将多个生成的图像特征值向量汇总为少数代表向量的装置; 以及用于通过使用每个汇总的代表向量作为检索查询执行类似的向量检索的装置，并且用于获取每个预生成的图像特征值向量的最大接近度数据。版权所有（C）2011，JPO＆INPIT

2. 发明专利

JP2011018238A Image retrieval system and image retrieval method 有权
标题翻译：图像检索系统和图像检索方法
公开(公告)号：JP2011018238A
公开(公告)日：2011-01-27
申请号：JP2009163095
申请日：2009-07-09
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： MATSUBARA DAISUKE , HIROIKE ATSUSHI , KAGEHIRO TATSUHIKO , AKIRA NAOTO
IPC分类号： G06T1/00 , G06F17/30 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To efficiently retrieve a target person by a retrieval key not depending on a person or a specific portion of the person without accurately detecting a person area.SOLUTION: An image retrieval system is provided for retrieving an image similar to an image designated by a user. An image acquired from a video or the like captured by a camera is divided into blocks each having a predetermined size. The characteristic amount of the block is extracted based on a color histogram. First information indicating correspondence relation among an identifier of the image, information on a position of the block, and the characteristic amount of the block is created. The characteristic amount of the first retrieval key and the characteristic amount of another block are compared with at least one block selected by the user of the divided blocks as the first retrieval key, based on the first information to detect a predetermined number of blocks similar to the first retrieval key as a retrieval result, and the image including the retrieval result is displayed to the user.
摘要翻译：要解决的问题：通过不依赖于人或特定部分的检索键有效地检索目标人，而无需准确地检测人的区域。解决方案：提供用于检索类似于图像的图像的图像检索系统由用户指定从由照相机拍摄的视频等获取的图像被分成具有预定尺寸的块。基于颜色直方图提取块的特征量。指示图像的标识符，块的位置的信息和块的特征量之间的对应关系的第一信息。基于第一信息，将第一检索关键字的特征量和另一块的特征量与由划分块的用户选择的至少一个块作为第一检索关键字进行比较，以检测预定数量的类似于第一检索关键字作为检索结果，并且包括检索结果的图像被显示给用户。

3. 发明专利

JP2009294855A Similar data retrieval system 有权
标题翻译：类似数据检索系统
公开(公告)号：JP2009294855A
公开(公告)日：2009-12-17
申请号：JP2008147060
申请日：2008-06-04
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： MATSUBARA DAISUKE , HIROIKE ATSUSHI
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To reduce the load of disk scanning by arranging feature value vectors so that featured value vectors whose similarity is high can be closely gathered on a secondary storage, and that the order of the number of closely gathering data can be turned into O(N
c ) depending on the number N
c of all data.
SOLUTION: In the case of registering new data, the prescribed number of clusters having a cluster average whose inter-vector distance with a featured vector extracted from new data is close is retrieved as a proximity cluster, and optimization by a k-means method with the member of the retrieved proximity cluster and new data as an object. When the number of members of the cluster exceeds the upper limit, the cluster is divided into two part, and the newly created cluster is added to the group of approximate clusters. The update of the cluster management is performed by making energy functions have the relation of the adjacent clusters and information showing where each cluster should be arranged in the whole cluster array.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：为了通过排列特征值向量来减少磁盘扫描的负担，使得可以在二级存储器上紧密地收集相似度高的特征值向量，并且紧密收集数据的顺序可以根据所有数据的数量N c ，变为O（N c ）。解决方案：在注册新数据的情况下，将具有与从新数据提取的特征向量的矢量间距离相近的聚类平均值的规定数量的集合作为近邻集群进行检索，并通过k- 是将检索到的邻近集群的成员和新数据作为对象的方法。当集群成员数量超过上限时，集群分为两部分，新创建的集群被添加到一组近似集群中。通过使能量函数具有相邻簇的关系和示出在整个簇阵列中应该布置每个簇的位置的信息来执行群集管理的更新。版权所有（C）2010，JPO＆INPIT

4. 发明专利

JP2013246544A Image search device and image search method 有权
标题翻译：图像搜索设备和图像搜索方法
公开(公告)号：JP2013246544A
公开(公告)日：2013-12-09
申请号：JP2012118320
申请日：2012-05-24
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： AKIRA NAOTO , HIROIKE ATSUSHI
IPC分类号： G06F17/30
摘要： PROBLEM TO BE SOLVED: To provide a search technology for improving accuracy, and for reducing omission from search in the case of searching for an image in a document by designating a keyword.SOLUTION: An image search device searches for an image which is similar to an image in document data including a search character string, and on the basis of the information amount of the search character string in the document data including the similar image and the information amount of the search character string in all document data, determines whether or not the image expresses the content of the search character string.
摘要翻译：要解决的问题：提供一种用于提高精度的搜索技术，并且通过指定关键字来搜索文档中的图像的情况下减少搜索中的遗漏。解决方案：图像搜索装置搜索类似于包括搜索字符串的文档数据中的图像，并且基于包括类似图像的文档数据中的搜索字符串的信息量和所有文档数据中的搜索字符串的信息量，确定是否图像表示搜索字符串的内容。

5. 发明专利

JP2009171472A System and device for monitoring network video image 有权
标题翻译：用于监控网络视频图像的系统和设备
公开(公告)号：JP2009171472A
公开(公告)日：2009-07-30
申请号：JP2008009864
申请日：2008-01-18
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： AKIRA NAOTO , HIROIKE ATSUSHI , KAGEHIRO TATSUHIKO , URANO TAKEHIRO , HIGASHIMURA KUNIHIKO
IPC分类号： H04N5/93 , G06F17/30 , H04N5/76 , H04N5/91 , H04N5/915 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To efficiently confirm video image data picked up with a plurality of cameras.
SOLUTION: This video image network system includes a plurality of cameras for picking up video images, a retrieval device for retrieving video images picked up with the cameras and transmitting retrieving information created based on the video images picked up with the cameras to a monitor device, a video image storage device for storing video images picked up with the cameras, and the monitor device for displaying the picked-up video images. The monitor device displays a retrieving image contained in the retrieving information received from the retrieving device, determines whether or not a video image relevant to the retrieving information received from the retrieving device is required based on the retrieving information, and when it is judged that the video image relevant to the retrieving information is required, requires the video image storage device to provide the video image relevant to the retrieving information, and displays video image data acquired from the video image storage device.
COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：有效地确认用多个照相机拾取的视频图像数据。解决方案：该视频图像网络系统包括用于拾取视频图像的多个摄像机，用于检索用照相机拾取的视频图像的检索装置，以及基于由相机拾取的视频图像创建的检索信息到监视器装置，用于存储用相机拾取的视频图像的视频图像存储装置，以及用于显示拾取的视频图像的监视装置。监视器装置显示包含在从检索装置接收的检索信息中的检索图像，根据检索信息确定是否需要与从检索装置接收到的检索信息相关的视频图像，并且当判断为需要与检索信息相关的视频图像，要求视频图像存储装置提供与检索信息相关的视频图像，并且显示从视频图像存储装置获取的视频图像数据。版权所有（C）2009，JPO＆INPIT

6. 发明专利

JP2011197892A Image retrieval system 有权
标题翻译：图像检索系统
公开(公告)号：JP2011197892A
公开(公告)日：2011-10-06
申请号：JP2010062619
申请日：2010-03-18
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： AKIRA NAOTO , HIROIKE ATSUSHI
IPC分类号： G06F17/30 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To perform image retrieval considering the contents and layout of an object.SOLUTION: An object image related to an input retrieval keyword is acquired on the basis of the retrieval keyword while referring to object information data, a layout of the object image is estimated on the basis of the size and positional information of the object image included in the object information data, a synthesized image in which the object image is arranged on a position where the object image frequently appears is generated, and a retrieval target image is retrieved by using the synthesized image as a query image to achieve image retrieval using the keyword as an input.
摘要翻译：要解决的问题：考虑到对象的内容和布局来执行图像检索。解决方案：在引用对象信息数据的基础上，基于检索关键字获取与输入检索关键字相关的对象图像，对象的布局基于对象信息数据中包括的对象图像的大小和位置信息来估计图像，生成对象图像经常出现的位置被布置的合成图像，以及检索对象图像通过使用合成图像作为查询图像来检索，以使用关键字作为输入来实现图像检索。

7. 发明专利

JP2010183355A Data acquisition system and transmission control device 有权
标题翻译：数据采集系统和传输控制设备
公开(公告)号：JP2010183355A
公开(公告)日：2010-08-19
申请号：JP2009025047
申请日：2009-02-05
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： ODAKA TOSHIYUKI , HIGASHIMURA KUNIHIKO , NAKAYAMA MARIKO , HIROIKE ATSUSHI , KAGEHIRO TATSUHIKO
IPC分类号： H04Q9/00 , H04L12/801 , H04L12/911
CPC分类号： H04N7/181 , H04L47/2475 , H04L47/26 , H04L47/805
摘要： PROBLEM TO BE SOLVED: To acquire data wherein a resource is effectively and efficiently utilized in a data acquisition system for acquiring data to a data utilization point from a data generation point. SOLUTION: In the data acquisition system, a transmit-side transmission control device 10 for sending data generated by a data generator device 11 to a data utilization point receives and retains notification of the allowable data transmission quantity from a receive-side transmission control device 20, and adjusts the data quantity sent from the data generator device 11 so as to fit within that allowable data transmission quantity range, and/or when a request is issued to change that data transmission quantity, the receive-side transmission control device 20 is notified of that allowable data transmission quantity change request. The receive-side transmission control device 20 retains the respective allowable data transmission quantities for transmit-side transmission control device 10, and when a change request is issued, reallocates the allowable data transmission quantities for all transmit-side transmission control devices to fit within the data processing load range stored beforehand within the data utilization point, and notifies the corresponding transmit-side transmission control device 10 of these reallocated allowable data transmission quantities. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：获取在数据采集系统中有效地利用资源的数据，用于从数据生成点向数据利用点采集数据。解决方案：在数据采集系统中，用于将由数据发生器装置11生成的数据发送到数据利用点的发送侧发送控制装置10接收并保持来自接收侧发送的允许数据发送量的通知控制装置20，并且调整从数据发生装置11发送的数据量，使其适合该容许数据发送量范围，和/或当发出更改该数据发送量的请求时，接收侧发送控制装置 20通知该允许数据发送量变更请求。接收侧发送控制装置20保持发送侧发送控制装置10的各自的允许数据发送量，并且当发出改变请求时，重新分配所有发送侧发送控制装置的允许数据发送量以适合数据处理负载范围预先存储在数据利用点内，并将相应的发送侧发送控制装置10通知这些重新分配的允许数据发送量。版权所有（C）2010，JPO＆INPIT

8. 发明专利

JP2006146628A Method and apparatus for retrieving document by content image 审中-公开
标题翻译：用于通过内容图像检索文档的方法和装置
公开(公告)号：JP2006146628A
公开(公告)日：2006-06-08
申请号：JP2004336860
申请日：2004-11-22
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： SAKO YUTAKA , HIROIKE ATSUSHI
IPC分类号： G06F17/30
CPC分类号： G06F17/30637 , G06F17/30277
摘要： PROBLEM TO BE SOLVED: To provide a document retrieving method capable of improving a retrieval ratio by expressing a document by a plurality of inner images and using the inner images.
SOLUTION: Images to be easily looked at are substituted for a document. Namely images such as photographs, graphics and tables in the document are used as key images of the document. A retrieving logical expression using one or more key images is inputted and all images in documents in which similar images satisfying the retrieving logical expression are included are three-dimensionally displayed on a display screen. When a retriever selects one of the displayed key images, document contents including the key image are displayed.
COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种能够通过用多个内部图像表达文档并使用内部图像来提高检索率的文档检索方法。
解决方案：可轻松查看的图像代替文档。即文件中的照片，图形和表格等图像被用作文档的关键图像。输入使用一个或多个关键图像的检索逻辑表达式，并且包括满足检索逻辑表达式的类似图像的文档中的所有图像被三维地显示在显示屏幕上。当检索者选择显示的关键图像之一时，显示包括关键图像的文档内容。版权所有（C）2006，JPO＆NCIPI

9. 发明专利

JP2006114053A Similar image retrieval method and device 有权
标题翻译：类似图像检索方法和设备
公开(公告)号：JP2006114053A
公开(公告)日：2006-04-27
申请号：JP2005309959
申请日：2005-10-25
申请人： Hitachi Ltd , Ministry Of Economy Trade & Industry , 株式会社日立製作所 , 経済産業大臣
发明人： HIROIKE ATSUSHI , MUSHA YOSHINORI
IPC分类号： G06F17/30 , G06T1/00
摘要： PROBLEM TO BE SOLVED: To visualize the degree of similarity determined by a system in a quantitative form for a user, and to present a large amount of retrieval results in a form well-organized for the user. SOLUTION: In a visualization space 210, images of a retrieval result are displayed as a three-dimensional scatter diagram. The size of each image in the three dimension is associated with the degree of similarity calculated from feature quantity data of each image and feature quantity data of a favorite image and an unfavorite image designated by the user. The degree of similarity is expressed by a real value between 0 and 1; and the image is displayed in the maximum size when it is 1. When it is less than 1, the image is displayed by being reduced in proportion to the degree of similarity. When it is not greater than 0.1, the image is not displayed. The value of the degree of similarity is determined by retrieval conditions. By automatically changing selection of an axis from the feature quantity, mobility is provided for display of the scatter diagram. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：以用户的定量形式可视化由系统确定的相似程度，并以为用户组织的形式呈现大量的检索结果。解决方案：在可视化空间210中，将检索结果的图像显示为三维散点图。三维中的每个图像的尺寸与从每个图像的特征量数据和喜好图像的特征量数据和用户指定的不利图像计算的相似度相关联。相似度由0和1之间的实数值表示; 当图像为1时，以最大尺寸显示图像。当小于1时，通过与相似度成比例地缩小图像来显示图像。当不大于0.1时，图像不显示。相似度的值由检索条件确定。通过自动更改轴从特征量的选择，提供移动性以显示散点图。版权所有（C）2006，JPO＆NCIPI

10. 发明专利

JP2004062356A Method of displaying data aggregate and program 有权
公开(公告)号：JP2004062356A
公开(公告)日：2004-02-26
申请号：JP2002217457
申请日：2002-07-26
申请人： Hitachi Ltd , 株式会社日立製作所
发明人： HIROIKE ATSUSHI , MUSHA YOSHINORI
IPC分类号： G06F17/30
CPC分类号： Y02D10/45
摘要： PROBLEM TO BE SOLVED: To solve the problem that displaying lists, while efficient in terms of using a display screen because there are no overlaps in data display with no wasteful gaps within the screen, is not an expression reflecting the similarity between data; on the other hand, expressing point diagrams, while spatially expressing the similarity between data, is not efficient in terms of using the display screen because overlaps and cover-ups could occur within the display area of each data and areas exist where no data are displayed.
SOLUTION: For an expression where data are arranged in a matrix on a display screen, an energy function is defined which gets higher the lower the similarity between adjacent data gets. By updating the arrangement of the data so that the energy function decreases, the similarity between the data is expressed in the display screen and the data display that efficiently uses the display screen is achieved.
COPYRIGHT: (C)2004,JPO

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式