专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

101. 发明授权

US09471601B2 Images for a question answering system 有权
标题翻译：问答系统的图像
公开(公告)号：US09471601B2
公开(公告)日：2016-10-18
申请号：US14224486
申请日：2014-03-25
申请人： International Business Machines Corporation
发明人： Salil Ahuja , Scott H. Isensee , Scott M. Lewis , William G. O'Keeffe , Cale R. Vardy
IPC分类号： G06F17/30
CPC分类号： G06F17/30268 , G06F17/30277 , G06F17/30412 , G06F17/30643 , G06F17/30867
摘要： A method for providing content relevant images for an input question to a deep question answering system is disclosed. The method can include formulating, in response to receiving the input question, an answer to the input question. The method can also include identifying, based on the answer to the input question, a set of candidate images from a corpus of information. The set of candidate images may relate to the answer. The method can also include determining, based on a confidence value of the set of candidate images and a designated display specification, a first subset of the set of candidate images to provide in a display area. The method can also include selecting the first subset to be provided in the display area.
摘要翻译：公开了一种向深问答系统提供输入问题的内容相关图像的方法。该方法可以包括响应于接收输入问题而形成对输入问题的答案。该方法还可以包括基于输入问题的答案来识别来自信息语料库的一组候选图像。候选图像的集合可以与答案有关。该方法还可以包括基于候选图像集合的置信度值和指定的显示规格来确定在显示区域中提供的候选图像集合的第一子集。该方法还可以包括选择要在显示区域中提供的第一子集。

102. 发明授权

US09466112B1 Zoom and image capture based on features of interest 有权
公开(公告)号：US09466112B1
公开(公告)日：2016-10-11
申请号：US14885763
申请日：2015-10-16
申请人： Google Inc.
发明人： Thad Eugene Starner , Joshua Weaver
IPC分类号： H04N5/232 , G06T7/00 , H04N5/262 , H04N5/225 , G02B27/01 , G06F3/01 , G06F17/30
CPC分类号： G06T7/0042 , G02B27/017 , G02B2027/0138 , G02B2027/014 , G02B2027/0178 , G06F3/013 , G06F17/30256 , G06F17/30268 , G06Q30/02 , H04N5/2253 , H04N5/23222 , H04N5/23293 , H04N5/23296 , H04N5/2628 , H04N7/181
摘要： Methods and systems for intelligently zooming to and capturing a first image of a feature of interest are provided. The feature of interest may be determined based on a first interest criteria. The captured image may be provided to a user, who may indicate a level of interest in the feature of interest. The level of interest may be based upon to store the captured image and capture another image. The level of interest may be a gradient value, or a binary value. The level of interest may be based upon to determine whether to store the captured image, and if so, a resolution at which the captured image is to be stored. The level of interest may also be based upon to determine whether to zoom to and capture a second image of a second feature of interest based on the first interest criteria or a second interest criteria.

103. 发明申请

US20160295157A1 IMAGE PROCESSING APPARATUS AND METHOD 有权
标题翻译：图像处理装置和方法
公开(公告)号：US20160295157A1
公开(公告)日：2016-10-06
申请号：US15036945
申请日：2014-03-25
申请人： HANWHA TECHWIN CO., LTD.
发明人： Sung Bong CHO , Sung Hoon LEE , Seok Ho CHAE , Hyo Jin KIM
IPC分类号： H04N5/91 , G06F17/30 , G06T5/50 , H04N5/77 , G06T7/00
CPC分类号： H04N5/91 , G06F17/30256 , G06F17/30268 , G06F17/30843 , G06F17/30867 , G06T5/50 , G06T7/10 , G06T7/194 , G06T2207/20221 , H04N5/77 , H04N9/8047
摘要： An image processing apparatus includes a storage storing images received from at least one camera, an image analyzer analyzing the images received from the at least one camera, separating an object, for which an event occurred, from a background, and extracting object properties information, a database storing the object properties information extracted with respect to each of the at least one camera, a search condition setter setting a search condition, a search engine searching the database for the object properties information matching the search condition, and obtaining image frames including the object properties information found from the storage, and a file generator generating a single image file by synthesizing the image frames.
摘要翻译：图像处理装置包括存储从至少一个相机接收的图像的存储器，分析从至少一个相机接收的图像的图像分析器，从背景中分离出事件的对象，以及提取对象属性信息，存储关于所述至少一个照相机中的每一个提取的对象属性信息的数据库，设置搜索条件的搜索条件设置器，搜索与搜索条件匹配的对象属性信息的搜索引擎，以及获得包括搜索条件的图像帧从存储器找到的对象属性信息，以及通过合成图像帧生成单个图像文件的文件生成器。

104. 发明申请

US20160292495A1 ASSISTED PHOTO-TAGGING WITH FACIAL RECOGNITION MODELS 审中-公开
公开(公告)号：US20160292495A1
公开(公告)日：2016-10-06
申请号：US15187189
申请日：2016-06-20
申请人： Shutterfly, Inc.
发明人： Andrea R. Johnson , Matthew J. Johnson , Nico Toutenhoofd , Clinton L. Fenton
IPC分类号： G06K9/00 , G06F17/30 , H04N5/77
CPC分类号： G06K9/00288 , G06F17/30244 , G06F17/30247 , G06F17/30256 , G06F17/30268 , G06F17/3028 , G06F17/30345 , G06K9/00221 , G06K9/00261 , G06K9/00268 , G06K9/6201 , G06K2009/00328 , H04N5/77
摘要： Embodiments of the invention perform assisted tagging of images, including tagging of people, locations, and activities depicted in those images. A batch of images is received comprising images of faces, including at least some faces that have not yet been tagged. A facial recognition algorithm is applied to the faces to determine matching data comprising possible tags for each untagged face. A logic engine applies logic rules to reduce the likelihood that certain matches are correct. The most likely match from among the possible matches is selected for suggestion to the user for verification. Once verified, the metadata of the image indicating the recognized people within the image is updated.

105. 发明申请

US20160292176A1 FILE SYSTEM FOR MEDICAL IMAGES AND DATA 有权
标题翻译：用于医学图像和数据的文件系统
公开(公告)号：US20160292176A1
公开(公告)日：2016-10-06
申请号：US14674974
申请日：2015-03-31
申请人： Synaptive Medical (Barbados) Inc.
发明人： Jonathan Resnick
IPC分类号： G06F17/30 , G06F19/00 , G06F3/0484
CPC分类号： G06F19/321 , G06F3/0482 , G06F3/04842 , G06F17/30091 , G06F17/30112 , G06F17/30194 , G06F17/30218 , G06F17/30265 , G06F17/30268 , G06F19/00
摘要： The present invention is an improvement to a computer system for processing, storing and searching DICOM medical imaging objects and non-DICOM files. The improvement is the addition of a directory manager, a user interface and a search manager that allows users to define a hierarchy of directories that link to both DICOM and non-DICOM files. Contents of files are indexed, including metadata so they are searchable. The system automatically creates directories representing DICOM series and studies by analyzing metadata in DICOM image files. DICOM devices can send DICOM data directly to directories in the file system using the DICOM protocol.
摘要翻译：本发明是对用于处理，存储和搜索DICOM医疗成像对象和非DICOM文件的计算机系统的改进。改进之处是添加了一个目录管理器，一个用户界面和一个搜索管理器，允许用户定义链接到DICOM和非DICOM文件的目录的层次结构。索引文件的内容，包括元数据，以便它们可搜索。系统自动创建表示DICOM系列的目录，并通过分析DICOM图像文件中的元数据进行研究。 DICOM设备可以使用DICOM协议将DICOM数据直接发送到文件系统中的目录。

106. 发明授权

US09460117B2 Image searching 有权
标题翻译：图像搜索
公开(公告)号：US09460117B2
公开(公告)日：2016-10-04
申请号：US13683384
申请日：2012-11-21
申请人： Alibaba Group Holding Limited
发明人： Huaxing Jin
IPC分类号： G06F17/30
CPC分类号： G06F17/30244 , G06F17/30247 , G06F17/30268
摘要： The present disclosure introduces a method and an apparatus for searching images. With respect to each image in an image searching database, respective labels of respective images are generated based on description information corresponding to the respective images. A corresponding relationship between the generated respective labels and the respective images is stored. Based on a received image searching request, description information corresponding to an image for search in the image searching request is obtained. Based on the description information of the image for search, the label of the image for search is generated. Based on the stored corresponding relationship between the respective labels and the respective images, one or more images corresponding to the label of the image for search are determined. The determined one or more images are sent to the client terminal that sends the image searching request.
摘要翻译：本公开引入了用于搜索图像的方法和装置。对于图像搜索数据库中的每个图像，基于与各个图像相对应的描述信息来生成各个图像的各个标签。存储所生成的各个标签和各个图像之间的对应关系。基于接收到的图像搜索请求，获得与图像搜索请求中搜索的图像相对应的描述信息。基于用于搜索的图像的描述信息，生成用于搜索的图像的标签。基于相应标签和相应图像之间存储的对应关系，确定与用于搜索的图像的标签相对应的一个或多个图像。确定的一个或多个图像被发送到发送图像搜索请求的客户终端。

107. 发明申请

US20160275153A1 METHOD AND SYSTEM OF VIRTUAL WORKSPACE LINKING DATA WITH LOCATION 审中-公开
标题翻译：虚拟工作空间连接数据与位置的方法与系统
公开(公告)号：US20160275153A1
公开(公告)日：2016-09-22
申请号：US15035225
申请日：2014-11-07
申请人： WEI WU
发明人： WEI WU
IPC分类号： G06F17/30 , G06T1/00 , G06F3/0484
CPC分类号： G06F17/30554 , G06F3/04842 , G06F3/04845 , G06F17/30241 , G06F17/30268 , G06T1/00
摘要： The invention discloses a virtual workspace method which allows bidirectional query between data and data locations. The method comprises: establish an image of data source object (DSO), and use the image as a virtual workspace; find virtual location of the data on the virtual workspace corresponding physical location of the data on DSO; annotate data identification information at the virtual location; according to the identification information, one can trace the data by the location, or trace the location by the data. The invention also discloses a system for realizing the method mentioned above, the system comprises: display unit, control unit and data processing unit; the display unit connects the control unit and the data processing unit, the display unit displays the data or the image of DSO, the control unit manipulates the display unit to display the data or the image; the data processing unit treats the data, Applying the method and the system, a link between the data and the location can be established anytime, no matter the data belong to data flow or multimedia information and no matter what location on the data source object the data come from, so that the data may be easily traced from the data location or the data location may be easily traced from the data.
摘要翻译：本发明公开了一种允许在数据和数据位置之间进行双向查询的虚拟工作空间方法。该方法包括：建立数据源对象（DSO）的图像，并使用该图像作为虚拟工作区; 在虚拟工作区上查找数据的虚拟位置对应于DSO上数据的物理位置; 在虚拟位置注释数据识别信息; 根据识别信息，可以通过位置跟踪数据，或者通过数据跟踪位置。本发明还公开了一种用于实现上述方法的系统，该系统包括：显示单元，控制单元和数据处理单元; 显示单元连接控制单元和数据处理单元，显示单元显示DSO的数据或图像，控制单元操纵显示单元显示数据或图像; 数据处理单元处理数据，应用方法和系统，数据和位置之间的链接可以随时建立，无论数据属于数据流还是多媒体信息，无论数据源对象上的哪个位置数据来自，从而可以从数据位置容易地跟踪数据，或者可以容易地从数据中追踪数据位置。

108. 发明申请

US20160275115A1 Object Information Derived From Object Images 有权
标题翻译：对象信息源自对象图像
公开(公告)号：US20160275115A1
公开(公告)日：2016-09-22
申请号：US15169948
申请日：2016-06-01
申请人： Nant Holdings IP, LLC
发明人： Wayne C. Boncyk , Ronald H. Cohen
IPC分类号： G06F17/30 , H04N5/44 , G06K9/46
CPC分类号： G06F17/30256 , G06F3/017 , G06F17/30244 , G06F17/30247 , G06F17/30259 , G06F17/30268 , G06F17/30277 , G06F17/30312 , G06F17/30486 , G06F17/30831 , G06F17/30864 , G06F17/3087 , G06F17/30994 , G06K9/00221 , G06K9/00523 , G06K9/00577 , G06K9/00597 , G06K9/00624 , G06K9/00664 , G06K9/00671 , G06K9/00744 , G06K9/209 , G06K9/22 , G06K9/3241 , G06K9/46 , G06K9/6288 , G06K9/72 , G06K9/78 , G06K2209/21 , G06Q20/10 , G06Q30/0261 , G06Q30/0267 , G06Q30/0269 , G06Q30/0601 , G06Q30/0613 , G06Q30/0623 , G06Q30/0625 , G06Q30/0635 , G06T7/00 , H04N5/23229 , H04N5/23293 , H04N5/44
摘要： Search terms are derived automatically from images captured by a camera equipped cell phone, PDA, or other image capturing device submitted to a search engine to obtain information of interest, and at least a portion of the resulting information is transmitted back locally to, or nearby, the device that captured the image.
摘要翻译：搜索词是自动从由配备有相机的手机，PDA或其他图像捕获设备捕获的图像导出到搜索引擎以获得感兴趣的信息，并且所得到的信息的至少一部分被本地传送回或附近，捕获图像的设备。

109. 发明授权

US09449521B2 Method for using virtual facial and bodily expressions 有权
标题翻译：使用虚拟面部和身体表情的方法
公开(公告)号：US09449521B2
公开(公告)日：2016-09-20
申请号：US14741120
申请日：2015-06-16
申请人： Erik Dahlkvist , Martin Gumpert , Lennart Hogman
发明人： Erik Dahlkvist , Martin Gumpert , Lennart Hogman
IPC分类号： G06F7/00 , G06F17/30 , G09B5/02 , G06F3/033 , G06K9/00
CPC分类号： G09B5/02 , G06F3/033 , G06F17/30259 , G06F17/30268 , G06F17/30277 , G06F17/30613 , G06F17/30634 , G06F17/30696 , G06F17/30716 , G06F17/30864 , G06K9/00302 , G06K9/00892
摘要： The method is for using a virtual face or body. The virtual face or body is provided on a screen associated with a computer system having a cursor. A user manipulates the virtual face or body with the cursor to show a facial expression. The communication device determines coordinates of the facial expression and frequency ranges of vocal cords or glottis. The communication device searches for facial expression coordinates in a database to match the coordinates and frequency ranges. A word or phrase is identified that is associated with the identified facial expression coordinates. The screen displays the word to the user. The user may also feed a word to the computer system that displays the facial expression associated with the word.
摘要翻译：该方法是使用虚拟脸或身体。在与具有光标的计算机系统相关联的屏幕上提供虚拟面部或身体。用户用光标操纵虚拟脸或身体以显示面部表情。通信装置确定面部表情的坐标和声带或声门的频率范围。通信设备在数据库中搜索面部表情坐标以匹配坐标和频率范围。识别与识别的面部表情坐标相关联的单词或短语。屏幕会显示用户的单词。用户还可以向显示与单词相关联的面部表情的计算机系统馈送单词。

110. 发明申请

US20160267321A1 Method and Apparatus for Automated Analysis and Identification of a Person in Image and Video Content 有权
公开(公告)号：US20160267321A1
公开(公告)日：2016-09-15
申请号：US15164395
申请日：2016-05-25
申请人： AT&T Intellectual Property I, L.P.
发明人： Zhu Liu , Andrea Basso , Lee Begeja , David Crawford Gibbon , Bernard S. Renger , Behzad Shahraray , Eric Zavesky
IPC分类号： G06K9/00 , G06F17/30
CPC分类号： G06K9/00288 , G06F17/30247 , G06F17/30259 , G06F17/30268 , G06F17/30793 , G06K9/00536 , G06K9/00677 , G06K2009/00328
摘要： A method, apparatus, and computer readable medium for identifying a person in an image includes an image analyzer. The image analyzer determines the content of an image such as a person, location, and object shown in the image. A person in the image may be identified based on the content and event data stored in a database. Event data includes information concerning events and related people, locations, and objects determined from other images and information. Identification metadata is generated and linked to each analyzed image and comprises information determined during image analysis. Tags for images are generated based on identification metadata. The event database can be queried to identify particular people, locations, objects, and events depending on a user's request.

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