公开(公告)号：WO2015120019A1

公开(公告)日：2015-08-13

申请号：PCT/US2015/014414

申请日：2015-02-04

Applicant: GOOGLE INC.

Inventor： KO, Teresa ,  ADAM, Hartwig ,  KOSER, Mikkel Crone ,  MASTEROV, Alexei ,  KIMBEMBE, Andrews-Junior ,  BRIDGES, Matthew J. ,  CHANG, Paul ,  PETROU, David ,  BERENZWEIG, Adam

IPC: G06K9/60

CPC classification number: H04N5/23293 ,  G06F3/04817 ,  G06F3/04842 ,  G06F3/1431 ,  G06F3/1438 ,  G06K9/00671 ,  G06K9/00677 ,  G06K9/78 ,  G09G5/363 ,  G09G2360/08 ,  H04N5/23216

Abstract: Implementations of the present disclosure include actions of receiving image data, the image data being provided from a camera and corresponding to a scene viewed by the camera, receiving one or more annotations, the one or more annotations being provided based on one or more entities determined from the scene, each annotation being associated with at least one entity, determining one or more actions based on the one or more annotations, and providing instructions to display an action interface including one or more action elements, each action element being selectable to induce execution of a respective action, the action interface being displayed in a viewfinder.

Abstract translation: 本公开的实现包括接收图像数据的动作，图像数据从相机提供并对应于由相机观看的场景，接收一个或多个注释，基于确定的一个或多个实体提供的一个或多个注释 从场景中，每个注释与至少一个实体相关联，基于一个或多个注释来确定一个或多个动作，以及提供指示以显示包括一个或多个动作元素的动作界面，每个动作元素可选择以诱导执行 操作界面被显示在取景器中。

公开(公告)号：WO2011017653A1

公开(公告)日：2011-02-10

申请号：PCT/US2010/044771

申请日：2010-08-06

Applicant: GOOGLE INC. ,  PETROU, David ,  RABINOVICH, Andrew ,  ADAM, Hartwig

Inventor： PETROU, David ,  RABINOVICH, Andrew ,  ADAM, Hartwig

IPC: G06F17/30 ,  G06K9/00

CPC classification number: G06F17/30268 ,  G06F17/30256 ,  G06F17/30277 ,  G06F17/3053 ,  G06F17/30867 ,  G06K9/00288 ,  G06K9/00677

Abstract: A facial recognition search system identifies one or more likely names (or other personal identifiers) corresponding to the facial image(s) in a query as follows. After receiving the visual query with one or more facial images, the system identifies images that potentially match the respective facial image in accordance with visual similarity criteria. Then one or more persons associated with the potential images are identified. For each identified person, person-specific data comprising metrics of social connectivity to the requester are retrieved from a plurality of applications such as communications applications, social networking applications, calendar applications, and collaborative applications. An ordered list of persons is then generated by ranking the identified persons in accordance with at least metrics of visual similarity between the respective facial image and the potential image matches and with the social connection metrics. Finally, at least one person identifier from the list is sent to the requester.

Abstract translation: 面部识别搜索系统如下所述在查询中识别与面部图像相对应的一个或多个可能的名称（或其他个人标识符）。 在接收到具有一个或多个面部图像的视觉查询之后，系统根据视觉相似性标准识别潜在地匹配相应面部图像的图像。 然后识别与潜在图像相关联的一个或多个人。 对于每个已识别的人，从诸如通信应用，社交网络应用，日历应用和协作应用的多个应用中检索包括对请求者的社交连接性度量的个人特定数据。 然后通过根据相应的面部图像和潜在图像匹配之间的视觉相似性的度量以及与社会连接度量进行评估来对所识别的人进行排名来生成有序的人物列表。 最后，从列表中至少有一个人标识符被发送到请求者。

公开(公告)号：WO2009139844A2

公开(公告)日：2009-11-19

申请号：PCT/US2009/002916

申请日：2009-05-12

Applicant: GOOGLE INC. ,  BRUCHER, Fernando, A. ,  BUDDEMEIER, Ulrich ,  ADAM, Hartwig ,  NEVEN, Hartmut

Inventor： BRUCHER, Fernando, A. ,  BUDDEMEIER, Ulrich ,  ADAM, Hartwig ,  NEVEN, Hartmut

IPC: G06K9/80

CPC classification number: G06F17/30256 ,  G06F3/04842 ,  G06F7/08 ,  G06F17/30241 ,  G06F17/30253 ,  G06F17/30265 ,  G06F17/30268 ,  G06F17/3028 ,  G06K9/0063 ,  G06T7/97

Abstract: In one embodiment the present invention is a method for populating and updating a database of images of landmarks including geo-clustering geo-tagged images according to geographic proximity to generate one or more geo-clusters, and visual-clustering the one or more geo-clusters according to image similarity to generate one or more visual clusters. In another embodiment, the present invention is a system for identifying landmarks from digital images, including the following components: a database of geo-tagged images; a landmark database; a geo-clustering module; and a visual clustering module. In other embodiments the present invention may be a method of enhancing user queries to retrieve images of landmarks, or a method of automatically tagging a new digital image with text labels.

Abstract translation: 在一个实施例中，本发明是一种用于根据地理接近度来填充和更新包括地理聚类地理标记图像的地标图像的数据库的方法，以生成一个或多个地理群集，并且对一个或多个地理位置集群进行视觉聚类， 根据图像相似性来生成一个或多个视觉集群。 在另一个实施例中，本发明是一种用于从数字图像识别地标的系统，包括以下部件：地理标记图像的数据库; 一个地标数据库; 地理群集模块; 和视觉聚类模块。 在其他实施例中，本发明可以是增强用户查询以检索地标图像的方法，或者是用文本标签自动标记新数字图像的方法。

公开(公告)号：WO2013019426A1

公开(公告)日：2013-02-07

申请号：PCT/US2012/047537

申请日：2012-07-20

Applicant: GOOGLE INC. ,  NEVEN, Hartmut ,  PETROU, David ,  SMULLYAN, Jacob ,  ADAM, Hartwig

Inventor： NEVEN, Hartmut ,  PETROU, David ,  SMULLYAN, Jacob ,  ADAM, Hartwig

IPC: G06F17/30 ,  G02B27/02 ,  G10L15/26

CPC classification number: G06F17/30047 ,  G06F17/30244 ,  G06F17/30654 ,  G06F17/30864 ,  G06F2212/171 ,  G06K9/00288 ,  G06K9/00295 ,  G06K9/00677 ,  G10L2015/088

Abstract: A method and apparatus for enabling a searchable history of real- world user experiences is described. The method may include capturing media data by a mobile computing device. The method may also include transmitting the captured media data to a server computer system, the server computer system to perform one or more recognition processes on the captured media data and add the captured media data to a history of real- world experiences of a user of the mobile computing device when the one or more recognition processes find a match. The method may also include transmitting a query of the user to the server computer system to initiate a search of the history or real-world experiences, and receiving results relevant to the query that include data indicative of the media data in the history of real- world experiences.

Abstract translation: 描述了实现真实用户体验的可搜索历史的方法和装置。 该方法可以包括由移动计算设备捕获媒体数据。 该方法还可以包括将所捕获的媒体数据发送到服务器计算机系统，该服务器计算机系统对所捕获的媒体数据执行一个或多个识别过程，并将所捕获的媒体数据添加到用户的现实世界体验的历史 当一个或多个识别过程找到匹配时，移动计算设备。 该方法还可以包括将用户的查询发送到服务器计算机系统以发起对历史或现实世界体验的搜索，以及接收与查询相关的结果，该结果包括表示实时历史中的媒体数据的数据， 世界经验

公开(公告)号：WO2011068574A2

公开(公告)日：2011-06-09

申请号：PCT/US2010/045631

申请日：2010-08-16

Applicant: GOOGLE INC. ,  PETROU, David ,  FLYNN, John ,  ADAM, Hartwig ,  NEVEN, Hartmut

Inventor： PETROU, David ,  FLYNN, John ,  ADAM, Hartwig ,  NEVEN, Hartmut

IPC: G06F17/30

CPC classification number: G06F17/30247 ,  G06F17/30241 ,  G06F17/30389 ,  G06F17/30528 ,  H04W4/02 ,  H04W64/00

Abstract: A visual query is received from a client system, along with location information for the client system, and processed by a server system. The server system sends the visual query and the location information to a visual query search system, and receives from the visual query search system enhanced location information based on the visual query and the location information. The server system then sends a search query, including the enhanced location information, to a location-based search system. The search system receives and provides to the client one or more search results to the client system.

Abstract translation: 从客户端系统接收到视觉查询以及客户端系统的位置信息，并由服务器系统进行处理。 服务器系统将视觉查询和位置信息发送到视觉查询搜索系统，并且基于视觉查询和位置信息从视觉查询搜索系统接收增强的位置信息。 然后，服务器系统将包括增强位置信息的搜索查询发送到基于位置的搜索系统。 搜索系统接收并向客户端提供一个或多个搜索结果给客户端系统。

公开(公告)号：WO2011062911A1

公开(公告)日：2011-05-26

申请号：PCT/US2010/056869

申请日：2010-11-16

Applicant: GOOGLE INC. ,  ROSS, David ,  RABINOVICH, Andrew ,  PILLAI, Anand ,  ADAM, Hartwig

Inventor： ROSS, David ,  RABINOVICH, Andrew ,  PILLAI, Anand ,  ADAM, Hartwig

IPC: G06K9/62 ,  G06K9/00

CPC classification number: G06K9/622 ,  G06K9/00295

Abstract: Methods and systems for automated identification of celebrity face images are provided that generate a name list of prominent celebrities, obtain a set of images and corresponding feature vectors for each name, detect faces within the set of images, and remove non-face images. An analysis of the images is performed using an intra-model analysis, an inter-model analysis, and a spectral analysis to return highly accurate biometric models for each of the individuals present in the name list. Recognition is then performed based on precision and recall to identify the face images as belonging to a celebrity or indicate that the face is unknown.

Abstract translation: 提供用于自动识别名人脸图像的方法和系统，其产生着名名人的名单，获得一组图像和每个名称的相应特征向量，检测该图像集内的面部，并且去除非面部图像。 使用模型内分析，模型间分析和光谱分析来执行图像的分析，以返回列表中存在的每个个体的高度精确的生物特征模型。 然后基于精度和召回来执行识别，以将脸部图像识别为属于名人，或指示脸部未知。

公开(公告)号：WO2010132789A1

公开(公告)日：2010-11-18

申请号：PCT/US2010/034930

申请日：2010-05-14

Applicant: GOOGLE INC. ,  ADAM, Hartwig ,  ZHANG, Li

Inventor： ADAM, Hartwig ,  ZHANG, Li

IPC: G06F17/30

CPC classification number: G06K9/6217 ,  G06F17/30244 ,  G06F17/30247 ,  G06F17/30265 ,  G06K9/00624 ,  G06K9/00664 ,  G06K9/46 ,  G06K9/726

Abstract: Methods and systems for automatic detection of landmarks in digital images and annotation of those images are disclosed. A method for detecting and annotating landmarks in digital images includes the steps of automatically assigning a tag descriptive of a landmark to one or more images in a plurality of text-associated digital images to generate a set of landmark- tagged images,learning an appearance model for the landmark from the set of landmark-tagged images, and detecting the landmark in a new digital image using the appearance model. The method can also include a step of annotating the new image with the tag descriptive of the landmark.

Abstract translation: 公开了用于自动检测数字图像中的地标的方法和系统以及那些图像的注释。 一种用于检测和注释数字图像中的地标的方法包括以下步骤：将描述地标的标签自动分配给多个文本相关联的数字图像中的一个或多个图像，以生成一组具有地标标签的图像，学习外观模型 用于从一组具有地标标签的图像中的地标，并使用外观模型检测新数字图像中的地标。 该方法还可以包括用描述地标的标签注释新图像的步骤。

公开(公告)号：WO2015042270A1

公开(公告)日：2015-03-26

申请号：PCT/US2014/056318

申请日：2014-09-18

Applicant: GOOGLE INC.

Inventor： GARCIA-BARRIO, Laura ,  PETROU, David ,  ADAM, Hartwig

IPC: G06F17/30

CPC classification number: G06F17/30247 ,  G06F17/30401

Abstract: An image input is obtained from a computing device when an image sensor of the computing device is directed to a scene. At least an object of interest in the scene is determined, and a label is determined for the object of interest. A search input is received from the computing device, where the search input is obtained from a mechanism other than the image sensor. An ambiguity is determined from the search input. A search query is determined that augments or replaces the ambiguity based at least in part on the label. A search result is based on the search query.

Abstract translation: 当计算设备的图像传感器被引导到场景时，从计算设备获得图像输入。 至少确定场景中的感兴趣对象，并且为感兴趣对象确定标签。 从计算设备接收搜索输入，其中搜索输入是从图像传感器以外的机制获得的。 从搜索输入确定歧义。 确定至少部分地基于标签增加或替代歧义的搜索查询。 搜索结果基于搜索查询。

公开(公告)号：WO2015009968A2

公开(公告)日：2015-01-22

申请号：PCT/US2014/047094

申请日：2014-07-17

Applicant: GOOGLE INC.

Inventor： McPHIE, Jonathan ,  ADAM, Hartwig ,  FREDINBURG, Dan ,  MASTEROV, Alexei

CPC classification number: G06K9/00241 ,  G06K9/00288 ,  G06K9/6254 ,  G06K9/6255

Abstract: Implementations generally relate to face template balancing. In some implementations, a method includes generating face templates corresponding to respective images. The method also includes matching the images to a user based on the face templates. The method also includes receiving a determination that one or more matched images are mismatched images. The method also includes flagging one or more face templates corresponding to the one or more mismatched images as negative face templates.

Abstract translation:

实现通常涉及面部模板平衡。 在一些实现中，一种方法包括生成对应于各个图像的面部模板。 该方法还包括基于脸部模板将图像匹配到用户。 该方法还包括接收一个或多个匹配图像是不匹配图像的确定。 该方法还包括将与一个或多个不匹配图像相对应的一个或多个脸部模板标记为否定脸部模板。

公开(公告)号：WO2013009422A2

公开(公告)日：2013-01-17

申请号：PCT/US2012/042095

申请日：2012-06-12

Applicant: GOOGLE INC. ,  LI, Yuan ,  ADAM, Hartwig

Inventor： LI, Yuan ,  ADAM, Hartwig

CPC classification number: G06K9/6256 ,  G06K9/00624 ,  G06K9/00718 ,  G06K9/6201

Abstract: Systems and methods for modeling the occurrence of common image components (e.g., sub-regions) in order to improve visual object recognition are disclosed. In one example, a query image may be matched to a training image of an object. A matched region within the training image to which the query image matches may be determined and a determination may be made whether the matched region is located within an annotated image component of the training image. When the matched region matches only to the image component, an annotation associated with the component may be identified. In another example, sub-regions within a plurality of training image corpora may be annotated as common image components including associated information (e.g., metadata). Matching sub-regions appearing in many training images of objects may be down-weighted in the matching process to reduce possible false matches to query images including common image components.

Abstract translation: 公开了用于对公共图像分量（例如，子区域）的发生进行建模以便改善视觉对象识别的系统和方法。 在一个示例中，查询图像可以与对象的训练图像匹配。 可以确定查询图像匹配的训练图像内的匹配区域，并且可以确定匹配区域是否位于训练图像的注释图像分量内。 当匹配的区域仅与图像组件匹配时，可以识别与组件相关联的注释。 在另一个示例中，多个训练图像语料库内的子区域可被注释为包括关联信息（例如，元数据）的共同图像分量。 在许多对象的训练图像中出现的匹配子区域可能在匹配过程中被降低权重以减少可能的错误匹配以查询包括普通图像分量的图像。