公开(公告)号：US10080114B1

公开(公告)日：2018-09-18

申请号：US15692682

申请日：2017-08-31

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  David Petrou

IPC: H04W4/18 ,  G06K9/00 ,  G06F17/30

CPC classification number: G06F9/451 ,  G06F3/04842 ,  G06F3/04845 ,  G06F16/156 ,  G06F16/2228 ,  G06F16/24578 ,  G06F16/583 ,  G06F16/5854 ,  G06F16/5866 ,  G06F16/957 ,  G06F17/2235 ,  G06F17/241 ,  G06F17/278 ,  G06K9/00469 ,  G06K9/6215 ,  G06Q10/1097 ,  H04L67/06 ,  H04W4/18

Abstract: Systems and methods are provided for detecting and ranking entities identified in screen content displayed on a mobile device. For example, a method includes receiving an image captured from a mobile device display for a mobile application and determining a window that includes a chronological set of images, the images each representing a respective screen captured from a display of a mobile device and having an associated timestamp. The method also includes identifying entities appearing in images in a first portion of the window using text for images in a remaining portion of the window as context to disambiguate ambiguous entity references.

公开(公告)号：US09762651B1

公开(公告)日：2017-09-12

申请号：US14465279

申请日：2014-08-21

Applicant: GOOGLE INC.

Inventor： Matthew Sharifi ,  David Petrou

IPC: G06F17/00 ,  H04L29/08 ,  G06F3/0484

CPC classification number: G06F17/30259 ,  G06F3/04842 ,  G06F3/04845 ,  G06F9/451 ,  G06F17/2235 ,  G06F17/241 ,  G06F17/278 ,  G06F17/30112 ,  G06F17/30247 ,  G06F17/30268 ,  G06F17/30321 ,  G06F17/3053 ,  G06F17/30899 ,  G06K9/00469 ,  G06K9/6215 ,  G06Q10/1097 ,  H04L67/06 ,  H04W4/18

Abstract: Systems and methods are provided for sharing a screen from a mobile device. For example, a method includes capturing an image of a screen displayed on the mobile device in response to a command to share the screen, receiving user instructions for redacting a portion of the image, and transmitting the image with the selected portion redacted to a recipient device selected by the user. As another example, a method includes receiving, from a first mobile device, an identifier for a recipient and an image representing a captured screen of a first mobile device, copying the image to an image repository associated with the recipient, performing recognition on the image, generating annotation data for the image, based on the recognition, that includes at least one visual cue, and providing the image and the annotation data to a second mobile device, the second mobile device being associated with the recipient.

公开(公告)号：US20160055182A1

公开(公告)日：2016-02-25

申请号：US14929958

申请日：2015-11-02

Applicant: Google Inc.

Inventor： David Petrou ,  Andrew Rabinovich ,  Hartwig Adam

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识别与查询中的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序来生成人的有序列表。 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：US20150193528A1

公开(公告)日：2015-07-09

申请号：US14596081

申请日：2015-01-13

Applicant: Google Inc.

Inventor： Samy Bengio ,  David Petrou

IPC: G06F17/30

CPC classification number: G06F17/30696 ,  G06F17/30268 ,  G06F17/30277 ,  G06F17/30663

Abstract: A method, system, and computer readable storage medium is provided for identifying textual terms in response to a visual query is provided. A server system receives a visual query from a client system. The visual query is responded to as follows. A set of image feature values for the visual query is generated. The set of image feature values is mapped to a plurality of textual terms, including a weight for each of the textual terms in the plurality of textual terms. The textual terms are ranked in accordance with the weights of the textual terms. Then, in accordance with the ranking the textual terms, one or more of the ranked textual terms are sent to the client system.

Abstract translation: 提供了一种方法，系统和计算机可读存储介质，用于识别响应于视觉查询提供的文本术语。 服务器系统从客户端系统接收可视化查询。 视觉查询响应如下。 生成视觉查询的一组图像特征值。 图像特征值的集合被映射到多个文本术语，包括多个文本术语中的每个文本术语的权重。 文本术语根据文本术语的权重进行排序。 然后，根据文本术语的排名，将一个或多个排名的文本术语发送到客户端系统。

公开(公告)号：US20140334746A1

公开(公告)日：2014-11-13

申请号：US14445420

申请日：2014-07-29

Applicant: Google Inc.

Inventor： David Petrou ,  Ashok C. Popat ,  Matthew R. Casey

IPC: G06K9/00 ,  G06F17/30

CPC classification number: G06K9/00456 ,  G06F17/30011 ,  G06F17/30253 ,  G06F17/30864 ,  G06K9/036 ,  G06K9/72 ,  G06K2209/01

Abstract: A server system receives a visual query from a client system, performs optical character recognition (OCR) on the visual query to produce text recognition data representing textual characters, including a plurality of textual characters in a contiguous region of the visual query. The server system also produces structural information associated with the textual characters in the visual query. Textual characters in the plurality of textual characters are scored. The method further includes identifying, in accordance with the scoring, one or more high quality textual strings, each comprising a plurality of high quality textual characters from among the plurality of textual characters in the contiguous region of the visual query. A canonical document that includes the one or more high quality textual strings and that is consistent with the structural information is retrieved. At least a portion of the canonical document is sent to the client system.

Abstract translation: 服务器系统从客户端系统接收视觉查询，在视觉查询上执行光学字符识别（OCR），以产生表示文本字符的文本识别数据，包括视觉查询的连续区域中的多个文本字符。 服务器系统还产生与视觉查询中的文本字符相关联的结构信息。 对多个文字进行文字处理。 该方法还包括根据评分识别一个或多个高质量的文本字符串，每个文本字符串包括来自视觉查询的连续区域中的多个文本字符中的多个高质量文本字符。 检索包含一个或多个高质量文本字符串并与结构信息一致的规范文档。 规范文件的至少一部分被发送到客户端系统。