中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

14 records (took 0.026 seconds)

    Verifying labels for images using image recognition
    1.
    发明授权
    Verifying labels for images using image recognition 有权
    使用图像识别验证图像的标签

    公开(公告)号：US09495614B1

    公开(公告)日：2016-11-15

    申请号：US14633704

    申请日：2015-02-27

    Applicant: Google, Inc.

    Inventor： Robert C. Boman ,  John Flynn ,  Farhana Bandukwala

    IPC: G06K9/68 ,  G06K9/62 ,  G06F17/30

    CPC classification number: G06K9/6215 ,  G06F17/30241 ,  G06K9/00671 ,  G06K9/325 ,  G06K9/6267 ,  G06K9/68 ,  G06K2209/27

    Abstract: Implementations relate to verifying labels for images using image recognition. In some implementations, a method includes obtaining an image associated with location information, obtaining one or more descriptor labels associated with the location information, determining one or more recognized image features depicted in the image, comparing the recognized image features with the descriptor labels, and determining one or more verified labels from the one or more descriptor labels. The verified labels are determined to describe at least one of the one or more recognized image features depicted in the image based on the comparing of the recognized image features with the descriptor labels.

    Abstract translation: 实现涉及使用图像识别验证图像的标签。 在一些实现中，一种方法包括获得与位置信息相关联的图像，获得与位置信息相关联的一个或多个描述符标签，确定图像中描绘的一个或多个识别图像特征，将识别的图像特征与描述符标签进行比较，以及 从所述一个或多个描述符标签确定一个或多个经验证的标签。 基于识别的图像特征与描述符标签的比较，确定验证的标签以描述图像中描绘的一个或多个识别的图像特征中的至少一个。

    Scene classification for place recognition
    4.
    发明授权
    Scene classification for place recognition 有权
    场地识别场景分类

    公开(公告)号：US08798378B1

    公开(公告)日：2014-08-05

    申请号：US13962352

    申请日：2013-08-08

    Applicant: Google Inc.

    Inventor： Boris Babenko ,  Hartwig Adam ,  John Flynn ,  Hartmut Neven

    IPC: G06K9/62

    CPC classification number: G06K9/00671 ,  G06K2209/27

    Abstract: Aspects of the disclosure pertain to identifying whether or not an image from a user's device is of a place or not. As part of the identification, a training procedure may be performed on a set of training images. The training procedure includes performing measurements of image data for each image in the set to derive a result. The result includes a series of variables for each training image in the set. The series of variable is evaluated for each training image to obtain one or more measurement weights and one or more measurement thresholds. These weights and thresholds are adjusted to set a false positive threshold and a false negative threshold for identifying whether an actual image is of a place type or is some other type of image.

    Abstract translation: 本公开的方面涉及确定来自用户设备的图像是否是位置。 作为识别的一部分，可以对一组训练图像执行训练程序。 训练过程包括对集合中的每个图像执行图像数据的测量以得到结果。 结果包括一组变量，用于集合中的每个训练图像。 对每个训练图像评估一系列变量以获得一个或多个测量权重和一个或多个测量阈值。 调整这些权重和阈值以设置假阳性阈值和假阴性阈值，用于识别实际图像是地方类型还是其他类型的图像。

    Method and apparatus for enabling virtual tags
    5.
    发明授权
    Method and apparatus for enabling virtual tags 有权
    用于启用虚拟标签的方法和装置

    公开(公告)号：US08661053B2

    公开(公告)日：2014-02-25

    申请号：US13674483

    申请日：2012-11-12

    Applicant: Google Inc.

    Inventor： John Flynn ,  Dragomir Anguelov ,  Hartmut Neven ,  Mark Cummins ,  James Philbin ,  Rafael Spring ,  Hartwig Adam ,  Anand Pillai

    IPC: G06F17/30

    CPC classification number: G06F17/30268 ,  G06F17/30247 ,  G06F17/3028

    Abstract: A method and apparatus for enabling virtual tags is described. The method may include receiving a first digital image data and virtual tag data to be associated with a real-world object in the first digital image data, wherein the first digital image data is captured by a first mobile device, and the virtual tag data includes metadata received from a user of the first mobile device. The method may also include generating a first digital signature from the first digital image data that describes the real-world object, and in response to the generation, inserting in substantially real-time the first digital signature into a searchable index of digital images. The method may also include storing, in a tag database, the virtual tag data and an association between the virtual tag data and the first digital signature inserted into the index of digital images.

    Abstract translation: 描述了一种用于启用虚拟标签的方法和装置。 该方法可以包括在第一数字图像数据中接收与真实世界对象相关联的第一数字图像数据和虚拟标签数据，其中第一数字图像数据由第一移动设备捕获，并且虚拟标签数据包括 从第一移动设备的用户接收的元数据。 该方法还可以包括从描述真实世界对象的第一数字图像数据生成第一数字签名，并且响应于生成，基本上实时地将第一数字签名插入到可搜索的数字图像索引中。 该方法还可以包括在标签数据库中存储虚拟标签数据以及虚拟标签数据与插入数字图像索引中的第一数字签名之间的关联。

    Matching An Approximately Located Query Image Against A Reference Image Set
    6.
    发明申请
    Matching An Approximately Located Query Image Against A Reference Image Set 有权
    将参考图像集合的大致位置查询图像进行匹配

    公开(公告)号：US20140029798A1

    公开(公告)日：2014-01-30

    申请号：US14037681

    申请日：2013-09-26

    Applicant: Google Inc.

    Inventor： John Flynn ,  Ulrich Buddemeier ,  Henrik C. Stewenius ,  Hartmut Neven ,  Fernando Brucher ,  Hartwig Adam

    IPC: G06K9/00

    CPC classification number: G06K9/00671 ,  G06F17/30241 ,  G06F17/30247 ,  G06K9/00704

    Abstract: Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.

    Abstract translation: 本发明的方面涉及将选定的图像/照片与具有位置信息的参考图像的数据库进行匹配。 感兴趣的图像可以包括一些位置信息本身，例如纬度/经度坐标和方向。 然而，用户设备提供的位置信息可能不准确或不完整。 感兴趣的图像被提供给前端服务器，前端服务器选择一个或多个单元以匹配图像。 每个单元可以具有多个图像和索引。 一个或多个单元匹配服务器根据前端服务器提供的信息将图像与特定单元进行比较。 索引存储服务器维护单元的索引数据，并将它们提供给单元匹配服务器。 如果找到匹配，则前端服务器识别接收到的图像的正确位置和方向，并且可以校正用户设备的估计位置中的错误。

    DEEPSTEREO: LEARNING TO PREDICT NEW VIEWS FROM REAL WORLD IMAGERY
    7.
    发明申请
    DEEPSTEREO: LEARNING TO PREDICT NEW VIEWS FROM REAL WORLD IMAGERY 有权
    DEEPSTEREO：学习预测真实世界图像的新视图

    公开(公告)号：US20160335795A1

    公开(公告)日：2016-11-17

    申请号：US15154417

    申请日：2016-05-13

    Applicant: Google Inc.

    Inventor： John Flynn ,  Keith Snavely ,  Ivan Neulander ,  James Philbin

    IPC: G06T15/20

    CPC classification number: G06T15/20 ,  G06K9/00664 ,  G06K9/4628 ,  G06K9/4652 ,  G06K9/6272 ,  G06N99/005 ,  G06T15/205

    Abstract: A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.

    Abstract translation: 使用深层网络深入学习从现有图像预测新视图的系统和方法可能会生成并改进大型数据的模型和表示。 这种深度学习的系统和方法可以采用深入的架构，直接从像素中执行新的视图合成，从大量呈现的图像集训练。 采用这种类型的深度网络的系统可以基于相邻视图的像素产生不可见视图的像素，从而将其自身应用于图形生成中。

    SYSTEMS AND METHODS FOR DYNAMIC VISUAL SEARCH ENGINE
    8.
    发明申请
    SYSTEMS AND METHODS FOR DYNAMIC VISUAL SEARCH ENGINE 有权
    动态视觉搜索引擎的系统与方法

    公开(公告)号：US20150169611A1

    公开(公告)日：2015-06-18

    申请号：US14526612

    申请日：2014-10-29

    Applicant: Google Inc.

    Inventor： James William Philbin ,  Anand Pillai ,  John Flynn ,  Hartwig Adam

    IPC: G06F17/30

    CPC classification number: G06F17/30153 ,  G06F17/30247 ,  G06F17/30256 ,  G06F17/30864

    Abstract: Systems and methods for a dynamic visual search engine are provided. In one example method, a criteria used to partition a set of compressed image descriptors into multiple database shards may be determined. Additionally, a size of a dynamic index may be determined. The dynamic index may represent a dynamic number of images and may be configured to accept insertion of reference images into the dynamic index that can be search against immediately. According to the method, an instruction to merge the uncompressed image descriptors of the dynamic index into the database shards of the compressed image descriptors may be received, and the uncompressed image descriptors of the dynamic index may be responsively merged into the database shards of the compressed image descriptors based on the criteria.

    Abstract translation: 提供了动态视觉搜索引擎的系统和方法。 在一个示例性方法中，可以确定用于将一组压缩图像描述符分割成多个数据库分片的标准。 另外，可以确定动态索引的大小。 动态索引可以表示动态数量的图像，并且可以被配置为接受将参考图像插入到可以立即搜索的动态索引中。 根据该方法，可以接收将动态索引的未压缩图像描述符合并到压缩图像描述符的数据库碎片中的指令，并且动态索引的未压缩图像描述符可以被响应地合并到压缩的图像描述符的数据库碎片中 基于标准的图像描述符。

    Matching an approximately located query image against a reference image set
    10.
    发明授权
    Matching an approximately located query image against a reference image set 有权
    将大致定位的查询图像与参考图像集进行匹配

    公开(公告)号：US08768107B2

    公开(公告)日：2014-07-01

    申请号：US14037681

    申请日：2013-09-26

    Applicant: Google Inc.

    Inventor： John Flynn ,  Ulrich Buddemeier ,  Henrik C. Stewenius ,  Hartmut Neven ,  Fernando Brucher ,  Hartwig Adam

    IPC: G06K9/62

    CPC classification number: G06K9/00671 ,  G06F17/30241 ,  G06F17/30247 ,  G06K9/00704

    Abstract: Aspects of the invention pertain to matching a selected image/photograph against a database of reference images having location information. The image of interest may include some location information itself, such as latitude/longitude coordinates and orientation. However, the location information provided by a user's device may be inaccurate or incomplete. The image of interest is provided to a front end server, which selects one or more cells to match the image against. Each cell may have multiple images and an index. One or more cell match servers compare the image against specific cells based on information provided by the front end server. An index storage server maintains index data for the cells and provides them to the cell match servers. If a match is found, the front end server identifies the correct location and orientation of the received image, and may correct errors in an estimated location of the user device.

    Abstract translation: 本发明的方面涉及将选定的图像/照片与具有位置信息的参考图像的数据库进行匹配。 感兴趣的图像可以包括一些位置信息本身，例如纬度/经度坐标和方向。 然而，用户设备提供的位置信息可能不准确或不完整。 感兴趣的图像被提供给前端服务器，前端服务器选择一个或多个单元以匹配图像。 每个单元可以具有多个图像和索引。 一个或多个单元匹配服务器根据前端服务器提供的信息将图像与特定单元进行比较。 索引存储服务器维护单元的索引数据，并将它们提供给单元匹配服务器。 如果找到匹配，则前端服务器识别接收到的图像的正确位置和方向，并且可以校正用户设备的估计位置中的错误。

Patent Agency Ranking