公开(公告)号：WO2017052874A1

公开(公告)日：2017-03-30

申请号：PCT/US2016/047965

申请日：2016-08-22

Applicant: GOOGLE INC.

Inventor： YU, Xinnan ,  KUMAR, Sanjiv ,  GUO, Ruiqi

IPC: G06F17/16 ,  G06F17/30

CPC classification number: G06F17/16 ,  G06F17/30259 ,  G06F17/30277 ,  G06K9/6247 ,  G06K9/6271

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for efficiently performing linear projections. In one aspect, a method includes actions for obtaining a plurality of content items from one or more content sources. Additional actions include, extracting a plurality of features from each of the plurality of content items, generating a feature vector for each of the extracted features in order to create a search space, generating a series of element matrices based upon the generated feature vectors, transforming the series of element matrices into a structured matrix such that the transformation preserves one or more relationships associated with each element matrix of the series of element matrices, receiving a search object, searching the enhanced search space based on the received search object, provided one or more links to a content item that are responsive to the search object.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于有效地执行线性投影。 一方面，一种方法包括用于从一个或多个内容源获得多个内容项的动作。 附加动作包括：从多个内容项中的每一个提取多个特征，为每个所提取的特征生成特征向量以便创建搜索空间，基于生成的特征向量生成一系列元素矩阵，转换 将所述一系列元素矩阵转换成结构化矩阵，使得所述变换保留与所述一系列元素矩阵中的每个元素矩阵相关联的一个或多个关系，接收搜索对象，基于所接收的搜索对象搜索所述增强搜索空间，提供一个或 指向响应搜索对象的内容项的更多链接。

公开(公告)号：WO2017031135A1

公开(公告)日：2017-02-23

申请号：PCT/US2016/047226

申请日：2016-08-16

Applicant: GOOGLE INC.

Inventor： ROWLEY, Henry, Allan ,  KUMAR, Sanjiv ,  LIU, Xiaofeng ,  CHANG, Brian, Lin ,  HOLTMANN-RICE, Daniel, Niels

IPC: G06K9/03 ,  G06K9/00 ,  G06K9/72

CPC classification number: G06Q20/10 ,  G06K9/00442 ,  G06K9/03 ,  G06K9/2063 ,  G06K9/723 ,  G06K2209/01 ,  G06Q20/36

Abstract: An application extracts a user name from a financial card image using optical character recognition ("OCR") and compares segments of the user name to names stored in user data to refine the extracted name. The application performs an OCR algorithm on a card image and compares an extracted name with user data. The application identifies likely matching names to the extracted name. The OCR application breaks the extracted name into one or more series of segments and compares the segments from the extracted name to segments from the stored names. The OCR application determines an edit distance between the extracted name and each potentially matching stored name. If the edit distance is below a configured threshold then the OCR application revises the extracted name to match the identified stored name. The refined name is presented to the user for verification.

Abstract translation: 应用程序使用光学字符识别（“OCR”）从金融卡片图像中提取用户名，并将用户名的段与存储在用户数据中的名称进行比较，以优化提取的名称。 应用程序在卡片图像上执行OCR算法，并将提取的名称与用户数据进行比较。 该应用程序可识别提取的名称可能匹配的名称。 OCR应用将提取的名称分解为一个或多个片段，并将来自提取的名称的片段与存储的名称的片段进行比较。 OCR应用程序确定提取的名称和每个潜在匹配的存储名称之间的编辑距离。 如果编辑距离低于配置的阈值，则OCR应用程序将修改提取的名称以匹配所标识的存储名称。 将精简的名称呈现给用户进行验证。

公开(公告)号：WO2009154861A9

公开(公告)日：2009-12-23

申请号：PCT/US2009/040975

申请日：2009-04-17

Applicant: GOOGLE INC. ,  MAKADIA, Ameesh ,  KUMAR, Sanjiv

Inventor： MAKADIA, Ameesh ,  KUMAR, Sanjiv

Abstract: Methods, systems, and apparatus, including computer program products, for generating data for annotating images automatically. In one aspect, a method includes receiving an input image, identifying one or more nearest neighbor images of the input image from among a collection of images, in which each of the one or more nearest neighbor images is associated with a respective one or more image labels, assigning a plurality of image labels to the input image, in which the plurality of image labels are selected from the image labels associated with the one or more nearest neighbor images, and storing in a data repository the input image having the assigned plurality of image labels. In another aspect, a method includes assigning a single image label to the input image, in which the single image label is selected from labels associated with multiple ranked nearest neighbor images.

公开(公告)号：WO2014210577A2

公开(公告)日：2014-12-31

申请号：PCT/US2014/044758

申请日：2014-06-27

Applicant: GOOGLE INC.

Inventor： KUMAR, Sanjiv ,  ROWLEY, Henry, Allan ,  WANG, Xiaohang ,  OKSHTEIN, Yakov ,  SHAMSI, Farhan ,  MITCHELL, Marcus, Quintana ,  BISSACCO, Alessandro

IPC: G06K9/20

CPC classification number: G06K9/6201 ,  G06K9/00201 ,  G06K9/00469 ,  G06K9/00483 ,  G06K9/03 ,  G06K9/036 ,  G06K9/18 ,  G06K9/20 ,  G06K9/2054 ,  G06K9/228 ,  G06K9/344 ,  G06K9/6202 ,  G06K9/78 ,  G06K2009/2045 ,  G06K2209/01 ,  G06K2209/40 ,  G06Q20/322 ,  G06Q20/327 ,  G06Q20/34 ,  G06Q20/4016 ,  G06T17/00

Abstract: Comparing extracted card data from a continuous scan comprises receiving, by one or more computing devices, a digital scan of a card; obtaining a plurality of images of the card from the digital scan of the physical card; performing an optical character recognition algorithm on each of the plurality of images; comparing results of the application of the optical character recognition algorithm for each of the plurality of images; determining if a configured threshold of the results for each of the plurality of images match each other; and verifying the results when the results for each of the plurality of images match each other. Threshold confidence level for the extracted card data can be employed to determine the accuracy of the extraction. Data is further extracted from blended images and three-dimensional models of the card. Embossed text and holograms in the images may be used to prevent fraud.

Abstract translation: 比较来自连续扫描的提取的卡数据包括由一个或多个计算设备接收卡的数字扫描; 从所述物理卡的数字扫描中获取所述卡的多个图像; 对所述多个图像中的每一个执行光学字符识别算法; 比较针对所述多个图像中的每一个的所述光学字符识别算法的应用结果; 确定所述多个图像中的每一个的结果的配置阈值是否彼此匹配; 以及当多个图像中的每一个的结果彼此匹配时验证结果。 可以采用提取的卡数据的阈值置信水平来确定提取的准确性。 从混合图像和卡片的三维模型进一步提取数据。 图像中的压纹文字和全息图可能被用来防止欺诈。

公开(公告)号：WO2014210576A2

公开(公告)日：2014-12-31

申请号：PCT/US2014/044757

申请日：2014-06-27

Applicant: GOOGLE INC.

Inventor： KUMAR, Sanjiv ,  ROWLEY, Henry, Allan ,  WANG, Xiaohang ,  BISSACCO, Alessandro ,  RODRIGUES, Jose, Jeronimo, Moreira ,  PAPINENI, Kishore, Ananda

IPC: G06K9/00

CPC classification number: G06K9/6269 ,  G06K9/00469 ,  G06K9/00536 ,  G06K9/18 ,  G06K9/186 ,  G06K9/3233 ,  G06K9/3258 ,  G06K9/46 ,  G06K9/6202 ,  G06K9/6267 ,  G06K9/66 ,  G06K2009/4666 ,  G06K2209/01 ,  G06Q20/227 ,  G06Q20/34 ,  G06T3/0012 ,  G06T7/11 ,  G06T2207/20132 ,  G07F7/0893

Abstract: Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition ("OCR"). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

Abstract translation: 这里的实施例提供了计算机实现的技术，用于允许用户计算设备使用光学字符识别（“OCR”）提取金融卡信息。 可以通过对图像数据应用各种分类器和其他变换来提高金融卡信息的提取。 例如，在应用OCR算法之前，对图像应用线性分类器以确定数字位置允许用户计算设备使用较少的处理能力来提取准确的卡数据。 OCR应用程序可以训练分类器来使用卡的磨损模式来改善OCR算法性能。 OCR应用可以应用线性分类器，然后应用非线性分类器来提高OCR算法的性能和准确性。 OCR应用程序使用典型的信用卡和借记卡使用的已知数字模式来提高OCR算法的准确性。

公开(公告)号：WO2010087909A1

公开(公告)日：2010-08-05

申请号：PCT/US2009/068108

申请日：2009-12-15

Applicant: GOOGLE INC. ,  CORTES, Corinna ,  KUMAR, Sanjiv ,  MAKADIA, Ameesh ,  MANN, Gideon ,  YAGNIK, Jay ,  ZHAO, Ming

Inventor： CORTES, Corinna ,  KUMAR, Sanjiv ,  MAKADIA, Ameesh ,  MANN, Gideon ,  YAGNIK, Jay ,  ZHAO, Ming

IPC: H04N7/173

CPC classification number: H04N21/2407 ,  G06F17/30784 ,  G06F17/30817 ,  G06F17/3082 ,  G06F17/30828 ,  G06K9/00711 ,  H04N21/23418 ,  H04N21/25883 ,  H04N21/4668 ,  H04N21/4826

Abstract: A video demographics analysis system selects a training set of videos to use to correlate viewer demographics and video content data. The video demographics analysis system extracts demographic data from viewer profiles related to videos in the training set and creates a set of demographic distributions, and also extracts video data from videos in the training set. The video demographics analysis system correlates the viewer demographics with the video data of videos viewed by that viewer. Using the prediction model produced by the machine learning process, a new video about which there is no a priori knowledge can be associated with a predicted demographic distribution specifying probabilities of the video appealing to different types of people within a given demographic category, such as people of different ages within an age demographic category.

Abstract translation: 视频人口统计分析系统选择用于将观众人口特征和视频内容数据相关联的一组视频。 视频人口统计分析系统从与训练集中的视频相关的观众简档中提取人口统计学数据，并创建一组人口分布，并从训练集中的视频中提取视频数据。 视频人口统计分析系统将观众人口统计学与观众观看的视频的视频数据相关联。 使用机器学习过程产生的预测模型，可以将预测的人口分布与预测的人口分布相关联，所述预测人口统计分布规定了给定人口统计学类别中的不同类型的人的视频的概率，例如人 在不同年龄的人口统计学类别。

公开(公告)号：WO2015009974A3

公开(公告)日：2015-01-22

申请号：PCT/US2014/047102

申请日：2014-07-17

Applicant: GOOGLE INC.

Inventor： MITCHELL, Marcus, Quintana ,  HAZLEHURST, Peter ,  WANG, Xiaohang ,  REPENNING, Debra, Lin ,  OKSHTEIN, Yakov ,  KUMAR, Sanjiv ,  SHAMSI, Farhan ,  ROWLEY, Henry, Allan

IPC: G06K9/00

Abstract: Providing improved card art for display comprises receiving, by one or more computing devices, an image of a card and performing an image recognition algorithm on the image. The computing device identifies images represented on the card image and comparing the identified images to an image database. The computing device determines a standard card art image associated with the identified image based at least in part on the comparison and associates the standard card art image with an account of a user, the account being associated with the card in the image. The computing device displays the standard card art as a representation of the account.

公开(公告)号：WO2015002906A1

公开(公告)日：2015-01-08

申请号：PCT/US2014/044968

申请日：2014-06-30

Applicant: GOOGLE INC.

Inventor： WANG, Xiaohang ,  SHAMSI, Farhan ,  OKSHTEIN, Yakov ,  KUMAR, Sanjiv ,  ROWLEY, Henry, Allan ,  MITCHELL, Marcus, Quintana ,  REPENNING, Debra, Lin ,  BISSACCO, Alessandro ,  SCHEINER, Justin ,  PALM, Leon ,  HUBER, Jeff

IPC: G06K9/32 ,  G06Q20/34 ,  G06Q20/32

CPC classification number: G06K9/3233 ,  G06K2009/363 ,  G06Q20/3276 ,  G06Q20/3567

Abstract: Extracting financial card information with relaxed alignment comprises a method to receive an image of a card (205), determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones (210). The method further identifies one or more quadrilaterals formed by intersections of extrapolations of the identified lines, determines an aspect ratio of the one or more quadrilateral, and compares the determined aspect ratios of the quadrilateral to an expected aspect ratio (215). The method then identifies a quadrilateral that matches the expected aspect ratio (220) and performs an optical character recognition algorithm on the rectified model (230). A similar method is performed on multiple cards in an image. The results of the analysis of each of the cards are compared to improve accuracy of the data.

Abstract translation: 以轻松对准提取金融卡信息包括接收卡片图像（205）的方法，确定图像位置中的一个或多个边缘查找器区域，以及识别该一个或多个边缘查找器区域（210）中的线条。 该方法还识别由所识别的线的外插的交点形成的一个或多个四边形，确定一个或多个四边形的纵横比，并将所确定的四边形的纵横比与预期纵横比进行比较（215）。 然后，该方法识别与预期宽高比匹配的四边形（220），并在整流模型（230）上执行光学字符识别算法。 在图像中的多个卡上执行类似的方法。 比较每个卡的分析结果，提高数据的准确性。

公开(公告)号：WO2014210548A2

公开(公告)日：2014-12-31

申请号：PCT/US2014/044719

申请日：2014-06-27

Applicant: GOOGLE INC.

Inventor： WANG, Xiaohang ,  SHAMSI, Farhan ,  OKSHTEIN, Yakov ,  KUMAR, Sanjiv ,  ROWLEY, Henry, Allan ,  MITCHELL, Marcus, Quintana ,  REPENNING, Debra, Lin ,  RODRIGUES, Jose, Jeronimo, Moreira ,  LI, Zhifei

IPC: G06K9/22

CPC classification number: G06K9/186 ,  G06K7/10 ,  G06K9/00469 ,  G06K9/18 ,  G06K9/2054 ,  G06K9/228 ,  G06K9/6202 ,  G06K2209/01 ,  G06Q20/32 ,  G06Q20/3223 ,  G06Q20/3276 ,  G06Q20/34 ,  G06Q20/36 ,  H04N1/00307

Abstract: Extracting card data comprises receiving, by one or more computing devices, a digital image of a card; perform an image recognition process on the digital representation of the card; identifying an image in the digital representation of the card; comparing the identified image to an image database comprising a plurality of images and determining that the identified image matches a stored image in the image database; determining a card type associated with the stored image and associating the card type with the card based on the determination that the identified image matches the stored image; and performing a particular optical character recognition algorithm on the digital representation of the card, the particular optical character recognition algorithm being based on the determined card type. Another example uses an issuer identification number to improve data extraction. Another example compares extracted data with user data to improve accuracy.

Abstract translation: 提取卡数据包括由一个或多个计算设备接收卡的数字图像; 对卡的数字表示进行图像识别处理; 识别卡的数字表示中的图像; 将识别的图像与包括多个图像的图像数据库进行比较，并且确定所识别的图像与图像数据库中存储的图像匹配; 基于所识别的图像与所存储的图像匹配的确定来确定与所存储的图像相关联的卡类型并将卡类型与卡相关联; 以及对所述卡的数字表示执行特定光学字符识别算法，所述特定光学字符识别算法基于所确定的卡类型。 另一个例子是使用发行人识别号来改进数据提取。 另一个例子比较了提取的数据与用户数据，以提高准确性。