公开(公告)号：US09262682B2

公开(公告)日：2016-02-16

申请号：US14645410

申请日：2015-03-11

Applicant: GOOGLE INC.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Xiaohang Wang ,  Jose Jeronimo Moreira Rodrigues

IPC: G06K9/00 ,  G06K9/18 ,  G06K9/62 ,  G06K9/66 ,  G06T3/00 ,  G06Q20/22 ,  G06Q20/34 ,  G07F7/08 ,  G06K9/32

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.

公开(公告)号：US09213907B2

公开(公告)日：2015-12-15

申请号：US14059071

申请日：2013-10-21

Applicant: GOOGLE INC.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Xiaohang Wang ,  Jose Jeronimo Moreira Rodrigues

IPC: G06K9/62 ,  G06K9/18 ,  G06K9/66 ,  G06T3/00 ,  G06K9/00 ,  G06Q20/22 ,  G06Q20/34 ,  G07F7/08 ,  G06K9/32

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：US20150186797A1

公开(公告)日：2015-07-02

申请号：US14145519

申请日：2013-12-31

Applicant: GOOGLE INC.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Francisco Jose Claude Faust

IPC: G06N99/00

CPC classification number: G06N99/005

Abstract: A set S is initialized. Initially, S is empty; but, as the disclosed process is performed, items are added to it. It may contain one or more samples (e.g., items) from each class. One or more labeled samples for one or more classes may be obtained. A series of operations may be performed, iteratively, until a stopping criterion is reach to obtain the reduced set. For each class of the one or more classes, a point may be generated based on at least one sample in the class having a nearest neighbor in a set S with a different class label than the sample. The point may be added to the set S. The process may be repeated unless a stopping criterion is reached. A nearest neighbor for a submitted point in the set S may be identified and a candidate nearest neighbor may be output for the submitted point.

Abstract translation: 一组S被初始化。 最初，S是空的 但是，随着所公开的处理被执行，项目被添加到它。 它可以包含来自每个类的一个或多个样本（例如，项目）。 可以获得用于一个或多个类别的一个或多个标记的样品。 可以迭代地执行一系列操作，直到达到停止标准以获得缩减的集合。 对于一个或多个类的每个类，可以基于类中具有与样本不同的类标签的集合S中的最近邻的至少一个样本来生成点。 该点可以被添加到集合S中。除非达到停止标准，否则可以重复该过程。 可以识别集合S中的提交点​​的最近邻，并且可以为所提交的点输出候选最近邻。

公开(公告)号：US09070183B2

公开(公告)日：2015-06-30

申请号：US14059108

申请日：2013-10-21

Applicant: GOOGLE INC.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Xiaohang Wang ,  Jose Jeronimo Moreira Rodrigues

IPC: G06K9/62 ,  G06T3/00 ,  G06K9/18 ,  G06K9/66 ,  G06K9/00 ,  G06Q20/22 ,  G06Q20/34 ,  G07F7/08 ,  G06K9/32

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：US08995741B2

公开(公告)日：2015-03-31

申请号：US14461001

申请日：2014-08-15

Applicant: Google Inc.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Xiaohang Wang ,  Jose Jeronimo Moreira Rodrigues

IPC: G06K9/00 ,  G06K9/18

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：US20150006360A1

公开(公告)日：2015-01-01

申请号：US14026738

申请日：2013-09-13

Applicant: GOOGLE INC.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Xiaohang Wang ,  Yakov Okshtein ,  Farhan Shamsi ,  Alessandro Bissacco

IPC: G06Q20/32

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：US20150003733A1

公开(公告)日：2015-01-01

申请号：US14462711

申请日：2014-08-19

Applicant: GOOGLE INC.

Inventor： Xiaohang Wang ,  Farhan Shamsi ,  Yakov Okshtein ,  Sanjiv Kumar ,  Henry Allan Rowley ,  Marcus Quintana Mitchell ,  Debra Lin Repenning ,  Alessandro Bissacco ,  Justin Scheiner ,  Leon Palm

IPC: G06K9/32

CPC classification number: G06K9/3283 ,  G06K9/00469 ,  G06K9/18 ,  G06K9/228 ,  G06K9/325 ,  G06K9/40 ,  G06K2009/363 ,  G06K2209/01

Abstract: Extracting financial card information with relaxed alignment comprises a method to receive an image of a card, determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones. 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. The method then identifies a quadrilateral that matches the expected aspect ratio and performs an optical character recognition algorithm on the rectified model. 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: 以轻松对准的方式提取金融卡信息包括接收卡的图像的方法，在图像的位置确定一个或多个边缘查找器区域，并识别一个或多个边缘查找器区域中的线。 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，并将确定的四边形的纵横比与预期的纵横比进行比较。 然后，该方法识别与预期宽高比匹配的四边形，并在整流模型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：US20150003732A1

公开(公告)日：2015-01-01

申请号：US14059108

申请日：2013-10-21

Applicant: GOOGLE INC.

Inventor： Sanjiv Kumar ,  Henry Allan Rowley ,  Xiaohang Wang ,  Jose Jeronimo Moreira Rodrigues

IPC: G06K9/18

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：US11196800B2

公开(公告)日：2021-12-07

申请号：US15708793

申请日：2017-09-19

Applicant: Google Inc.

Inventor： Ananda Theertha Suresh ,  Sanjiv Kumar ,  Hugh Brendan McMahan ,  Xinnan Yu

IPC: H04L29/08 ,  G06N7/00 ,  G06F17/16 ,  H03M7/30 ,  H03M7/40 ,  G06F17/12 ,  G06N20/00 ,  G06F17/18 ,  H04L29/06

Abstract: The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).

公开(公告)号：US20190294967A1

公开(公告)日：2019-09-26

申请号：US15014804

申请日：2016-02-03

Applicant: Google Inc.

Inventor： Sanjiv Kumar ,  Xinnan Yu

IPC: G06N3/08 ,  G06N99/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network that includes a circulant neural network layer. One of the methods includes receiving a layer input for the circulant layer; and processing the layer input to generate a layer output for the circulant layer, wherein processing the layer input comprises computing an activation function, wherein the activation function is dependent on the product of the circulant matrix associated with the circulant layer and the layer input, and wherein computing the activation function comprises performing a circular convolution using a Fast Fourier Transform (FFT).