知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

53 records (took 0.018 seconds)

    ANALYZING WRITING USING PRESSURE SENSING TOUCHSCREENS
    1.
    发明申请
    ANALYZING WRITING USING PRESSURE SENSING TOUCHSCREENS 审中-公开

    公开(公告)号：US20190213387A1

    公开(公告)日：2019-07-11

    申请号：US16354497

    申请日：2019-03-15

    Applicant: International Business Machines Corporation

    Inventor： Nicholas G. Danyluk ,  Eli M. Dow ,  Kavita Sehgal ,  Diane M. Stamboni ,  Sneha M. Varghese ,  John S. Werner ,  Sarah Wu

    IPC: G06K9/00

    CPC classification number: G06K9/00181 ,  G06F3/0414 ,  G06K9/00174 ,  G06K9/00187

    Abstract: The present invention provides a computer implemented method, a system, and a computer program product for verifying a writing of a user. In an exemplary embodiment, the present invention includes in response to receiving a writing on a pressure sensing touchpad logically coupled a computer system, recording a position and a pressure of one or more points of the writing via a pressure sensing touchscreen, executing a set of logical operations normalizing the writing, comparing the normalized writing to one or more stored writing parameters, executing a set of logical operations determining the normalized writing is within a tolerance of writing parameter deviation limits, thereby verifying the writing, and in response to determining the writing is within the tolerance of writing parameter deviation limits, storing, by the computer system, a value indicating that the writing is valid.

    METHODS AND SYSTEMS FOR SIGNATURE ANALYSIS AND AUTHENTICATION
    4.
    发明申请
    METHODS AND SYSTEMS FOR SIGNATURE ANALYSIS AND AUTHENTICATION 审中-公开
    用于签名分析和认证的方法和系统

    公开(公告)号：US20170046560A1

    公开(公告)日：2017-02-16

    申请号：US15306297

    申请日：2015-04-19

    Applicant: SIGNPASS LTD.

    Inventor： Doron Tsur

    IPC: G06K9/00 ,  G06Q20/40 ,  G06F21/32

    CPC classification number: G06K9/00181 ,  G06F21/32 ,  G06K9/00154 ,  G06K9/627 ,  G06Q20/02 ,  G06Q20/40145

    Abstract: A method for training a classifier for authenticating signatures hand-drawn on an electronic input element includes receiving a set of multiple signature properties of each of multiple signatures documented over a time range of a common user, each set of multiple signature properties is associated with a time period during which a respective signature was documented at the time range, wherein the plurality of signatures were hand-drawn and digitally recorded using an electronic input element; generating a signature authenticating classifier for authenticating additional signatures of the common user based on the set of multiple signature properties of each of the plurality of signatures, wherein a weight assigned to each the set of multiple signature properties or a portion thereof decreases overtime, the weight is used for the generation of the classifier; and providing the signature authenticating classifier for authenticating the additional signatures.

    Abstract translation: 用于训练用于认证在电子输入元件上绘制的签名的分类器的方法包括接收在公共用户的时间范围内记录的多个签名中的每个签名的一组多个签名属性，每组多个签名属性与 在该时间段期间记录相应签名的时间段，其中使用电子输入元素手绘和数字记录多个签名; 生成签名认证分类器，用于基于所述多个签名中的每一个的多个签名属性的集合来认证所述公共用户的附加签名，其中，分配给每个所述多个签名属性或其一部分的权重减少超时，所述权重 用于生成分类器; 并提供用于认证附加签名的签名认证分类器。

    Reading Performance System
    5.
    发明申请
    Reading Performance System 有权
    阅读表演系统

    公开(公告)号：US20130227421A1

    公开(公告)日：2013-08-29

    申请号：US13405566

    申请日：2012-02-27

    Applicant: John Burgess

    Inventor： John Burgess

    IPC: G06F3/048

    CPC classification number: G09B17/003 ,  A63F3/0421 ,  A63F3/0423 ,  A63F9/0098 ,  A63F2011/0076 ,  A63F2011/0083 ,  A63F2011/0093 ,  A63F2300/208 ,  G06F3/048 ,  G06F3/0484 ,  G06F3/04847 ,  G06K9/00 ,  G06K9/00026 ,  G06K9/00033 ,  G06K9/00181 ,  G09B3/00 ,  G09B5/00 ,  G09B5/04 ,  G09B7/00 ,  G09B17/00 ,  G09B17/04

    Abstract: A system for enhancing reading performance operates on a network-connected server with software executing from a non transitory medium at the server providing an interactive interface for a user connected to the server via a browser link. There is a data repository coupled to the server. The interactive interface provides a word search exercise for the user for improving the user's reading performance, displays a passage comprising a first number of words and a search list with a second number of words that each appear at least once in the passage, the second number smaller than the first number, and when the user clicks on every word in the passage for a word that appears in the search list, that word is indicated in the list as found, until all the words in the search list have been indicated as found.

    Abstract translation: 用于增强阅读性能的系统在网络连接的服务器上运行，该服务器具有在服务器上从非暂时介质执行的软件，为通过浏览器链接连接到服务器的用户提供交互界面。 有一个数据存储库耦合到服务器。 交互式界面为用户提供词搜索练习，以改善用户的阅读性能，显示包括第一数量的单词的通道和具有在通过中至少出现一次的第二数量的单词的搜索列表，第二数字 小于第一个数字，当用户点击出现在搜索列表中的单词的段落中的每个单词时，该列表中将显示该单词，直到搜索列表中的所有单词已被指示为已找到 。

    Handwriting teaching data selection system
    6.
    发明授权
    Handwriting teaching data selection system 失效
    手写教学数据选择系统

    公开(公告)号：US07760946B2

    公开(公告)日：2010-07-20

    申请号：US11454664

    申请日：2006-06-16

    Applicant: Erik M. Geidl ,  James A. Pittman

    Inventor： Erik M. Geidl ,  James A. Pittman

    IPC: G06K9/00

    CPC classification number: G06K9/00181

    Abstract: Various technologies and techniques are disclosed that generate a teaching data set for use by a handwriting recognizer. Ink input is received from various ink sources, such as implicit field data, scripted untruthed ink, scripted truth ink, and/or ink from at least one other language in the same script as the target language for the recognizer. The ink input is used with various machine learning methods and/or other algorithmic methods to generate a teaching ink data set. Examples of the various machine learning methods include a character and/or word n-gram distribution leveling method, an allograph method, a subject diversity method, and a print and cursive data selection method. The teaching ink data is used by a handwriting trainer to produce the handwriting recognizer for the target language.

    Abstract translation: 公开了生成手写识别器使用的教学数据集的各种技术和技术。 墨水输入从与识别器的目标语言相同的脚本中从各种墨水源接收，例如隐含的场数据，脚本化的未绘制的墨水，脚本的真墨，和/或来自至少一种其他语言的墨水。 墨水输入与各种机器学习方法和/或其他算法方法一起使用以产生教学墨水数据集。 各种机器学习方法的示例包括字符和/或字n-gram分布调平方法，同画法，主题分集方法以及打印和草书数据选择方法。 手写教练使用教学墨水数据来产生用于目标语言的手写识别器。

    Method for training a neural network for classifying an unknown signal with respect to known signals
    7.
    发明授权
    Method for training a neural network for classifying an unknown signal with respect to known signals 失效
    用于训练用于对已知信号进行未知信号分类的神经网络的方法

    公开(公告)号：US5455892A

    公开(公告)日：1995-10-03

    申请号：US904734

    申请日：1992-06-25

    Applicant: Joel Minot ,  Philippe Gentric

    Inventor： Joel Minot ,  Philippe Gentric

    IPC: G06F15/18 ,  G06G7/60 ,  G06N3/00 ,  G06N3/04 ,  G06N99/00

    CPC classification number: G06K9/6272 ,  G06K9/00154 ,  G06K9/00181 ,  G06K9/6273 ,  G06K9/6287 ,  G06N3/04

    Abstract: The device includes a neural network with an input layer 3, an internal layer 4, and an output layer 5. This network is designed to classify data vectors to classes, the synaptic weights in the network being determined through programming on the basis of specimens whose classes are known. Each class is defined during programming as corresponding to a set of neurons of which each represents a domain which contains a fixed number of specimens. The network includes a number of neurons and synaptic weights which have been determined as a function of the classes thus defined.

    Abstract translation: 该设备包括具有输入层3，内层4和输出层5的神经网络。该网络被设计为将数据向量分类到类，网络中的突触权重通过基于标本的标本 课程是已知的。 每个类在编程期间被定义为对应于一组神经元，其中每个神经元各自表示包含固定数量的样本的域。 网络包括已经根据如此定义的类别的函数确定的许多神经元和突触权重。

    DYNAMIC HANDWRITING VERIFICATION AND HANDWRITING-BASED USER AUTHENTICATION
    10.
    发明申请
    DYNAMIC HANDWRITING VERIFICATION AND HANDWRITING-BASED USER AUTHENTICATION 审中-公开

    公开(公告)号：US20160070951A1

    公开(公告)日：2016-03-10

    申请号：US14940925

    申请日：2015-11-13

    Applicant: Wacom Co., Ltd.

    Inventor： Nicholas Mettyear ,  Yoshitaka Nakayama ,  Jin Kon Ryu

    IPC: G06K9/00

    CPC classification number: G06K9/00154 ,  G06K9/00161 ,  G06K9/00181 ,  G06K9/00865 ,  G06K9/222 ,  G06K9/6206

    Abstract: Handwriting verification methods and related computer systems, and handwriting-based user authentication methods and related computer systems are disclosed. A handwriting verification method comprises obtaining a handwriting test sample containing a plurality of available parameters, extracting geometric parameters, deriving geometric features comprising an x-position value and a y-position value for each of a plurality of feature points in the test sample, performing feature matching between geometric features of the test sample and a reference sample, determining a handwriting verification result based at least in part on the feature matching, and outputting the handwriting verification result. The geometric features may further comprise values derived from the geometric parameters, such as direction and curvature values. The handwriting verification result can be further based on a count of unlinked feature points. Handwriting-based user authentication methods can employ such handwriting verification methods, or other handwriting verification methods.

Patent Agency Ranking