会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 91. 发明授权
    • Feature design for HMM based Eastern Asian character recognition
    • 基于HMM的东亚字符识别功能设计
    • US07974472B2
    • 2011-07-05
    • US11772032
    • 2007-06-29
    • Yu ZouMing ChangShi HanDongmei ZhangJian Wang
    • Yu ZouMing ChangShi HanDongmei ZhangJian Wang
    • G06K9/00
    • G06K9/00416G06K2209/011
    • An exemplary method for online character recognition of East Asian characters includes acquiring time sequential, online ink data for a handwritten East Asian character, conditioning the ink data to produce conditioned ink data where the conditioned ink data includes information as to writing sequence of the handwritten East Asian character and extracting features from the conditioned ink data where the features include a tangent feature, a curvature feature, a local length feature, a connection point feature and an imaginary stroke feature. Such a method may determine neighborhoods for ink data and extract features for each neighborhood. An exemplary Hidden Markov Model based character recognition system may use various exemplary methods for training and character recognition.
    • 用于东亚字符的在线字符识别的示例性方法包括获取用于手写东亚字符的时间顺序在线墨水数据,调节墨水数据以产生经调节的墨水数据,其中调节的墨水数据包括关于写入东方手写的顺序的信息 亚洲字符和从调节的墨水数据中提取特征,其中特征包括切线特征,曲率特征,局部长度特征,连接点特征和假想笔划特征。 这种方法可以确定墨水数据的邻域并提取每个邻域的特征。 基于示例性的基于隐马尔可夫模型的角色识别系统可以使用用于训练和角色识别的各种示例性方法。
    • 93. 发明申请
    • COMBINING ONLINE AND OFFLINE RECOGNIZERS IN A HANDWRITING RECOGNITION SYSTEM
    • 在手持识别系统中组合在线和离线识别器
    • US20120183223A1
    • 2012-07-19
    • US13426427
    • 2012-03-21
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • G06K9/62
    • G06K9/00973G06K9/6292G06K9/6296
    • Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
    • 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常,该组合提高了整体识别精度。 在一个方面,单独执行在线和离线识别以获得用于候选者(假设)的在线和离线角色级识别分数。 基于统计分析的组合算法,AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如,HMM识别器可以生成用于构建激进图形的在线激进分数,然后使用离线激进识别分数进行重新分类。 然后,搜索折叠图中的路径以提供组合识别结果,例如对应于具有最高分数的路径。
    • 94. 发明申请
    • COMBINING ONLINE AND OFFLINE RECOGNIZERS IN A HANDWRITING RECOGNITION SYSTEM
    • 在手持识别系统中组合在线和离线识别器
    • US20110194771A1
    • 2011-08-11
    • US13090242
    • 2011-04-19
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • G06K9/00
    • G06K9/00973G06K9/6292G06K9/6296
    • Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
    • 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常,该组合提高了整体识别精度。 在一个方面,单独执行在线和离线识别以获得用于候选者(假设)的在线和离线角色级识别分数。 基于统计分析的组合算法,AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如,HMM识别器可以生成用于构建激进图形的在线激进分数,然后使用离线激进识别分数进行重新分类。 然后,搜索折叠图中的路径以提供组合识别结果,例如对应于具有最高分数的路径。
    • 96. 发明申请
    • Combining online and offline recognizers in a handwriting recognition system
    • 将在线和离线识别器结合在手写识别系统中
    • US20090003706A1
    • 2009-01-01
    • US11823644
    • 2007-06-28
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • G06K9/00
    • G06K9/00973G06K9/6292G06K9/6296
    • Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
    • 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常,该组合提高了整体识别精度。 在一个方面,单独执行在线和离线识别以获得用于候选者(假设)的在线和离线角色级识别分数。 基于统计分析的组合算法,AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如,HMM识别器可以生成用于构建激进图形的在线激进分数,然后使用离线激进识别分数进行重新分类。 然后,搜索折叠图中的路径以提供组合识别结果,例如对应于具有最高分数的路径。
    • 97. 发明申请
    • Feature Design for HMM Based Eastern Asian Character Recognition
    • 基于HMM的东亚字符识别功能设计
    • US20090003705A1
    • 2009-01-01
    • US11772032
    • 2007-06-29
    • Yu ZouMing ChangShi HanDongmei ZhangJian Wang
    • Yu ZouMing ChangShi HanDongmei ZhangJian Wang
    • G06K9/18
    • G06K9/00416G06K2209/011
    • An exemplary method for online character recognition of East Asian characters includes acquiring time sequential, online ink data for a handwritten East Asian character, conditioning the ink data to produce conditioned ink data where the conditioned ink data includes information as to writing sequence of the handwritten East Asian character and extracting features from the conditioned ink data where the features include a tangent feature, a curvature feature, a local length feature, a connection point feature and an imaginary stroke feature. Such a method may determine neighborhoods for ink data and extract features for each neighborhood. An exemplary Hidden Markov Model based character recognition system may use various exemplary methods for training and character recognition.
    • 用于东亚字符的在线字符识别的示例性方法包括获取用于手写东亚字符的时间顺序在线墨水数据,调节墨水数据以产生经调节的墨水数据,其中调节的墨水数据包括关于写入东方手写的顺序的信息 亚洲字符和从调节的墨水数据中提取特征,其中特征包括切线特征,曲率特征,局部长度特征,连接点特征和假想笔划特征。 这种方法可以确定墨水数据的邻域并提取每个邻域的特征。 基于示例性的基于隐马尔可夫模型的角色识别系统可以使用用于训练和角色识别的各种示例性方法。
    • 98. 发明申请
    • FEATURE DESIGN FOR CHARACTER RECOGNITION
    • 特征识别功能设计
    • US20120251006A1
    • 2012-10-04
    • US13526236
    • 2012-06-18
    • Yu ZouMing ChangShi HanDongmei ZhangJian Wang
    • Yu ZouMing ChangShi HanDongmei ZhangJian Wang
    • G06K9/46
    • G06K9/00416G06K2209/011
    • An exemplary method for online character recognition of characters includes acquiring time sequential, online ink data for a handwritten character, conditioning the ink data to produce conditioned ink data where the conditioned ink data includes information as to writing sequence of the handwritten character and extracting features from the conditioned ink data where the features include a tangent feature, a curvature feature, a local length feature, a connection point feature and an imaginary stroke feature. Such a method may determine neighborhoods for ink data and extract features for each neighborhood. An exemplary character recognition system may use various exemplary methods for training and character recognition.
    • 用于字符的在线字符识别的示例性方法包括获取用于手写字符的时间顺序在线墨水数据,调节墨水数据以产生经调节的墨水数据,其中经调节的墨水数据包括关于写入手写字符的序列的信息并从 调节的油墨数据,其中特征包括切线特征,曲率特征,局部长度特征,连接点特征和假想笔画特征。 这种方法可以确定墨水数据的邻域并提取每个邻域的特征。 示例性字符识别系统可以使用用于训练和字符识别的各种示例性方法。
    • 99. 发明授权
    • Platform for learning based recognition research
    • 基于学习的平台识别研究
    • US08266078B2
    • 2012-09-11
    • US12366655
    • 2009-02-06
    • Yu ZouHao WeiGong ChengDongmei ZhangJian Wang
    • Yu ZouHao WeiGong ChengDongmei ZhangJian Wang
    • G06F15/18G06K9/62G06K9/46
    • G06K9/6253G10L15/063
    • A method for researching and developing a recognition model in a computing environment, including gathering one or more data samples from one or more users in the computing environment into a training data set used for creating the recognition model, receiving one or more training parameters defining a feature extraction algorithm configured to analyze one or more features of the training data set, a classifier algorithm configured to associate the features to a template set, a selection of a subset of the training data set, a type of the data samples, or combinations thereof, creating the recognition model based on the training parameters, and evaluating the recognition model.
    • 一种用于在计算环境中研究和开发识别模型的方法,包括将来自所述计算环境中的一个或多个用户的一个或多个数据样本收集到用于创建所述识别模型的训练数据集中,接收定义一个或多个训练参数的训练参数 特征提取算法,其被配置为分析训练数据集的一个或多个特征,分类器算法,被配置为将特征与模板集合相关联,训练数据集的子集的选择,数据样本的类型或其组合 ,基于训练参数创建识别模型,并对识别模型进行评估。
    • 100. 发明授权
    • Combining online and offline recognizers in a handwriting recognition system
    • 将在线和离线识别器结合在手写识别系统中
    • US07953279B2
    • 2011-05-31
    • US11823644
    • 2007-06-28
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • Xinjian ChenDongmei ZhangYu ZouMing ChangShi HanJian Wang
    • G06K9/00G06F17/00
    • G06K9/00973G06K9/6292G06K9/6296
    • Described is a technology by which online recognition of handwritten input data is combined with offline recognition and processing to obtain a combined recognition result. In general, the combination improves overall recognition accuracy. In one aspect, online and offline recognition is separately performed to obtain online and offline character-level recognition scores for candidates (hypotheses). A statistical analysis-based combination algorithm, an AdaBoost algorithm, and/or a neural network-based combination may determine a combination function to combine the scores to produce a result set of one or more results. Online and offline radical-level recognition may be performed. For example, a HMM recognizer may generate online radical scores used to build a radical graph, which is then rescored using the offline radical recognition scores. Paths in the rescored graph are then searched to provide the combined recognition result, e.g., corresponding to the path with the highest score.
    • 描述了通过在线识别手写输入数据与离线识别和处理相结合以获得组合识别结果的技术。 通常,该组合提高了整体识别精度。 在一个方面,单独执行在线和离线识别以获得用于候选者(假设)的在线和离线角色级识别分数。 基于统计分析的组合算法,AdaBoost算法和/或基于神经网络的组合可以确定组合函数以组合分数以产生一个或多个结果的结果集。 可以执行在线和离线激进级别识别。 例如,HMM识别器可以生成用于构建激进图形的在线激进分数,然后使用离线激进识别分数进行重新分类。 然后,搜索折叠图中的路径以提供组合识别结果,例如对应于具有最高分数的路径。