-
41.发明申请公开(公告)号：US20110194771A1
公开(公告)日：2011-08-11
申请号：US13090242
申请日：2011-04-19
申请人： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
发明人： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
IPC分类号： G06K9/00
CPC分类号： G06K9/00973 , G06K9/6292 , G06K9/6296
摘要： 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.
摘要翻译： 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。
-
公开(公告)号：US20100205120A1
公开(公告)日：2010-08-12
申请号：US12366655
申请日：2009-02-06
申请人： Yu Zou , Hao Wei , Gong Cheng , Dongmei Zhang , Jian Wang
发明人： Yu Zou , Hao Wei , Gong Cheng , Dongmei Zhang , Jian Wang
CPC分类号： G06K9/6253 , G10L15/063
摘要： 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.
摘要翻译： 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。
-
43.发明申请公开(公告)号：US20090003706A1
公开(公告)日：2009-01-01
申请号：US11823644
申请日：2007-06-28
申请人： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
发明人： Xinjian Chen , Dongmei Zhang , Yu Zou , Ming Chang , Shi Han , Jian Wang
IPC分类号： G06K9/00
CPC分类号： G06K9/00973 , G06K9/6292 , G06K9/6296
摘要： 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.
摘要翻译： 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。
-
公开(公告)号：US20090003705A1
公开(公告)日：2009-01-01
申请号：US11772032
申请日：2007-06-29
申请人： Yu Zou , Ming Chang , Shi Han , Dongmei Zhang , Jian Wang
发明人： Yu Zou , Ming Chang , Shi Han , Dongmei Zhang , Jian Wang
IPC分类号： G06K9/18
CPC分类号： G06K9/00416 , G06K2209/011
摘要： 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.
摘要翻译： 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。
-
45.发明申请公开(公告)号：US20080240570A1
公开(公告)日：2008-10-02
申请号：US11693299
申请日：2007-03-29
申请人： Yu Shi , Frank Kao-Ping Soong , Jian-lai Zhou , Dongmei Zhang
发明人： Yu Shi , Frank Kao-Ping Soong , Jian-lai Zhou , Dongmei Zhang
IPC分类号： G06K9/00
CPC分类号： G06K9/6296 , G06K2209/01
摘要： A forward pass through a sequence of strokes representing a handwritten equation is performed from the first stroke to the last stroke in the sequence. At each stroke, a path score is determined for a plurality of symbol-relation pairs that each represents a symbol and its spatial relation to a predecessor symbol. A symbol graph having nodes and links is constructed by backtracking through the strokes from the last stroke to the first stroke and assigning scores to the links based on the path scores for the symbol-relation pairs. The symbol graph is used to recognize a mathematical expression based in part on the scores for the links and the mathematical expression is stored.
摘要翻译： 从序列中的第一行程到最后一个行程执行表示手写方程的笔画序列的向前传递。 在每个笔划处，确定多个符号 - 关系对的路径分数，每个符号 - 关系对都表示符号及其与前身符号的空间关系。 具有节点和链接的符号图是通过从最后笔划到第一笔划的笔画回溯构成的，并且基于符号 - 关系对的路径得分将分数分配给链接。 符号图用于部分地基于链接的分数来识别数学表达式，并存储数学表达式。
-
公开(公告)号：US20100262643A1
公开(公告)日：2010-10-14
申请号：US12422315
申请日：2009-04-13
申请人： Xu Yang , Zhouchen Lin , Sijun Liu , Tianjun Ye , Dongmei Zhang
发明人： Xu Yang , Zhouchen Lin , Sijun Liu , Tianjun Ye , Dongmei Zhang
摘要： Described is a technology, such as implemented in a computational software program, by which a minimal polynomial is efficiently determined for a radical expression over the ring Z of integer numbers or the ring Q of rational numbers. The levels of the radical are grouped into a level permutation group that is used to find a level permutation set. An annihilation polynomial is found based upon the level permutation set. The annihilation polynomial is factored, and a selection mechanism selects the minimal polynomial based upon the annihilation polynomial's factors.
摘要翻译： 描述了一种技术，例如在计算软件程序中实现的技术，通过该技术，对于整数的环Z或有理数的环Q，对于根基表达式有效地确定最小多项式。 激进的级别被分组成用于找到级别置换集合的级别置换组。 湮没多项式是基于层次排列集合找到的。 湮灭多项式被考虑，选择机制根据湮灭多项式的因素选择最小多项式。
-
公开(公告)号：US09122563B2
公开(公告)日：2015-09-01
申请号：US12422315
申请日：2009-04-13
申请人： Xu Yang , Zhouchen Lin , Sijun Liu , Tianjun Ye , Dongmei Zhang
发明人： Xu Yang , Zhouchen Lin , Sijun Liu , Tianjun Ye , Dongmei Zhang
摘要： Described is a technology, such as implemented in a computational software program, by which a minimal polynomial is efficiently determined for a radical expression over the ring Z of integer numbers or the ring Q of rational numbers. The levels of the radical are grouped into a level permutation group that is used to find a level permutation set. An annihilation polynomial is found based upon the level permutation set. The annihilation polynomial is factored, and a selection mechanism selects the minimal polynomial based upon the annihilation polynomial's factors.
摘要翻译： 描述了一种技术，例如在计算软件程序中实现的技术，通过该技术，对于整数的环Z或有理数的环Q，对于根基表达式有效地确定最小多项式。 激进的级别被分组成用于找到级别置换集合的级别置换组。 湮没多项式是基于层次排列集合找到的。 湮灭多项式被考虑，选择机制根据湮灭多项式的因素选择最小多项式。
-
48.发明申请公开(公告)号：US20100163316A1
公开(公告)日：2010-07-01
申请号：US12345668
申请日：2008-12-30
申请人： Ming Chang , Shi Han , Dongmei Zhang , Yu Zou , Xinjian Chen
发明人： Ming Chang , Shi Han , Dongmei Zhang , Yu Zou , Xinjian Chen
IPC分类号： G08C21/00
CPC分类号： G06K9/00416 , G06K9/00429 , G16C20/70
摘要： Described is a multi-path handwriting recognition framework based upon stroke segmentation, symbol recognition, two-dimensional structure analysis and semantic structure analysis. Electronic pen input corresponding to handwritten input (e.g., a chemical expression) is recognized and output via a data structure, which may include multiple recognition candidates. A recognition framework performs stroke segmentation and symbol recognition on the input, and analyzes the structure of the input to output the data structure corresponding to recognition results. For chemical expressions, the structural analysis may perform a conditional sub-expression analysis for inorganic expressions, or organic bond detection, connection relationship analysis, organic atom determination and/or conditional sub-expression analysis for organic expressions. The structural analysis also performs subscript, superscript analysis and character determination. Further analysis may be performed, e.g., chemical valence analysis and/or semantic structure analysis.
摘要翻译： 描述了基于笔划分割，符号识别，二维结构分析和语义结构分析的多路径手写识别框架。 对应于手写输入（例如，化学表达）的电子笔输入通过可包括多个识别候选的数据结构被识别和输出。 识别框架对输入进行笔划分割和符号识别，并分析输入结构以输出与识别结果相对应的数据结构。 对于化学表达式，结构分析可以对有机表达进行无机表征或有机键检测，连接关系分析，有机原子测定和/或条件子表达分析的条件子表达分析。 结构分析还执行下标，上标分析和字符测定。 可以进行进一步分析，例如化学价态分析和/或语义结构分析。
-
公开(公告)号：US20100191793A1
公开(公告)日：2010-07-29
申请号：US12360853
申请日：2009-01-28
申请人： Xu Yang , Xiaolin Quan , Dongmei Zhang , Gong Cheng , Jian Wang , Hao Wei
发明人： Xu Yang , Xiaolin Quan , Dongmei Zhang , Gong Cheng , Jian Wang , Hao Wei
摘要： A method for performing symbolic computations on a mathematical expression. The mathematical expression may be converted to a tree structure having one or more parent nodes and one or more child nodes. Each parent node may be a mathematical operation. Each child node may be a mathematical expression on which the mathematical operation is performed in a specified order. Each child node may be in a hierarchical relationship to one of the parent nodes. The parent nodes, the child nodes or both may be manipulated to perform a first symbolic computation on the mathematical expression.
摘要翻译： 一种用于对数学表达式执行符号计算的方法。 数学表达式可以转换为具有一个或多个父节点和一个或多个子节点的树结构。 每个父节点可以是数学运算。 每个子节点可以是以指定顺序执行数学运算的数学表达式。 每个子节点可以与父节点中的一个分层关系。 可以操纵父节点，子节点或两者以对数学表达式执行第一符号计算。
-
公开(公告)号：US20100169605A1
公开(公告)日：2010-07-01
申请号：US12346061
申请日：2008-12-30
申请人： Xu Yang , Hao Wei , Gong Cheng , ZhangZhang Song , Dongmei Zhang , Jian Wang
发明人： Xu Yang , Hao Wei , Gong Cheng , ZhangZhang Song , Dongmei Zhang , Jian Wang
CPC分类号： G06F7/483 , G06F7/49957
摘要： Techniques for providing arbitrary precision floating number (APFN) processing are disclosed. In some aspects, an APFN store may be used to store a large number (i.e., an APFN) having many significant digits, which in turn may enable a high degree of precision in mathematical operations. An APFN module may be used to create and define the APFN store. The APFN module may enable a user to define a precision (significant digits) for the large number that corresponds to the size of an array of bytes in the APFN store that are allocated for storing the large number. In further aspects, the APFN store may be used to store additional intermediary data and a resultant.
摘要翻译： 公开了提供任意精度浮动数（APFN）处理的技术。 在一些方面，可以使用APFN存储来存储具有许多有效数字的大量（即，APFN），这又可以使数学运算中的高度精度。 可以使用APFN模块来创建和定义APFN存储。 APFN模块可以使用户能够为与分配用于存储大数量的APFN存储中的字节数组的大小相对应的大数量定义精确度（有效数字）。 在另外的方面，APFN存储可以用于存储附加的中间数据和结果。
-
-
-
-
-
-
-
-
-
搜索结果
115 条记录 (耗时 0.035 秒)
