-
1.发明授权Method and system for training a handwriting recognizer at the time of misrecognition 失效错误识别时用于训练手写识别器的方法和系统
公开(公告)号：US5550930A
公开(公告)日：1996-08-27
申请号：US42834
申请日：1993-04-05
申请人： Eric R. Berman , Luis F. T. Abdala , Marlin Eller
发明人： Eric R. Berman , Luis F. T. Abdala , Marlin Eller
CPC分类号： G06K9/033
摘要： A method and system for training a handwriting recognizer at the time of misrecognition is provided. In a preferred embodiment, a trainer program traps and stores the output from a recognizer. The output includes the recognized symbols mapped to the handwritten data. When training is requested by a user, the trainer displays the handwritten data that was input by the user and the recognized symbols. The user then selects the symbols to train on. In response to the selection, the trainer displays the portion of the handwritten data corresponding to the selected symbols. The user then enters the symbols that the displayed portion of the handwritten data should be recognized as. The trainer then requests the recognizer to train based on the displayed portion of the data and the entered symbols. When training is complete, the trainer requests re-recognition of the handwritten data and displays the newly recognized symbols.
摘要翻译： 提供了一种用于在错误识别时对手写识别器进行训练的方法和系统。 在优选实施例中，训练器程序捕获并存储来自识别器的输出。 输出包括映射到手写数据的识别符号。 当用户请求训练时，训练者显示由用户输入的手写数据和识别的符号。 然后用户选择要训练的符号。 响应于选择，训练者显示与所选符号对应的手写数据的部分。 然后，用户输入手写数据的显示部分应该被识别的符号。 训练者然后根据所显示的数据部分和输入的符号请求识别器进行训练。 培训完成后，培训师要求重新识别手写数据并显示新识别的符号。
-
2.发明授权公开(公告)号：US06201174B1
公开(公告)日：2001-03-13
申请号：US09211163
申请日：1998-12-11
申请人： Marlin Eller
发明人： Marlin Eller
IPC分类号： G09B1502
CPC分类号： G09B15/023 , G09B15/003
摘要： A computerized tablature composer automatically updates a tablature notation following edits of a corresponding staff notation. The computerized tablature composer conversely links edits to a tablature notation with corresponding updates in a staff notation for a corresponding musical score. The computerized tablature composer ensures vertical alignment between corresponding notes in a staff notation and a tablature notation. The computerized tablature composer ensures that the actual played notes in both musical representations are aligned so that the musician knows which note in the staff notation corresponds to which note in the tablature notation. The computerized tablature composer further allows the coupling between tablature and conventional staff notation to be de-coupled upon request. The computerized tablature composer provides a musician with alternate fret locations for the notes in a musical work when the musician indicates an alternate string for a given note. The computerized tablature composer provides a virtual tuning peg that allows a musician to use non-standard tunings by changing the fret numbers in the tablature notation to reflect new tuning data for one or more strings represented by the tablature notation.
摘要翻译： 计算机化的标签作曲家在相应的工作人员符号编辑后自动更新标签符号。 计算机化的tablature作曲家反过来将编辑与一个tablature符号相关联，并以相应的乐谱的工作人员符号中的相应更新。 计算机化的标签作曲家确保在工作人员符号和标签符号之间的对应笔记之间的垂直对齐。 计算机化的标签作曲家确保在两个音乐表现中实际播放的音符是对齐的，以便音乐家知道工作人员符号中哪个音符对应于标签符号中的哪个音符。 计算机化标签作曲家进一步允许根据要求将标签和常规工作人员符号之间的耦合取消耦合。 计算机化的乐谱作曲家为音乐家提供音乐作品中的音符，当音乐家指示给定音符的另一个字符串时，可以为音乐人提供音乐。 计算机化的tablature作曲家提供了一个虚拟调音栓，允许音乐家通过改变标签符号中的fret数来使用非标准调谐，以反映由tablature表示法表示的一个或多个字符串的新调谐数据。
-
3.发明授权Method and system for recognizing a graphic object's shape, line style, and fill pattern in a pen environment 失效在笔式环境中识别图形对象的形状，线条和填充图案的方法和系统
公开(公告)号：US5636297A
公开(公告)日：1997-06-03
申请号：US303339
申请日：1994-09-09
CPC分类号： G06K9/222 , G06K9/00402 , G06T11/40
摘要： A method and system for recognizing a graphic object's shape, line style, and fill pattern in a pen environment are provided. In a preferred embodiment, a user draws a graphic object on an electronic tablet of a computer system. The graphic object comprises a shape attribute, a line style attribute, and a fill pattern attribute. A Recognizer, recognizes the graphic object. The graphic object is made up of a plurality of data points, each data point having an x-coordinate and a y-coordinate. The Recognizer subdivides the plurality of data points into one or more strokes, each stroke representative of a path travelled by the handwriting instrument after the handwriting instrument touches the tablet and before the handwriting instrument is lifted off of the tablet. For each data point in each stroke, the recognizer maps the data point to a normalized data point, then transforms the normalized data point into a transformed data point, and then determines whether the transformed data point is a shape-defining data point or an interior-defining data point. Shape-defining data points are representative of the shape attribute and the line style attribute, while the interior-defining data points are representative of the fill pattern attribute. Based on the coordinates of the transformed data points and the coordinates of the data points, the recognizer determines the attributes. After determining the attributes of the graphic object, the recognizer selects a representation of the graphic object that corresponds to the determined attributes and displays the representation on the electronic tablet.
摘要翻译： 提供了一种用于在笔环境中识别图形对象的形状，线条和填充图案的方法和系统。 在优选实施例中，用户在计算机系统的电子平板电脑上绘制图形对象。 图形对象包括形状属性，线条样式属性和填充图案属性。 识别器，识别图形对象。 图形对象由多个数据点组成，每个数据点具有x坐标和y坐标。 识别器将多个数据点细分成一个或多个笔画，每个笔画代表在手写乐器触摸平板电脑之后以及在手写乐器从平板电脑上提起之前由手写乐器行进的路径。 对于每个笔画中的每个数据点，识别器将数据点映射到归一化数据点，然后将归一化数据点变换为变换数据点，然后确定变换数据点是否是形状定义数据点或内部 定义数据点。 形状定义数据点代表形状属性和线条样式属性，而内部定义数据点代表填充图案属性。 基于变换的数据点的坐标和数据点的坐标，识别器确定属性。 在确定图形对象的属性之后，识别器选择对应于确定的属性的图形对象的表示，并在电子平板电脑上显示该表示。
-
4.发明授权
公开(公告)号：US5710832A
公开(公告)日：1998-01-20
申请号：US569497
申请日：1995-12-08
CPC分类号： G06K9/033
摘要： A method and system for training a handwriting recognizer at the time of misrecognition is provided. In a preferred embodiment, a trainer program traps and stores the output from a recognizer. The output includes the recognized symbols mapped to the handwritten data. When training is requested by a user, the trainer displays the handwritten data that was input by the user and the recognized symbols. The user then selects the symbols to train on. In response to the selection, the trainer displays the portion of the handwritten data corresponding to the selected symbols. The user then enters the symbols that the displayed portion of the handwritten data should be recognized as. The trainer then requests the recognizer to train based on the displayed portion of the data and the entered symbols. When training is complete, the trainer requests re-recognition of the handwritten data and displays the newly recognized symbols.
摘要翻译： 提供了一种用于在错误识别时对手写识别器进行训练的方法和系统。 在优选实施例中，训练器程序捕获并存储来自识别器的输出。 输出包括映射到手写数据的识别符号。 当用户请求训练时，训练者显示由用户输入的手写数据和识别的符号。 然后用户选择要训练的符号。 响应于选择，训练者显示与所选符号对应的手写数据的部分。 然后，用户输入手写数据的显示部分应该被识别的符号。 训练者然后根据所显示的数据部分和输入的符号请求识别器进行训练。 培训完成后，培训师要求重新识别手写数据并显示新识别的符号。
-
5.发明授权Method and system for recognizing a graphic object's shape, line style, and fill pattern in a pen environment 失效在笔式环境中识别图形对象的形状，线条和填充图案的方法和系统
公开(公告)号：US5287417A
公开(公告)日：1994-02-15
申请号：US942952
申请日：1992-09-10
CPC分类号： G06K9/222 , G06K9/00402 , G06T11/40
摘要： A method and system for recognizing a graphic object's shape, line style, and fill pattern in a pen environment are provided. In a preferred embodiment, a user draws a graphic object on an electronic tablet of a computer system. The graphic object comprises a shape attribute, a line style attribute, and a fill pattern attribute. A Recognizer, provided by the present invention, recognizes the graphic object drawn by the user. The graphic object drawn by the user is made up of a plurality of data points, each data point having an x-coordinate and a y-coordinate. The Recognizer subdivides the plurality of data points into one or more strokes, each stroke representative of a path travelled by the handwriting instrument after the handwriting instrument touches the electronic tablet and before the handwriting instrument is lifted off of the electronic tablet. For each data point in each stroke, the recognizer maps the data point to a normalized data point, then transforms the normalized data point into a transformed data point, and then determines whether the transformed data point is a shape-defining data point or an interior-defining data point. Shape-defining data points are representative of the shape attribute and the line style attribute, while the interior-defining data points are representative of the fill pattern attribute. Based on the coordinates of the transformed data points and the coordinates of the data points input by the user, the recognizer determines the attributes. After determining what the attributes of the graphic object are, the recognizer selects a representation of the graphic object that corresponds to the determined attributes and displays the selected representation on the electronic tablet.
摘要翻译： 提供了一种用于在笔环境中识别图形对象的形状，线条和填充图案的方法和系统。 在优选实施例中，用户在计算机系统的电子平板电脑上绘制图形对象。 图形对象包括形状属性，线条样式属性和填充图案属性。 由本发明提供的识别器识别用户绘制的图形对象。 由用户绘制的图形对象由多个数据点组成，每个数据点具有x坐标和y坐标。 识别器将多个数据点细分成一个或多个笔画，每个笔画代表在手写乐器触摸电子图形输入板之后以及在手写乐器从电子图形输出板上提起之前由手写乐器行进的路径。 对于每个笔画中的每个数据点，识别器将数据点映射到归一化数据点，然后将归一化数据点变换为变换数据点，然后确定变换数据点是否是形状定义数据点或内部 定义数据点。 形状定义数据点代表形状属性和线条样式属性，而内部定义数据点代表填充图案属性。 基于变换的数据点的坐标和用户输入的数据点的坐标，识别器确定属性。 在确定图形对象的属性之后，识别器选择对应于确定的属性的图形对象的表示，并在电子平板上显示所选择的表示。
-
-
-
-
搜索结果
5 条记录 (耗时 0.023 秒)
