利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

39 条记录 (耗时 0.025 秒)

    Character recognition apparatus and method
    2.
    发明授权
    Character recognition apparatus and method 失效
    字符识别装置及方法

    公开(公告)号：US6052482A

    公开(公告)日：2000-04-18

    申请号：US773838

    申请日：1996-12-27

    申请人： Tsunekazu Arai ,  Eiji Takasu ,  Hiroto Yoshii

    发明人： Tsunekazu Arai ,  Eiji Takasu ,  Hiroto Yoshii

    IPC分类号： G06K9/68 ,  G06K9/62

    CPC分类号： G06K9/6253

    摘要： A threshold value for identifying similar characters is set at will from a keyboard. It is determined whether a character entered on a character input panel by a pen is a similar character and, if the entered character is judged to be a similar character, a feature quantity of this character is calculated. The calculated feature quality and the set threshold value are compared. On the basis of the comparison, the character determined to be a similar character is identified as being in any of a plurality of character groups of similar characters.

    摘要翻译： 用于识别相似字符的阈值是从键盘设置的。 确定通过笔输入的字符输入面板上的字符是否是相似的字符，并且如果输入的字符被判定为相似的字符，则计算该字符的特征量。 比较计算出的特征质量和设定的阈值。 在比较的基础上，确定为相似字符的字符被识别为具有相似字符的多个字符组中的任何一个。

    Image processing method and an image processing apparatus
    4.
    发明授权
    Image processing method and an image processing apparatus 失效
    图像处理方法和图像处理装置

    公开(公告)号：US5835632A

    公开(公告)日：1998-11-10

    申请号：US612494

    申请日：1996-03-07

    申请人： Eiji Takasu ,  Tsunekazu Arai ,  Hiroto Yoshii

    发明人： Eiji Takasu ,  Tsunekazu Arai ,  Hiroto Yoshii

    IPC分类号： G06K9/46 ,  G06K9/42 ,  G06K9/62 ,  G06K9/00

    CPC分类号： G06K9/42 ,  G06K9/6255 ,  G06K2209/01

    摘要： An image processing system includes entering a predetermined sample character, comparing characteristic data for the sample character with characteristic data for a predetermined reference character, extracting characteristic data inherent to the entered sample character and relative to the reference character, storing the extracted characteristic data, and correcting a character which is newly entered for recognition and different from the predetermined sample character in accordance with the stored characteristic data.

    摘要翻译： 一种图像处理系统，包括输入预定的采样字符，将样本字符的特征数据与预定参考字符的特征数据进行比较，提取输入的采样字符固有的特征数据和相对于参考字符，存储所提取的特征数据，以及 根据所存储的特征数据，校正新输入的用于识别并与预定采样字符不同的字符。

    Information processing method and apparatus
    5.
    发明授权
    Information processing method and apparatus 失效
    信息处理方法和装置

    公开(公告)号：US06697524B1

    公开(公告)日：2004-02-24

    申请号：US09597822

    申请日：2000-06-19

    申请人： Tsunekazu Arai ,  Katsuhiko Sakaguchi ,  Shigeki Mori ,  Kazuhiro Matsubayashi ,  Takashi Harada ,  Eiji Takasu ,  Hiroto Yoshii

    发明人： Tsunekazu Arai ,  Katsuhiko Sakaguchi ,  Shigeki Mori ,  Kazuhiro Matsubayashi ,  Takashi Harada ,  Eiji Takasu ,  Hiroto Yoshii

    IPC分类号： G06K900

    CPC分类号： G06K9/6255 ,  G06K9/222 ,  G06K9/6807

    摘要： An information processing method and apparatus which uses a memory storing stroke data forming one character together with respective stroke order information to display each stroke data based on the stored stroke order information at an arbitrary speed. In addition, a display speed changing instruction is input into the apparatus and the display speed of the stroke data is changed in response to the display speed changing instruction. In addition, stroke data stored in correspondence to the stroke order information of an input stroke order number is read from the memory and displayed. Further, the stroke data can be displayed under different display conditions such that the stroke order information stored in correspondence to the stroke data can be distinguished from each other.

    摘要翻译： 一种信息处理方法和装置，其使用存储形成一个字符的笔划数据的存储器以及相应的笔画顺序信息，以任意速度基于所存储的笔画顺序信息来显示每个笔划数据。 此外，显示改变指令被输入到装置中，并且根据显示速度改变指令改变笔画数据的显示速度。 此外，从存储器读取与输入笔画顺序编号的笔顺顺序信息相对应地存储的笔迹数据并显示。 此外，笔画数据可以在不同的显示条件下显示，使得可以将与笔画数据相对应存储的笔画顺序信息彼此区分开。

    Information processing method and apparatus with mixing of processing command input strokes and input strokes for patterns
    6.
    发明授权
    Information processing method and apparatus with mixing of processing command input strokes and input strokes for patterns 失效
    具有处理命令输入笔画和模式输入笔画的信息处理方法和装置

    公开(公告)号：US06408091B1

    公开(公告)日：2002-06-18

    申请号：US08637156

    申请日：1996-04-24

    申请人： Katsuhiko Sakaguchi ,  Tsunekazu Arai ,  Eiji Takasu ,  Hiroto Yoshii

    发明人： Katsuhiko Sakaguchi ,  Tsunekazu Arai ,  Eiji Takasu ,  Hiroto Yoshii

    IPC分类号： G06K900

    CPC分类号： G06F3/04883

    摘要： The present invention is to discriminate and extract a gesture stroke from a group of input strokes when inputting, in a batch processing, both a character or symbol of strokes to be processed and a gesture of strokes selecting a process to be executed for the character or symbol, and execute a process selected by the gesture stroke for all the strokes but the extracted gesture stroke, so that the character or symbol and the gesture do not need inputting individually at time intervals, thus improving the operability.

    摘要翻译： 本发明是在批量处理中输入要处理的笔画的字符或符号以及选择要为字符执行的处理的笔画的手势时，从一组输入笔画中区分并提取手势笔画，或者 符号，并且执行由所有笔划的手势笔画选择的处理，但是提取的手势笔画，使得字符或符号和手势不需要以时间间隔单独输入，从而提高可操作性。

    Information processing method, information processing apparatus, and storage medium
    8.
    发明授权
    Information processing method, information processing apparatus, and storage medium 失效
    信息处理方法，信息处理装置和存储介质

    公开(公告)号：US5982933A

    公开(公告)日：1999-11-09

    申请号：US777249

    申请日：1996-12-31

    申请人： Hiroto Yoshii ,  Tsunekazu Arai ,  Eiji Takasu

    发明人： Hiroto Yoshii ,  Tsunekazu Arai ,  Eiji Takasu

    IPC分类号： G06K9/62 ,  G06K9/00

    CPC分类号： G06K9/6282

    摘要： This relates to a classification generation method whereby, in order to efficiently and accurately recognize a pattern having a large number of characteristics, a pattern classification tree is generated, with which a macro structural characteristic of a pattern is appropriately reflected and a competitive relationship between categories is adequately reflected, and to a method for recognizing an input pattern by using the generated classification tree. When an input pattern is formed using strokes, a training stroke is divided into a plurality of segments, and vector quantization is performed for the strokes in the segments. Among the quantized strokes in the segments, adjacent stroke sets are synthesized to repetitively generate upper rank stroke vectors. A stroke vector for which a predetermined entropy function is maximized is selected from the upper rank stroke vectors in a layered stroke vector series, and development is performed extending down into the lower rank stroke vector sets. As a result, a classification tree is prepared.

    摘要翻译： 这涉及一种分类生成方法，为了有效且准确地识别具有大量特征的图案，生成了模式分类树，其中模式的宏观结构特征被适当地反映，并且类别之间的竞争关系 以及通过使用生成的分类树来识别输入模式的方法。 当使用笔画形成输入图案时，将训练笔划分成多个段，并且对段中的笔画执行向量量化。 在片段中的量化笔画中，合成相邻的笔画集以重复地产生上级笔画矢量。 从分层笔画矢量序列中的上位行程矢量中选择预定熵函数最大化的笔画矢量，并且进行向下延伸到下级笔画矢量集的显影。 结果，准备了分类树。

    Pattern recognition apparatus and method utilizing conversion to a common scale by a linear function
    10.
    发明授权
    Pattern recognition apparatus and method utilizing conversion to a common scale by a linear function 失效
    利用线性函数将模式识别装置和方法转换成公共尺度

    公开(公告)号：US06671403B1

    公开(公告)日：2003-12-30

    申请号：US08715121

    申请日：1996-09-17

    申请人： Eiji Takasu ,  Tsunekazu Arai ,  Hiroto Yoshii

    发明人： Eiji Takasu ,  Tsunekazu Arai ,  Hiroto Yoshii

    IPC分类号： G06K900

    CPC分类号： G06K9/6292

    摘要： Two different recognition processing units respectively perform a plurality of different recognition processing operations for the pattern to be recognized input from a character input unit, and acquire a plurality of recognition candidates and recognition scores. An accuracy calculation unit converts the recognition scores obtained by the two recognition processing units into accuracies based on a scale common to the plurality of different recognition processing operations using parameters stored in a parameter storage unit. A determination unit generates a recognition candidate sequence by determining the order of the recognition candidates obtained by the two recognition processing units on the basis of the accuracies converted by the accuracy calculation unit.

    摘要翻译： 两个不同的识别处理单元分别对从字符输入单元输入的图案进行多个不同的识别处理操作，并且获取多个识别候选和识别分数。 准确度计算单元使用存储在参数存储单元中的参数，将由两个识别处理单元获得的识别分数转换为基于与多个不同识别处理操作共同的标度的精度。 确定单元通过基于由精度计算单元转换的精度来确定由两个识别处理单元获得的识别候选的顺序来生成识别候选序列。