利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

130 条记录 (耗时 0.023 秒)

    Process and equipment for recognition of a pattern on an item presented
    35.
    发明公开
    Process and equipment for recognition of a pattern on an item presented 有权
    所呈现的物体上的方法和用于识别的图案的设备

    公开(公告)号：EP0955600A2

    公开(公告)日：1999-11-10

    申请号：EP99105724.1

    申请日：1999-03-20

    申请人： International Business Machines Corporation

    发明人： Maier, Udo, Dipl.-Ing. ,  Ruppert, Werner, Dipl.-Ing.

    IPC分类号： G06K9/03

    CPC分类号： G06K9/685 ,  G06K9/03

    摘要： A novel system for recognition of patterns on presented item. A known recognition system expanded by a complementary recognition which is linked with the primary recognition. The results of the primary recognition which are not positively recognised are passed on to the complementary recognition and any characters not positively recognised by the complementary recognition are again passed on to a correction system. Here an operator classifies the unrecognised characters which are then used to teach the complementary recognition unit. Thus, the classified data of the correction system provide the training data for a continuous training process which is coupled with the correction system.

    摘要翻译： 一种新型的系统，用于识别上呈现项目的图案。 通过补充识别扩展的已知识别系统中的所有其与初级识别的联系。 未积极地识别的初级识别的结果被传递到补充识别和补充识别不积极地识别的任何字符被再次传递到一个校正系统。在这里，在操作者进行分类的无法识别的字符然后将它们用于教 补充识别单元。 因此，校正系统的分类的数据提供被加上校正系统用于连续锻炼过程中的锻炼数据全部。

    A pattern recognition apparatus and method for doing the same
    37.
    发明授权
    A pattern recognition apparatus and method for doing the same 失效
    模式识别装置及其方法

    公开(公告)号：EP0355748B1

    公开(公告)日：1997-11-19

    申请号：EP89115297.7

    申请日：1989-08-18

    申请人： FUJITSU LIMITED

    发明人： Kimura, Masayuki

    IPC分类号： G06K9/62 ,  G06K9/68 ,  G10L3/00

    CPC分类号： G06K9/685 ,  G10L15/00 ,  Y10S707/99935

    摘要： A learning pattern is classified into a plurality of patterns by a classifying means (102). The result of the classification, as well as the representative features quantity calculated by a representative feature quantity operating unit (103), are stored in a dictionary storing unit (104) in respective regions. Upon recognition, after feature quantities of unknown input patterns are extracted from a feature quantity extracting unit (101), a similarity operating unit (105) arithmetically operates the similarity between the input pattern and respective learning patterns for respective regions. The point accumulating means (106) searches a dictionary storing unit (104) and accumulates points corresponding to a rank for respective learning patterns included in class having the upper rank from the highest to a lower similarity for respective regions. The recognition result candidate outputting unit (107) outputs the recognition result candidate in accordance with the order of the higher accumulated point for the learning pattern. Therefore, the present pattern recognition can decrease the memory capacity of the dictionary and the number of the calculations.

    Sign recognition apparatus and method and sign translation system using same
    38.
    发明公开
    Sign recognition apparatus and method and sign translation system using same 失效
    手语识别设备和方法，并使用相同的手语翻译系统。

    公开(公告)号：EP0585098A2

    公开(公告)日：1994-03-02

    申请号：EP93306674.8

    申请日：1993-08-23

    申请人： HITACHI, LTD.

    发明人： Sakou, Hiroshi ,  Sagawa, Hirohiko, Hitachi Daiyon Kyoshinryo ,  Abe, Masahiro ,  Ichikawa, Akira ,  Inoue, Kiyoshi ,  Arai, Kiyoshi ,  Shimura, Takanori ,  Toda, Yuji

    IPC分类号： G06K9/00

    CPC分类号： G06F17/2872 ,  G06K9/00355 ,  G06K9/6293 ,  G06K9/685 ,  G09B21/009

    摘要： In continuous sign language recognition, reference sign language patterns of good quality are generated. Continuous sign language patterns and reference sign language patterns are efficiently compressed. The compressed continuous sign language patterns are sequentially and directly matched with the compressed reference sign language patterns to recognize the sign language at high speed and with high precision. A reference sign pattern generating unit (3) generates a reference sign language pattern by normalizing sample patterns while taking into consideration of their nonlinear compression/expansion and by calculating an average of the sample patterns. A continuous sign language recognition unit (5) recognizes a continuous sign language at high speed by sequentially matching the continuous sign language of time sequential patterns with reference sign language patterns while allowing nonlinear expansion and compression in the time domain. A sign language translation system is provided in which a sign language as well as the facial expression or emotion of a sign language user is recognized and converted into a spoken language with emotion, and transferred in the form of texts, voices, sign languages of another type to a particular partner among a plurality of unknown system users.

    摘要翻译： 在连续手语识别，生成质量好的符号语言模式。 连续手语图案和符号语言模式有效地压缩。 压缩连续符号的语言模式是顺序并直接与压缩基准符号语言模式匹配来识别手语以高速和高精确度。 参考符号图案通过归一化，同时考虑到它们的非线性压缩/膨胀的样本图案和通过计算在样品图案的平均生成部（3）基因率的参考符号的语言模式。 的连续手语识别单元（5）确认通过顺序地以高速连续手语与附图标记语言模式匹配的时间序列模式的连续的手语，同时允许在时域非线性膨胀和压缩。 手语翻译系统是将提供手语和手语使用者的面部表情或情绪被识别并转换成与情绪的口语，并在文字，声音的形式传输，签署的另一种语言 键入未知系统用户的多元化中的特定的合作伙伴。

    Pattern recognition apparatus
    39.
    发明公开
    Pattern recognition apparatus 失效
    Mustererkennungsgerät。

    公开(公告)号：EP0335696A2

    公开(公告)日：1989-10-04

    申请号：EP89303116.1

    申请日：1989-03-29

    申请人： KABUSHIKI KAISHA TOSHIBA

    发明人： Kurosawa, Yoshiaki c/o Patent Division

    IPC分类号： G06K9/68

    CPC分类号： G06K9/685

    摘要： A pattern recognition apparatus has a contour segmentation unit (14) for dividing an input pattern into segments, a characteristic extraction unit (16) for extracting characteristics of the input segments, and a reference unit (20) for storing characteristic data of reference patterns. The reference unit (20) includes a main reference (22) and a detailed matching reference (26). The main reference (22) stores partial pattern characteristic data representing the characteristics of segments of each reference pattern. The detailed matching reference (26) stores detailed characteristic data of each reference pattern together with a program for specifying an operation procedures thereof. A matching processor (18) sequentially compares and colla­tes the input pattern with the reference patterns to find out that standard pattern with which the input pat­tern is matched with the highest similarity. When the input pattern is matched with several reference pat­terns, a detailed recognition unit (24) performs a detailed recognition process using the detailed charac­teristic data of these reference patterns to finally select the correct one from among the reference pat­terns. The main reference (22) additionally stores identification marks to identify specific reference segments necessary to acquired the above detailed characteristic data.

    摘要翻译： 模式识别装置具有用于将输入图案分割成段的轮廓分割单元（14），用于提取输入段特征的特征提取单元（16），以及用于存储参考图形特征数据的参考单元（20）。 参考单元（20）包括主参考（22）和详细匹配参考（26）。 主参考（22）存储表示每个参考图案的段的特征的部分图案特征数据。 详细匹配参考（26）存储每个参考模式的详细特征数据以及用于指定其操作过程的程序。 匹配处理器（18）顺序地将输入图案与参考图案进行比较和整理，以找出输入图案与最高相似度匹配的标准图案。 当输入图案与几个参考图案匹配时，详细的识别单元（24）使用这些参考图案的详细特征数据执行详细的识别处理，以最终从参考图案中选择正确的参考图案。 主要参考（22）另外存储识别标记以识别获取上述详细特征数据所必需的特定参考段。

    Optical character reader
    40.
    发明公开
    Optical character reader 失效
    Optische Zeichenlesevorrichtung。

    公开(公告)号：EP0322920A2

    公开(公告)日：1989-07-05

    申请号：EP88121865.5

    申请日：1988-12-29

    申请人： SUMITOMO ELECTRIC INDUSTRIES LIMITED

    发明人： Yamaguchi, Mikio c/o Osaka Works ,  Maeda, Naoki c/o Osaka Works

    IPC分类号： G06K9/03

    CPC分类号： G06K9/03 ,  G06K9/685

    摘要： An apparatus and method for determining a character read by an optical character reader during a plurality of scans, whereby the character is determined from the plurality of scans by taking into consideration the tendency that the character will be misread as a second character. If there is no possibility that the second character could be interpreted as a misreading of the character which is read by the optical character reader, a "REJECT" or error signal may be generated, thus improving the reliability of determined characters.

    摘要翻译： 一种用于在多次扫描期间确定由光学字符读取器读取的字符的装置和方法，由此通过考虑字符将被误读为第二个字符的趋势，从多个扫描确定字符。 如果不可能将第二个字符解释为由光学字符读取器读取的字符的误读，则可以生成“拒绝”或错误信号，从而提高确定字符的可靠性。