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
    • 4. 发明专利
    • Document recognizing method
    • 文件识别方法
    • JP2002366893A
    • 2002-12-20
    • JP2001173631
    • 2001-06-08
    • Hitachi Ltd株式会社日立製作所
    • TSUTSUI TATSUMIWATANABE SHIGERUASANO EISUKE
    • G06K9/20G06F19/00G06K9/03G06Q10/10
    • PROBLEM TO BE SOLVED: To provide a document recognizing method which can improve the recognition precision.
      SOLUTION: The document recognizing method which limits a document kind for an inputted document image (104), recognizes characters of the document image with the limited document kind (104), and outputs the recognition result to a host device (108) is characterized in that when the character recognition of a recognition request area in the document image is performed, a character string equivalent to a character string entered into the recognition request area which is detected in an area other than the recognition request area and the recognition result are merged and outputted to the host device.
      COPYRIGHT: (C)2003,JPO
    • 要解决的问题:提供可以提高识别精度的文档识别方法。 解决方案:限制文件类型(104)的文档类型的文档识别方法以有限文档类型(104)识别文档图像的字符,并将识别结果输出到主机设备(108),其特征在于 当执行文件图像中的识别请求区域的字符识别时,将与在识别请求区域以外的区域中检测到的输入到识别请求区域的字符串相当的字符串和识别结果合并, 输出到主机设备。
    • 5. 发明专利
    • Document recognizing method
    • 文件识别方法
    • JP2003016281A
    • 2003-01-17
    • JP2001200428
    • 2001-07-02
    • Hitachi Ltd株式会社日立製作所
    • WATANABE SHIGERUASANO EISUKE
    • G06K9/20G06F19/00G06Q10/10G06Q40/00G06Q40/02G06F17/60
    • PROBLEM TO BE SOLVED: To improve entire identification accuracy while suppressing the prolongation of processing time by improving the identification rate of only a specified document kind with the high frequency of appearance.
      SOLUTION: Each of mail sorters 102 and 103 reads the destination of mail and a DM kind, acquires statistical information on a delivery area and a number of documents for each read document type and sends the information to a center 101. In the center, with the date of passing through the sorter for each couple of document type and delivery area as a reference, a predictive appearance frequency graph showing the date and a number of recipients of transfer is prepared and on the basis of this graph, a strengthening instruction is prepared for strengthening reading of a document (y) in an area (x) during a period (z) and sent to document recognizing devices 104-106 in correspondent areas. When the document recognizing device can not discriminate a document type, a controlled image for document (y) is fetched, a definition file for identifying the document (y) is loaded, the document type is discriminated again and the discriminated document is read by loading the definition file for document reading.
      COPYRIGHT: (C)2003,JPO
    • 要解决的问题:通过提高具有高频率外观的特定文件种类的识别率,来提高整体识别精度,同时抑制处理时间的延长。 解决方案:每个邮件分类器102和103读取邮件的目的地和DM类,获取关于每个读取文档类型的传送区域和文档数量的统计信息,并将信息发送到中心101.在中心,具有 通过分拣机的每一对文件类型和交付区域的日期作为参考,准备了显示转移的接收者的日期和数量的预测出现频率图,并且基于该图,准备加强指令 用于在时段(z)期间加强在区域(x)中的文档(y)的读取,并将其发送到对应区域中的文档识别装置104-106。 当文档识别装置不能区分文件类型时,取出用于文件(y)的受控图像,加载用于识别文档(y)的定义文件,再次识别文档类型,并通过加载来读取所识别的文档 用于文档读取的定义文件。