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
    • 2. 发明授权
    • Document identifying device and method
    • 文件识别装置和方法
    • US07110600B1
    • 2006-09-19
    • US10049635
    • 1999-09-30
    • Takayuki MatsuiYutaka KatsumataKazunori YamamotoShinichi Eguchi
    • Takayuki MatsuiYutaka KatsumataKazunori YamamotoShinichi Eguchi
    • G06K9/34G06K9/00
    • G06K9/2054G06K2209/01
    • The invention relates to a document discriminating apparatus and a discriminating method for use in processing documents at financial institutions. A characteristic portion inherent in an optional format is cut out from image data read from a document in the optional format. Color constituents of the cut out image data are analyzed, and a color constituent exhibiting characteristics is selected from the constituents, and a color separation parameter is set for the selected color constituent. Data information is prepared which is related to the image data cut out based upon the color separation parameter. On the other hand, data information is prepared from image data obtained by reading a document to be discriminated based on the color separation parameter. Then, the data information is compared for determination with the data information stored in the document discriminating dictionary unit, whereby the document is discriminated.
    • 本发明涉及一种在金融机构处理文件的文件鉴别装置和鉴别方法。 从可选格式的文档读取的图像数据中切出可选格式固有的特征部分。 分析切出的图像数据的颜色成分,并从成分中选择显示特征的颜色成分,并为所选色成分设定色分离参数。 准备与基于颜色分离参数切出的图像数据有关的数据信息。 另一方面,从通过根据颜色分离参数读取待鉴别的文档获得的图像数据来准备数据信息。 然后,将数据信息与存储在文档识别字典单元中的数据信息进行比较以确定文档,从而识别文档。
    • 10. 发明授权
    • Boundary extracting method, program, and device using the same
    • 边界提取方法,程序和设备使用相同
    • US07729536B2
    • 2010-06-01
    • US10958231
    • 2004-10-06
    • Shinichi EguchiNaoko SuzukiYutaka KatsumataKouichi Kanamoto
    • Shinichi EguchiNaoko SuzukiYutaka KatsumataKouichi Kanamoto
    • G06K9/34G06K9/00
    • G06K9/00449G06K9/32
    • An edge detecting method detects edge segments by searching all of the search lines forming an image from an end of the image in a direction perpendicular to the edges. If a line whose edge segment cannot be detected exists, a search is made in all of the search lines from the vicinity of the center of the image toward the end of the image, whereby edge segments are detected. A linear edge is determined from edge segments. A plurality of edge candidates are obtained from the edge segments for all of the search lines, and an optimum candidate is selected from among the edge candidates. Ruled lines are extracted from the source document in the image, and an optimum candidate is selected based on a comparison with a ruled line. As a result, an edge of the source document can be detected with high accuracy even if an image on a background side is unstable, or if materials of the background and the source document are similar.
    • 边缘检测方法通过从垂直于边缘的方向从图像的结尾搜索形成图像的所有搜索线来检测边缘片段。 如果存在不能检测其边缘段的线,则在从图像的中心附近到图像的结尾的所有搜索线中进行搜索,从而检测边缘片段。 从边缘段确定线性边。 从所有搜索线的边缘片段获得多个边缘候选,并且从边缘候选中选择最佳候选。 从图像中的源文档中提取标准线,并且基于与格线的比较来选择最佳候选。 结果,即使背景侧的图像不稳定,或者背景和源文档的材料相似,也可以高精度地检测源文档的边缘。