知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.01 seconds)

    Document comparison and analysis
    1.
    发明授权
    Document comparison and analysis 失效
    文件比较分析

    公开(公告)号：US08472726B2

    公开(公告)日：2013-06-25

    申请号：US12929199

    申请日：2011-01-07

    Applicant: Yuval Gronau ,  Edo Likhovski

    Inventor： Yuval Gronau ,  Edo Likhovski

    IPC: G06K9/00

    CPC classification number: G06K9/03 ,  G06K9/00402 ,  G06K9/00483

    Abstract: A method including a process by which a first digital image of the document is obtained. A second digital image of a document is retrieved from a computer, a mobile device, a computer network or by imaging of a second document. The method includes calculating the transformation between the first and second digital images such as geometrical distortion, local brightness and contrast differences and blurring due to the optical imaging process. The method estimates the parameters of these transformations so that the transformations can be applied to one of the images, rendering it as similar as possible to the other image. The method further compares the two images in order to find differences such as addition, deletion or changing of characters or words.The method further displays the differences on a display such as a computer screen or mobile device screen or reports to the user that the two documents are identical.

    Abstract translation: 一种方法，包括获得文档的第一数字图像的处理。 从计算机，移动设备，计算机网络或第二文档的成像检索文档的第二数字图像。 该方法包括计算第一和第二数字图像之间的变换，例如几何失真，局部亮度和对比度差异以及由于光学成像过程引起的模糊。 该方法估计这些变换的参数，使得可以将变换应用于一个图像，使其尽可能类似于另一图像。 该方法进一步比较两个图像以便发现诸如字符或单词的添加，删除或改变之类的差异。 该方法还显示诸如计算机屏幕或移动设备屏幕的显示器上的差异，或向用户报告两个文档是相同的。

    Document comparison and analysis
    3.
    发明申请
    Document comparison and analysis 失效
    文件比较分析

    公开(公告)号：US20120177291A1

    公开(公告)日：2012-07-12

    申请号：US12929199

    申请日：2011-01-07

    Applicant: Yuval Gronau ,  Edo Likhovski

    Inventor： Yuval Gronau ,  Edo Likhovski

    IPC: G06K9/46 ,  G06K9/68

    CPC classification number: G06K9/03 ,  G06K9/00402 ,  G06K9/00483

    Abstract: A method including a process by which a first digital image of the document is obtained. A second digital image of a document is retrieved from a computer, a mobile device, a computer network or by imaging of a second document. The method includes calculating the transformation between the first and second digital images such as geometrical distortion, local ‘brightness and contrast differences and blurring due to the optical imaging process. The method estimates the parameters of these transformations so that the transformations can be applied to one of the images, rendering it as similar as possible to the other image. The method further compares the two images in order to find differences such as addition, deletion or changing of characters or words.The method further displays the differences on a display such as a computer screen or mobile device screen or reports to the user that the two documents are identical.

    Abstract translation: 一种方法，包括获得文档的第一数字图像的处理。 从计算机，移动设备，计算机网络或第二文档的成像检索文档的第二数字图像。 该方法包括计算第一和第二数字图像之间的变换，例如几何失真，局部亮度和对比度差异以及由于光学成像过程引起的模糊。 该方法估计这些变换的参数，使得可以将变换应用于一个图像，使其尽可能类似于另一图像。 该方法进一步比较两个图像以便发现诸如字符或单词的添加，删除或改变之类的差异。 该方法还显示诸如计算机屏幕或移动设备屏幕的显示器上的差异，或向用户报告两个文档是相同的。

    Document comparison and analysis for improved OCR
    5.
    发明授权
    Document comparison and analysis for improved OCR 失效
    改进OCR的文件比较和分析

    公开(公告)号：US08472727B2

    公开(公告)日：2013-06-25

    申请号：US12929200

    申请日：2011-01-07

    Applicant: Yuval Gronau ,  Edo Likhovski

    Inventor： Yuval Gronau ,  Edo Likhovski

    IPC: G06K9/00

    CPC classification number: G06K9/03 ,  G06K9/685 ,  G06K2209/01

    Abstract: A method for enhancing the accuracy of Optical Character Recognition (OCR) algorithms by detection of differences between a digital image of a document and a text file corresponding to the digital image, created by the OCR algorithm.The method includes calculating the transformation between the first and second digital images such as geometrical distortion, local brightness and contrast differences and blurring due to the optical imaging process. The method estimates the parameters of these transformations so that the transformations can be applied to at least one of the images, rendering it as similar as possible to the other image. The method further compares the two images in order to find differences. The method further displays the differences on a display device and analyzes the differences. The analysis results are fed back to the OCR algorithm.

    Abstract translation: 通过检测由OCR算法创建的文档的数字图像与对应于数字图像的文本文件之间的差异来增强光学字符识别（OCR）算法的精度的方法。 该方法包括计算第一和第二数字图像之间的变换，例如几何失真，局部亮度和对比度差异以及由于光学成像过程引起的模糊。 该方法估计这些变换的参数，使得可以将变换应用于至少一个图像，使其尽可能类似于另一图像。 该方法进一步比较两个图像以便发现差异。 该方法进一步显示显示设备上的差异并分析差异。 分析结果反馈给OCR算法。

    Document comparison and analysis for improved OCR
    6.
    发明申请
    Document comparison and analysis for improved OCR 失效
    改进OCR的文件比较和分析

    公开(公告)号：US20120177295A1

    公开(公告)日：2012-07-12

    申请号：US12929200

    申请日：2011-01-07

    Applicant: Yuval Gronau ,  Edo Likhovski

    Inventor： Yuval Gronau ,  Edo Likhovski

    IPC: G06K9/68

    CPC classification number: G06K9/03 ,  G06K9/685 ,  G06K2209/01

    Abstract: A method for enhancing the accuracy of Optical Character Recognition (OCR) algorithms by detection of differences between a digital image of a document and a text file corresponding to the digital image, created by the OCR algorithm.The method includes calculating the transformation between the first and second digital images such as geometrical distortion, local brightness and contrast differences and blurring due to the optical imaging process. The method estimates the parameters of these transformations so that the transformations can be applied to at least one of the images, rendering it as similar as possible to the other image. The method further compares the two images in order to find differences. The method further displays the differences on a display device and analyzes the differences. The analysis results are fed back to the OCR algorithm.

    Abstract translation: 通过检测由OCR算法创建的文档的数字图像与对应于数字图像的文本文件之间的差异来增强光学字符识别（OCR）算法的精度的方法。 该方法包括计算第一和第二数字图像之间的变换，例如几何失真，局部亮度和对比度差异以及由于光学成像过程引起的模糊。 该方法估计这些变换的参数，使得可以将变换应用于至少一个图像，使其尽可能类似于另一图像。 该方法进一步比较两个图像以便发现差异。 该方法进一步显示显示设备上的差异并分析差异。 分析结果反馈给OCR算法。

Patent Agency Ranking