利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

48 条记录 (耗时 0.042 秒)

    Methods and systems for determining a document region-of-interest in an image
    4.
    发明授权
    Methods and systems for determining a document region-of-interest in an image 有权
    用于确定图像中文档感兴趣区域的方法和系统

    公开(公告)号：US08655071B2

    公开(公告)日：2014-02-18

    申请号：US13034594

    申请日：2011-02-24

    申请人： Ahmet Mufit Ferman ,  Lawrence Shao-hsien Chen

    发明人： Ahmet Mufit Ferman ,  Lawrence Shao-hsien Chen

    IPC分类号： G06K9/34

    CPC分类号： G06K9/3233 ,  G06K2209/01

    摘要： Aspects of the present invention are related to systems and methods for identifying a document region in a non-scanned image. A first candidate document region-of-interest mask may be determined from a luminance-only image by foreground elimination, non-uniformity reduction and thresholding. A second candidate document region-of-interest mask may be formed by subtracting from the first candidate document region-of-interest mask an edge mask resulting from detecting edges in the luminance-only input image. The second candidate document region-of-interest mask may be refined, to form a final document region-of-interest mask, based on text features calculated from the luminance-only input image. The document region-of-interest may be extracted using the final document region-of-interest mask.

    摘要翻译： 本发明的方面涉及用于识别非扫描图像中的文档区域的系统和方法。 可以通过前景消除，不均匀性降低和阈值处理从仅亮度图像确定第一候选文档感兴趣区域掩模。 可以通过从第一候选文档感兴趣区域掩码中减去仅在亮度输入图像中检测边缘产生的边缘掩码来形成第二候选文档感兴趣区域掩模。 可以基于从仅亮度输入图像计算的文本特征来细化第二候选文档感兴趣区域掩模，以形成最终文档感兴趣区域掩模。 可以使用最终文档感兴趣区域掩模来提取文档感兴趣区域。

    Methods and Systems for Determining a Document Region-of-Interest in an Image
    6.
    发明申请
    Methods and Systems for Determining a Document Region-of-Interest in an Image 有权
    确定图像中文档感兴趣区域的方法和系统

    公开(公告)号：US20120219222A1

    公开(公告)日：2012-08-30

    申请号：US13034594

    申请日：2011-02-24

    申请人： Ahmet Mufit Ferman ,  Lawrence Shao-hsien Chien

    发明人： Ahmet Mufit Ferman ,  Lawrence Shao-hsien Chien

    IPC分类号： G06K9/34

    CPC分类号： G06K9/3233 ,  G06K2209/01

    摘要： Aspects of the present invention are related to systems and methods for identifying a document region in a non-scanned image. A first candidate document region-of-interest mask may be determined from a luminance-only image by foreground elimination, non-uniformity reduction and thresholding. A second candidate document region-of-interest mask may be formed by subtracting from the first candidate document region-of-interest mask an edge mask resulting from detecting edges in the luminance-only input image. The second candidate document region-of-interest mask may be refined, to form a final document region-of-interest mask, based on text features calculated from the luminance-only input image. The document region-of-interest may be extracted using the final document region-of-interest mask.

    摘要翻译： 本发明的方面涉及用于识别非扫描图像中的文档区域的系统和方法。 可以通过前景消除，不均匀性降低和阈值处理从仅亮度图像确定第一候选文档感兴趣区域掩模。 可以通过从第一候选文档感兴趣区域掩码中减去仅在亮度输入图像中检测边缘产生的边缘掩码来形成第二候选文档感兴趣区域掩模。 可以基于从仅亮度输入图像计算的文本特征来细化第二候选文档感兴趣区域掩模，以形成最终文档感兴趣区域掩模。 可以使用最终文档感兴趣区域掩模来提取文档感兴趣区域。