METHOD OF PROCESSING AN OBJECT-BASED IMAGE FILE WITH CONTENT TYPE DEPENDENT IMAGE PROCESSING ALGORITHMS
    1.
    发明申请
    METHOD OF PROCESSING AN OBJECT-BASED IMAGE FILE WITH CONTENT TYPE DEPENDENT IMAGE PROCESSING ALGORITHMS 审中-公开
    使用内容类型依赖图像处理算法处理基于对象的图像文件的方法

    公开(公告)号:US20120159292A1

    公开(公告)日:2012-06-21

    申请号:US13311229

    申请日:2011-12-05

    IPC分类号: G06F17/00

    CPC分类号: G06T11/60 G06T2207/30176

    摘要: 1. A method of processing an object-based image file with content type dependent image processing algorithms, comprising the steps of: rasterizing the image, segmenting the rasterized image into segments that are distinguished by pre-defined content types, deriving, from the image file, a display list with objects to be included in the image, associating each object with one of the segments on the basis of a spatial relationship between the object and the segments, selecting, for each object, an image processing algorithm based on the content type of the associated segment, and processing each object with the selected algorithm.

    摘要翻译: 1.一种利用内容类型相关图像处理算法处理基于对象的图像文件的方法,包括以下步骤:光栅化图像,将光栅化图像分割成由预定义内容类型区分的片段,从图像中导出 文件,具有要包括在图像中的对象的显示列表,基于对象和片段之间的空间关系将每个对象与其中一个片段相关联,为每个对象选择基于内容的图像处理算法 相关联的段的类型,并使用所选择的算法处理每个对象。

    AUTOMATIC TABLE LOCATION IN DOCUMENTS
    6.
    发明申请
    AUTOMATIC TABLE LOCATION IN DOCUMENTS 有权
    文件中的自动表位置

    公开(公告)号:US20120177290A1

    公开(公告)日:2012-07-12

    申请号:US13359989

    申请日:2012-01-27

    IPC分类号: G06K9/34

    CPC分类号: G06K9/00449

    摘要: A method for locating tables in documents includes defining a plurality of tiles for a document, for each tile, determining a horizontal profile and a vertical profile, determining the location of lines by means of gradients of the horizontal profiles and the vertical profiles, selecting from the lines, the lines that are persistent, determining a rectangle in at least one corner of the document based on the persistent lines, and applying heuristics in order to accept or reject a determined rectangle as a table of the document. An apparatus for automatically locating a table in a document applies the method for locating tables in documents.

    摘要翻译: 用于在文档中定位表的方法包括为每个瓦片定义用于文档的多个瓦片,确定水平轮廓和垂直轮廓,通过水平轮廓和垂直轮廓的梯度来确定线的位置,从 行,持久行,基于持久行确定文档的至少一个角落中的矩形,以及应用启发式以接受或拒绝作为文档的表的确定的矩形。 用于在文档中自动定位表的装置应用用于在文档中定位表的方法。

    Automatic table location in documents
    8.
    发明授权
    Automatic table location in documents 有权
    文件自动表位置

    公开(公告)号:US08463040B2

    公开(公告)日:2013-06-11

    申请号:US13359989

    申请日:2012-01-27

    IPC分类号: G06K9/36

    CPC分类号: G06K9/00449

    摘要: A method for locating tables in documents includes defining a plurality of tiles for a document, for each tile, determining a horizontal profile and a vertical profile, determining the location of lines by means of gradients of the horizontal profiles and the vertical profiles, selecting from the lines, the lines that are persistent, determining a rectangle in at least one corner of the document based on the persistent lines, and applying heuristics in order to accept or reject a determined rectangle as a table of the document. An apparatus for automatically locating a table in a document applies the method for locating tables in documents.

    摘要翻译: 用于在文档中定位表的方法包括为每个瓦片定义用于文档的多个瓦片,确定水平轮廓和垂直轮廓,通过水平轮廓和垂直轮廓的梯度来确定线的位置,从 行,持久行,基于持久行确定文档的至少一个角落中的矩形,以及应用启发式以接受或拒绝作为文档的表的确定的矩形。 用于在文档中自动定位表的装置应用用于在文档中定位表的方法。

    Method for generating print data and a color printer system
    9.
    发明授权
    Method for generating print data and a color printer system 有权
    用于生成打印数据的方法和彩色打印机系统

    公开(公告)号:US08411323B2

    公开(公告)日:2013-04-02

    申请号:US13480654

    申请日:2012-05-25

    IPC分类号: G06K15/00 H04N1/60

    CPC分类号: H04N1/6072 H04N1/52

    摘要: A method for generating print data for digital color images uses a division of the images in windows. Each window is characterized as belonging to a predefined class, based on values of pixels in corresponding windows in at least two sub-images that are derived from the color image by a series of image processing steps. These sub-images are, e.g. a gradient sub-image in which the value of every pixel indicates the difference of that pixel with its local neighborhood and a non-uniformity sub-image in which each pixel determined to be comprised in a uniform area is provided with a predetermined value. The percentage of windows belonging to a class is calculated and compared to threshold values to identify an image type. This image type is used to select a conversion method to convert the color image into print data for printing on the printer system.

    摘要翻译: 用于产生数字彩色图像的打印数据的方法使用窗口中的图像的划分。 基于通过一系列图像处理步骤从彩色图像导出的至少两个子图像中的相应窗口中的像素的值,将每个窗口表征为属于预定义类别。 这些子图像是例如。 梯度子图像,其中每个像素的值指示该像素与其局部邻域的差异以及其中确定包含在均匀区域中的每个像素被提供有预定值的不均匀性子图像。 计算属于类的窗口的百分比,并将其与阈值进行比较以识别图像类型。 该图像类型用于选择将彩色图像转换为打印数据以在打印机系统上进行打印的转换方法。