Image processing method and apparatus
    1.
    发明授权
    Image processing method and apparatus 失效
    图像处理方法和装置

    公开(公告)号:US6104832A

    公开(公告)日:2000-08-15

    申请号:US574598

    申请日:1995-12-18

    IPC分类号: G06K9/20 G06T5/00 G06K9/34

    摘要: An image processing apparatus includes an image input unit which inputs an image, and an image thinner for taking the OR of (m dots in the vertical direction).times.(n dots in the horizontal direction) of the input image, thereby thinning out the (m.times.n) pixels and newly forming one pixel. A labeler adds labels to black pixels of every line of the thinned out image. The same label is added to pixels which are continuous in the vertical, horizontal or oblique direction and simultaneously traces a rectangle. A separator detector distinguishes a rectangle corresponding to a sentence portion, a rectangle corresponding to a figure or photograph, a rectangle corresponding to a table, and a rectangle corresponding to a separator, by using a width, a height, an area, and a pixel density (the number of pixels in the area) of the rectangle added to the label by the labeler. The area of the input image is divided based on the result of the detection of the separator detector.

    摘要翻译: 图像处理装置包括输入图像的图像输入单元和用于取得输入图像的x(n个水平方向的)的(或垂直方向的m个)的或更薄的图像的图像,从而使( mxn)像素并且新形成一个像素。 标签器为稀疏图像的每一行的黑色像素添加标签。 相同的标签被添加到在垂直,水平或倾斜方向上连续的像素,并且同时追踪矩形。 分离器检测器通过使用宽度,高度,面积和像素来区分对应于句子部分的矩形,对应于图形或照片的矩形,与表对应的矩形和对应于分隔符的矩形 由贴标机添加到标签的矩形的密度(区域中的像素数)。 基于分离器检测器的检测结果对输入图像的区域进行分割。

    Image processing method and apparatus
    2.
    发明授权
    Image processing method and apparatus 失效
    图像处理方法和装置

    公开(公告)号:US06385338B1

    公开(公告)日:2002-05-07

    申请号:US09606171

    申请日:2000-06-29

    IPC分类号: G06K934

    摘要: An image processing apparatus comprises: an image input unit to input an image; an image thinner for getting the OR of (m dots in the vertical direction)×(n dots in the horizontal direction) for the input image from the image input unit, thereby thinning out the (m×n) pixels and newly forming one pixel; a labeler for adding labels every line to black pixels of the image which was thinned out by the image thinner and adding the same label to the pixels which are continuous in the vertical, horizontal, or oblique direction and simultaneously tracing a rectangle; and a separator detector for distinguishing a rectangle corresponding to a sentence portion, a rectangle corresponding to a figure or photograph, a rectangle corresponding to a table, a rectangle corresponding to a separator, and the like by using a width, a height, an area, and a pixel density (the number of pixels to the area) of the rectangle added with the label by the labeler. On the basis of the result of the detection of the separator detector, the area of the input image is divided.

    摘要翻译: 一种图像处理装置包括:图像输入单元,用于输入图像; 对于来自图像输入单元的输入图像,获得(垂直方向上的m个点)的x(水平方向的n个点)的或更薄的图像,从而使(m×n)个像素变薄并重新形成一个像素; 每一行的标签添加到由图像稀疏的图像的黑色像素中并将相同的标签添加到在垂直,水平或倾斜方向上连续的像素并同时追踪矩形的标签; 以及分离器检测器,用于区分与句子部分相对应的矩形,对应于图形或照片的矩形,对应于表的矩形,对应于分隔符的矩形等,通过使用宽度,高度,面积 ,以及标签器附加有标签的矩形的像素密度(面积的像素数)。 基于分离器检测器的检测结果,输入图像的面积被分割。

    Image processing method and apparatus
    3.
    发明授权
    Image processing method and apparatus 失效
    图像处理方法和装置

    公开(公告)号:US5754689A

    公开(公告)日:1998-05-19

    申请号:US250941

    申请日:1994-05-31

    申请人: Tohru Niki

    发明人: Tohru Niki

    IPC分类号: G06K9/46 G06K9/48

    CPC分类号: G06K9/46 G06K2209/01

    摘要: There is provided an image processing method whereby a slope at a first position on an outline of character data in input image data is extracted and phase data at a second position on a background of the character data is also extracted. The second position exists in the normal direction of the slope at the first position and is away from the first position by a predetermined distance. The phase data is based on states of black pixels in a plurality of predetermined directions at a target point. The predetermined distance depends on the size of character data.

    摘要翻译: 提供一种图像处理方法,其中提取输入图像数据中的字符数据的轮廓上的第一位置处的斜率,并且还提取字符数据的背景上的第二位置处的相位数据。 第二位置在第一位置处的斜面的法线方向上存在,并且离开第一位置预定的距离。 相位数据基于目标点处的多个预定方向上的黑色像素的状态。 预定距离取决于字符数据的大小。