利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

33 条记录 (耗时 0.023 秒)

    Segmentation of text, picture and lines of a document image
    2.
    发明授权
    Segmentation of text, picture and lines of a document image 失效
    分割文档，图片和文字图像的行

    公开(公告)号：US5465304A

    公开(公告)日：1995-11-07

    申请号：US230073

    申请日：1994-04-20

    申请人： John F. Cullen ,  Koichi Ejiri

    发明人： John F. Cullen ,  Koichi Ejiri

    IPC分类号： G06K9/20 ,  G06T9/00 ,  G06K9/34

    CPC分类号： G06K9/00456 ,  G06T9/005

    摘要： In a character recognition system, a method and apparatus for segmenting a document image into areas containing text and non-text. Document segmentation in the present invention is comprised generally of the steps of: providing a bit-mapped representation of the document image, extracting run lengths for each scanline from the bit-mapped representation of the document image; constructing rectangles from the run lengths; initially classifying each of the rectangles as either text or non-text; correcting for the skew in the rectangles; merging associated text into one or more text blocks; and logically ordering the text blocks.

    摘要翻译： 在字符识别系统中，用于将文档图像分割成包含文本和非文本的区域的方法和装置。 本发明中的文档分割通常包括以下步骤：提供文档图像的位映射表示，从文档图像的位映射表示中提取每条扫描线的运行长度; 从运行长度构造矩形; 最初将每个矩形分类为文本或非文本; 纠正矩形的偏斜; 将相关文本合并成一个或多个文本块; 并逻辑地排序文本块。

    Skew detection and correction of a document image representation
    3.
    发明授权
    Skew detection and correction of a document image representation 失效
    偏移检测和校正文档图像表示

    公开(公告)号：US5452374A

    公开(公告)日：1995-09-19

    申请号：US863948

    申请日：1992-04-06

    申请人： John F. Cullen ,  Koichi Ejiri

    发明人： John F. Cullen ,  Koichi Ejiri

    IPC分类号： G06K9/20 ,  G06K9/32 ,  G06T7/00 ,  H04N1/04 ,  H04N1/387

    CPC分类号： G06K9/3283 ,  G06K9/00463 ,  G06T7/004 ,  G06K2209/01

    摘要： In a character recognition system, a method and apparatus for correcting the skew of a document image. Skew correction is typically performed during segmentation of the document image into text and non-text parts. Skew correction generally involves skew angle determination and correction of the document image based on the skew angle. A skew angle is determined through the steps of: providing a set of associated rectangles representing the document image, identifying a column edge associated with the set of associated rectangles, comparing rectangles from the set of associated rectangles to identify those that are in the same column and suitably far apart, calculating a tangential angle between the rectangles identified and identifying the most common tangential angle as the skew angle. Once the skew angle is determined, correction of the document image is made by constructing real skewed rectangles from corresponding extracted rectangles and rotating each of the real skewed rectangles around an origin coordinate for a distance based on the skew angle.

    摘要翻译： 一种字符识别系统，用于校正文档图像的偏斜的方法和装置。 通常在将文档图像分割成文本和非文本部分时执行倾斜校正。 偏斜校正通常涉及基于倾斜角的偏斜角确定和文档图像的校正。 通过以下步骤确定偏斜角：提供一组表示文档图像的关联矩形，识别与该组相关矩形相关联的列边缘，比较来自相关矩形集合的矩形以识别位于相同列中的矩形 并且相当远的距离，计算所识别的矩形之间的切线角度，并将最常见的切线角度确定为倾斜角度。 一旦确定了倾斜角度，就通过从对应的提取的矩形构造实际的偏斜矩形来进行文件图像的校正，并且基于偏斜角将围绕原点坐标的每个实际偏斜矩形旋转一段距离。

    Segmentation of text, picture and lines of a document image
    4.
    发明授权
    Segmentation of text, picture and lines of a document image 失效
    分割文档，图片和文字图像的行

    公开(公告)号：US5335290A

    公开(公告)日：1994-08-02

    申请号：US864423

    申请日：1992-04-06

    申请人： John F. Cullen ,  Koichi Ejiri

    发明人： John F. Cullen ,  Koichi Ejiri

    IPC分类号： G06K9/20 ,  G06T9/00 ,  G06K9/34

    CPC分类号： G06K9/00456 ,  G06T9/005

    摘要： In a character recognition system, a method and apparatus for segmenting a document image into areas containing text and non-text. Document segmentation in the present invention is comprised generally of the steps of: providing a bit-mapped representation of the document image, extracting run lengths for each scanline from the bit-mapped representation of the document image; constructing rectangles from the run lengths; initially classifying each of the rectangles as either text or non-text; correcting for the skew in the rectangles; merging associated text into one or more text blocks; and logically ordering the text blocks.

    摘要翻译： 在字符识别系统中，用于将文档图像分割成包含文本和非文本的区域的方法和装置。 本发明中的文档分割通常包括以下步骤：提供文档图像的位映射表示，从文档图像的位映射表示中提取每条扫描线的运行长度; 从运行长度构造矩形; 最初将每个矩形分类为文本或非文本; 纠正矩形的偏斜; 将相关文本合并成一个或多个文本块; 并逻辑地排序文本块。

    Skew detection and correction of a document image representation
    5.
    发明授权
    Skew detection and correction of a document image representation 失效

    公开(公告)号：US5854854A

    公开(公告)日：1998-12-29

    申请号：US937098

    申请日：1997-09-24

    申请人： John F. Cullen ,  Koichi Ejiri

    发明人： John F. Cullen ,  Koichi Ejiri

    IPC分类号： G06K9/20 ,  G06K9/32 ,  G06T7/00 ,  H04N1/04 ,  H04N1/387 ,  G06K9/00

    CPC分类号： G06K9/3283 ,  G06K9/00463 ,  G06T7/004 ,  G06K2209/01

    摘要： In a character recognition system, a method and apparatus for correcting the skew of a document image. Skew correction is typically performed during segmentation of the document image into text and non-text parts. Skew correction generally involves skew angle determination and correction of the document image based on the skew angle. A skew angle is determined through the steps of: providing a set of associated rectangles representing the document image, identifying a column edge associated with the set of associated rectangles, comparing rectangles from the set of associated rectangles to identify those that are in the same column and suitably far apart, calculating a tangential angle between the rectangles identified and identifying the most common tangential angle as the skew angle. Once the skew angle is determined, correction of the document image is made by constructing real skewed rectangles from corresponding extracted rectangles and rotating each of the real skewed rectangles around an origin coordinate for a distance based on the skew angle.

    Method and apparatus for detection of a skew angle of a document image using a regression coefficient
    8.
    发明授权
    Method and apparatus for detection of a skew angle of a document image using a regression coefficient 失效
    使用回归系数检测文档图像的偏斜角的方法和装置

    公开(公告)号：US5563403A

    公开(公告)日：1996-10-08

    申请号：US355902

    申请日：1994-12-14

    申请人： Goroh Bessho ,  Koichi Ejiri

    发明人： Goroh Bessho ,  Koichi Ejiri

    IPC分类号： G06K9/32 ,  G06T7/60 ,  H01J40/14

    CPC分类号： G06K9/3283 ,  G06K2209/01

    摘要： A method and apparatus for detecting the skew angle of a document image. Skew angle determination is performed by the steps of determining a set of sampling points from an input document image and processing X and Y coordinates of the sampling points in order to calculate a regression coefficient of the sampling points. The skew angle of the document is determined using the regression coefficient. To evaluate a calculated skew angle which corresponds to the regression coefficient, a correlation coefficient is calculated and evaluated. As coordinates of sampling points are obtained for a plurality of sets of data corresponding to different ruled lines or lines of characters, a histogram may be used to determine the most probable skew angle.

    摘要翻译： 一种用于检测文档图像的歪斜角度的方法和装置。 通过从输入文档图像确定一组采样点并处理采样点的X和Y坐标以便计算采样点的回归系数的步骤来执行倾斜角确定。 使用回归系数确定文档的歪斜角度。 为了评估与回归系数对应的计算出的偏斜角，计算并评估相关系数。 由于针对对应于不同的格线或字符行的多组数据获得采样点的坐标，因此可以使用直方图来确定最可能的倾斜角。

    Method of assigning direction code to boundary picture element in character recognition system
    9.
    发明授权
    Method of assigning direction code to boundary picture element in character recognition system 失效
    在字符识别系统中向边界图像元素分配方向代码的方法

    公开(公告)号：US4524454A

    公开(公告)日：1985-06-18

    申请号：US417962

    申请日：1982-09-14

    申请人： Koichi Ejiri

    发明人： Koichi Ejiri

    IPC分类号： G06K9/46 ,  G06K9/48 ,  G06T9/20

    CPC分类号： G06K9/481 ,  G06K2209/01

    摘要： A method applicable to a character recognition system is disclosed which assigns direction codes to a number of boundary picture elements contained in a two-level character pattern. The direction of connectivity of a boundary picture element observed is fractionized to minimize the error due to the quantization of the direction. The direction codes are converted into those which correspond to connectivity directions which should be finally grasped. Such direction codes allow strokes to be extracted quite faithfully to the original character pattern.

    摘要翻译： 公开了一种适用于字符识别系统的方法，其将方向代码分配给包含在两级字符图案中的多个边界图像元素。 对观察到的边界像素的连接方向进行分割，以最小化由于方向的量化引起的误差。 方向代码被转换为对应于应该最终掌握的连接方向的方向代码。 这样的方向代码允许相当忠实地提取笔画到原始字符图案。

    SYSTEM AND METHOD FOR DISPLAYING AN IMAGE INDICATING A POSITIONAL RELATION BETWEEN PARTIALLY OVERLAPPING IMAGES
    10.
    发明申请
    SYSTEM AND METHOD FOR DISPLAYING AN IMAGE INDICATING A POSITIONAL RELATION BETWEEN PARTIALLY OVERLAPPING IMAGES 失效
    用于显示表示部分重叠图像之间的位置关系的图像的系统和方法

    公开(公告)号：US20090185054A1

    公开(公告)日：2009-07-23

    申请号：US12413053

    申请日：2009-03-27

    申请人： Koichi Ejiri ,  Shin Aoki ,  Takashi Saitoh ,  Guan Haike ,  Takuji Sakamoto

    发明人： Koichi Ejiri ,  Shin Aoki ,  Takashi Saitoh ,  Guan Haike ,  Takuji Sakamoto

    IPC分类号： H04N5/76

    CPC分类号： H04N5/772 ,  G06T7/223 ,  G06T7/30 ,  G06T7/73 ,  G06T2200/24 ,  G06T2200/32 ,  G06T2207/10016 ,  G06T2207/20021 ,  H04N5/23238 ,  H04N5/23293 ,  H04N5/907

    摘要： A device includes a display monitor configured to display on a screen of the display monitor at least one of a current image and a preceding image taken by an optical unit, a storage unit configured to store the preceding image, and a control unit configured to display a part of the preceding image on the screen when the current image is displayed on the screen, the displayed part of the preceding image indicating a positional relationship between the current image and the preceding image. The current image is taken when the displayed part of the preceding image substantially overlaps a corresponding portion of the current image such that the current image and the preceding image can be processed to form a panoramic image.

    摘要翻译： 一种设备包括显示监视器，被配置为在显示监视器的屏幕上显示由光学单元拍摄的当前图像和先前图像中的至少一个，被配置为存储前一图像的存储单元和被配置为显示的控制单元 在当前图像显示在屏幕上时屏幕上的前一图像的一部分，前一图像的显示部分指示当前图像和前一图像之间的位置关系。 当前一图像的显示部分基本上与当前图像的对应部分重叠时，拍摄当前图像，使得可以处理当前图像和前一图像以形成全景图像。