公开(公告)号：US20060140504A1

公开(公告)日：2006-06-29

申请号：US11359096

申请日：2006-02-22

申请人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

IPC分类号： G06K9/40

CPC分类号： G06T5/006 ,  G06T3/0031 ,  G06T3/608 ,  H04N1/387

摘要： A projection set of geodesic lines which are parallel with each other on a curved surface of a paper face is extracted from an image in which a paper face has been imaged by an image-pickup device, using the paper face contents as a clue; and also a projection set of ruling lines which form a ruled surface corresponding to the curved surface of the paper face is extracted from the projection set of geodesic lines. Then, the curved surface of the paper face is estimated from the projection set of the geodesic lines and ruling lines, and distortion of the image is corrected based on this curved surface of the paper face. If this is done, correspondence with various types of diverse distortions becomes possible, and distortion correction can be performed even when only one part of the paper face appears in the image.

摘要翻译： 使用纸面内容作为线索，从通过图像拾取装置成像的纸面的图像中提取在纸面的弯曲表面上彼此平行的测地线的投影集; 并且从测地线的投影组中提取形成对应于纸面的弯曲表面的刻线表面的投影线的投影组。 然后，从测地线和划线的投影组估计纸面的弯曲表面，并且基于纸面的弯曲表面校正图像的变形。 如果这样做，就可以进行与各种各样的变形的对应关系，并且即使只有一部分纸面出现在图像中，也可以执行失真校正。

公开(公告)号：US07471848B2

公开(公告)日：2008-12-30

申请号：US11359096

申请日：2006-02-22

申请人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

IPC分类号： G06K9/40

CPC分类号： G06T5/006 ,  G06T3/0031 ,  G06T3/608 ,  H04N1/387

摘要： A projection set of geodesic lines which are parallel with each other on a curved surface of a paper face is extracted from an image in which a paper face has been imaged by an image-pickup device, using the paper face contents as a clue; and also a projection set of ruling lines which form a ruled surface corresponding to the curved surface of the paper face is extracted from the projection set of geodesic lines. Then, the curved surface of the paper face is estimated from the projection set of the geodesic lines and ruling lines, and distortion of the image is corrected based on this curved surface of the paper face. If this is done, correspondence with various types of diverse distortions becomes possible, and distortion correction can be performed even when only one part of the paper face appears in the image.

摘要翻译： 使用纸面内容作为线索，从通过图像拾取装置成像的纸面的图像中提取在纸面的弯曲表面上彼此平行的测地线的投影集; 并且从测地线的投影组中提取形成对应于纸面的弯曲表面的刻线表面的投影线的投影组。 然后，从测地线和划线的投影组估计纸面的弯曲表面，并且基于纸面的弯曲表面校正图像的变形。 如果这样做，就可以进行与各种各样的变形的对应关系，并且即使只有一部分纸面出现在图像中，也可以执行失真校正。

公开(公告)号：US07903874B2

公开(公告)日：2011-03-08

申请号：US11894188

申请日：2007-08-20

申请人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

IPC分类号： G06K9/34

CPC分类号： G06K9/2027 ,  G06K9/2036 ,  G06K9/3283

摘要： A set of straight lines that associate a top parallel geodesic projection positioned at an upper end with a bottom parallel geodesic projection positioned at a lower end, among sets of parallel geodesic projections, is extracted as a set of ruled-line candidate projections as a search target of a set of ruled line projections. A deviation of neighborhood, which is a distance between a cross ratio vector of the ruled-line candidate projection and a cross ratio vector of a neighboring line obtained by shifting the ruled-line candidate projection by a predetermined interval, is calculated for each ruled-line candidate projection. A set of straight lines having the smallest sum total of deviations of neighborhood, in the set of straight lines, which do not intersect with each other, among the sets of ruled-line projection candidates is extracted as a set of ruled line projections by continuous dynamic programming.

摘要翻译： 将位于上端的顶部平行测地线突起与位于下方的平行测地线投影的底部平行测地线投影相关联的一组直线作为一组划线候选投影提取为搜索 一套规则线的预测目标。 对于每个被划线的候选投影，通过将划线候选投影移动预定间隔而获得的相邻行的交叉比矢量之间的距离为邻域的偏差， 线候选投影。 一组直线投影候选之间的直线投影的组合，在一组直线上彼此不相交的相邻偏差的总和最小的一组直线被提取为一组连续的线条投影 动态规划。

公开(公告)号：US20080112619A1

公开(公告)日：2008-05-15

申请号：US11894188

申请日：2007-08-20

申请人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Misako Suwa ,  Hiroaki Takebe ,  Satoshi Naoi

IPC分类号： G06K9/34

CPC分类号： G06K9/2027 ,  G06K9/2036 ,  G06K9/3283

摘要： A set of straight lines that associate a top parallel geodesic projection positioned at an upper end with a bottom parallel geodesic projection positioned at a lower end, among sets of parallel geodesic projections, is extracted as a set of ruled-line candidate projections as a search target of a set of ruled line projections. A deviation of neighborhood, which is a distance between a cross ratio vector of the ruled-line candidate projection and a cross ratio vector of a neighboring line obtained by shifting the ruled-line candidate projection by a predetermined interval, is calculated for each ruled-line candidate projection. A set of straight lines having the smallest sum total of deviations of neighborhood, in the set of straight lines, which do not intersect with each other, among the sets of ruled-line projection candidates is extracted as a set of ruled line projections by continuous dynamic programming.

摘要翻译： 将位于上端的顶部平行测地线突起与位于下方的平行测地线投影的底部平行测地线投影相关联的一组直线作为一组划线候选投影提取为搜索 一套规则线的预测目标。 对于每个被划线的候选投影，通过将划线候选投影移动预定间隔而获得的相邻行的交叉比矢量之间的距离为邻域的偏差， 线候选投影。 一组直线投影候选之间的直线投影的组合，在一组直线上彼此不相交的相邻偏差的总和最小的一组直线被提取为一组连续的线条投影 动态规划。

公开(公告)号：US20090016608A1

公开(公告)日：2009-01-15

申请号：US12168370

申请日：2008-07-07

申请人： Katsuhito Fujimoto ,  Misako Suwa ,  Satoshi Naoi

发明人： Katsuhito Fujimoto ,  Misako Suwa ,  Satoshi Naoi

IPC分类号： G06K9/00

CPC分类号： G06K9/6205 ,  G06K9/00463

摘要： According to an aspect of an embodiment, a method of character recognition out of an image having a frame and a plurality of characters in an area, comprises the steps of: dividing the area into a plurality of partial areas having a plurality of partial images, respectively; providing a template image having a reference frame image; calculating differences between the partial images and the reference frame image of the template image, respectively; calculating misalignment of the image from the template image based on the average of the differences of the partial images and the reference frame image; and recognizing the characters out of the image upon correction of the misalignment.

摘要翻译： 根据实施例的一个方面，一种在区域中具有帧和多个字符的图像中的字符识别方法包括以下步骤：将该区域划分为具有多个部分图像的多个部分区域， 分别; 提供具有参考帧图像的模板图像; 分别计算模板图像的部分图像和参考帧图像之间的差异; 基于所述部分图像和所述参考帧图像的差的平均值计算所述图像与所述模板图像的未对准; 并且在校正不对准时识别图像中的字符。

公开(公告)号：US07280693B2

公开(公告)日：2007-10-09

申请号：US10602624

申请日：2003-06-25

申请人： Koji Kurokawa ,  Katsuhito Fujimoto ,  Misako Suwa ,  Yoshinobu Hotta ,  Satoshi Naoi

发明人： Koji Kurokawa ,  Katsuhito Fujimoto ,  Misako Suwa ,  Yoshinobu Hotta ,  Satoshi Naoi

IPC分类号： G06K9/00

CPC分类号： G06F3/0486 ,  G06K9/2054 ,  G06K2209/01

摘要： A document information input apparatus detects a position and an attribute of an area of a real document to be input designated by a user with high accuracy. Based on the detected position and attribute, the document information input apparatus recognizes an image of the area as text information by performing recognition processes suitable for the detected attribute such as character recognition, table recognition and a figure process. Then, the document information input apparatus pastes the resulting information to a pertinent position of an electronic document on a display. As a result, it is possible to input information such as a character sequence, a table and a figure from a real document to an electronic document at high speed and with high accuracy.

摘要翻译： 文件信息输入装置以高精度检测要由用户指定的真实文件的区域的位置和属性。 基于检测到的位置和属性，文档信息输入装置通过执行诸如字符识别，表识别和图形处理的检测属性的识别处理，将该区域的图像识别为文本信息。 然后，文件信息输入装置将所得到的信息粘贴到显示器上的电子文档的相关位置。 结果，可以高速且高精度地将诸如字符序列，表格和图形的信息从真实文档输入到电子文档。

公开(公告)号：US07136526B2

公开(公告)日：2006-11-14

申请号：US10020249

申请日：2001-12-18

申请人： Yoshinobu Hotta ,  Katsuhito Fujimoto ,  Satoshi Naoi ,  Misako Suwa

发明人： Yoshinobu Hotta ,  Katsuhito Fujimoto ,  Satoshi Naoi ,  Misako Suwa

IPC分类号： G06K9/00 ,  G06K9/18

CPC分类号： G06K9/2054 ,  G06K2209/01

摘要： A key word is first and automatically extracted from a character string group to be recognized, and entered. Then, a character is recognized by segmenting an individual character from a character string image to be recognized, and a character string corresponding to the extracted/entered key word id extracted. Then, a word area delimited by a key word is extracted from the character string image, and a word is recognized. Furthermore, a word recognition result is verified, and a final character string recognition result is output.

公开(公告)号：US20090208107A1

公开(公告)日：2009-08-20

申请号：US12371822

申请日：2009-02-16

申请人： Misako Suwa ,  Katsuhito Fujimoto

发明人： Misako Suwa ,  Katsuhito Fujimoto

IPC分类号： G06K9/00

CPC分类号： G06K9/344 ,  G06K2209/01

摘要： A character recognition apparatus includes a division mechanism for dividing a diagram into a plurality of parts, a candidate character string acquisition mechanism for combining the plurality of parts of the diagram, and a character string selection mechanism for selecting one character string. The candidate character string acquisition mechanism includes at least one of first mechanism for duplicating a character line that touches adjacent characters and then including a duplicated character line as an element of a candidate character string, and second mechanism for including a candidate character string in which the touching character line between the adjacent characters has been removed, and a candidate character string in which the touching character line is contained, in the plurality of candidate character strings.

摘要翻译： 字符识别装置包括用于将图分解为多个部分的分割机构，用于组合图的多个部分的候选字符串获取机构和用于选择一个字符串的字符串选择机构。 候选字符串获取机构包括用于复制接触相邻字符的字符行然后包括作为候选字符串的元素的复制字符行的第一机制中的至少一个，以及用于包括候选字符串的第二机制， 在多个候选字符串中已经去除了相邻字符之间的触摸字符行和包含触摸字符行的候选字符串。

公开(公告)号：US20080175483A1

公开(公告)日：2008-07-24

申请号：US12004798

申请日：2007-12-21

申请人： Misako Suwa ,  Katsuhito Fujimoto

发明人： Misako Suwa ,  Katsuhito Fujimoto

IPC分类号： G06K9/46

CPC分类号： G06K9/346 ,  G06K2209/01

摘要： When an operator starts a pattern separation extraction tool, an input screen is displayed on the display device. The operator can choose and designate any one of document image data within the storage device through the input screen. The document image that is chosen by the operator is displayed on the display device. The operator can choose and designate a color sample by a drag operation on the document image that is displayed on the display device. If the operator inputs the designation to finish the designation of a color sample through the input device after designating some color samples, the pattern separating extraction device generates and outputs the image data that consists of one print pattern for each of the print patterns included in the document image chosen by the operator.

摘要翻译： 当操作者启动图案分离提取工具时，在显示装置上显示输入画面。 操作员可以通过输入画面选择和指定存储设备内的任何一个文档图像数据。 由操作员选择的文档图像显示在显示设备上。 操作者可以通过在显示装置上显示的文档图像上的拖动操作来选择和指定颜色样本。 如果在指定了一些颜色样本之后，操作者通过输入装置输入完成指定颜色样本的指定，则图案分离提取装置产生并输出包括在每个打印图案中的每个印刷图案的一个打印图案的图像数据 由操作员选择的文档图像。

公开(公告)号：US06850645B2

公开(公告)日：2005-02-01

申请号：US10000525

申请日：2001-12-04

申请人： Satoshi Naoi ,  Misako Suwa ,  Yoshinobu Hotta

发明人： Satoshi Naoi ,  Misako Suwa ,  Yoshinobu Hotta

IPC分类号： G06K9/20 ,  G06K9/68 ,  G06K9/46

CPC分类号： G06K9/00463 ,  G06K9/6807

摘要： A pattern recognizing apparatus having a character extractor that extracts a character from an input image, a non-character extractor that extracts a non-character from an input image, a character recognizer that recognizes a character, a non-character recognizer that recognizes a non-character and an environment recognizer that instructs the character recognizer to perform a recognition process when the character extractor extracts a character, and that instructs the non-character recognizer to perform a recognition process when the non-character recognizer extracts a non-character.

摘要翻译： 具有从输入图像提取字符的字符提取器的图案识别装置，从输入图像提取非字符的非字符提取器，识别字符的字符识别器，识别非字符的非字符识别器， 字符和环境识别器，当字符提取器提取字符时，指示字符识别器执行识别处理，并且当非字符识别器提取非字符时，指示非字符识别器执行识别处理。