公开(公告)号：WO2009137073A1

公开(公告)日：2009-11-12

申请号：PCT/US2009/002830

申请日：2009-05-06

Applicant: COMPULINK MANAGEMENT CENTER, INC. ,  HUNT, Martin ,  PAVLOVSKAIA, Maria ,  GORDON, Logan ,  TIPTON, William ,  PHAM, Trang ,  YONG, Darryl ,  GU, Weiqing ,  EGAN, James ,  WU, Liangnan ,  WONG, Kin-Chung

Inventor： HUNT, Martin ,  PAVLOVSKAIA, Maria ,  GORDON, Logan ,  TIPTON, William ,  PHAM, Trang ,  YONG, Darryl ,  GU, Weiqing ,  EGAN, James ,  WU, Liangnan ,  WONG, Kin-Chung

IPC: G06K9/34

CPC classification number: H04N1/00251 ,  G06K9/3208 ,  G06K9/3283 ,  G06K2209/01 ,  G06T3/0031

Abstract: A process and system to transform a digital photograph of a text document into a scan-quality image is disclosed. By extracting the document text from the image, and analyzing visual clues from the text, a grid is constructed over the image representing the distortions in the image. Transforming the image to straighten this grid removes distortions introduced by the camera image-capture process. Variations in lighting, the extraction of text line information, and the modeling of curved lines in the image may be corrected.

Abstract translation: 公开了将文本文档的数字照片变换为扫描质量图像的处理和系统。 通过从图像中提取文档文本，并从文本中分析视觉线索，在表示图像中的失真的图像上构建网格。 转换图像以校正该网格可消除摄像机图像捕获过程引入的失真。 可以校正照明的变化，文本行信息的提取以及图像中的曲线的建模。

公开(公告)号：WO2009137634A1

公开(公告)日：2009-11-12

申请号：PCT/US2009/043057

申请日：2009-05-07

Applicant: COMPULINK MANAGEMENT CENTER, INC. ,  HUNT, Martin ,  PAVLOVSKAIA, Maria ,  GORDON, Logan ,  TIPTON, William ,  PHAM, Trang ,  YONG, Darryl ,  GU, Weiqing ,  EGAN, James ,  WU, Liangnan ,  WONG, Kin-chung

Inventor： HUNT, Martin ,  PAVLOVSKAIA, Maria ,  GORDON, Logan ,  TIPTON, William ,  PHAM, Trang ,  YONG, Darryl ,  GU, Weiqing ,  EGAN, James ,  WU, Liangnan ,  WONG, Kin-chung

IPC: G06K9/34

CPC classification number: H04N1/00251 ,  G06K9/3208 ,  G06K9/3283 ,  G06K2209/01 ,  G06T3/0031

Abstract: A process and system to transform a digital photograph of a text document into a scan- quality image is disclosed. By extracting the document text from the image, and analyzing visual clues from the text, a grid is constructed over the image representing the distortions in the image. Transforming the image to straighten this grid removes distortions introduced by the camera image-capture process. Variations in lighting, the extraction of text line information, and the modeling of curved lines in the image may be corrected.

Abstract translation: 公开了将文本文档的数字照片变换为扫描质量图像的处理和系统。 通过从图像中提取文档文本，并从文本中分析视觉线索，在表示图像中的失真的图像上构建网格。 转换图像以校正该网格可消除摄像机图像捕获过程引入的失真。 可以校正照明的变化，文本行信息的提取以及图像中的曲线的建模。