Dual page mode detection
AssigneeL&H Applications USA, Inc.
InventorStephen R. Baum
Life of this patent
Estimating the term…
Abstract
A method of correcting an image file produced by scanning a document is described. The method includes determining probable regions of text from an image file containing an image of a left page and a right page of a document and determining a page boundary between the regions of text. The method splits the image file about the determined page boundary into two separate image files corresponding to an image of the left hand page and the right hand page. The method can be implemented as a computer program product residing on a computer readable medium for separating an image file containing a pair of pages into separate image files of each page.
Claims38
A method of splittting an image file produced by scanning a document, the method comprises:
- determining probable regions of text from an image file containing an image of a left page and a right page of a document;
- determining a page boundary between the regions of text;
- and
- splitting the image file about the determined page boundary into two separate image files corresponding to an image of the left hand page and the right hand page.
A computer program product residing on a computer readable medium for separating an image file containing a pair of pages into separate image files of each page comprises instructions for causing a computer to:
- determine probable regions of text of an image file;
- determine from the probable regions of text a page boundary between the regions of text;
- and
- split the image file into two separate image files corresponding to an image of the left hand page of the image file and the right hand page of the image file text.
A method of pre-processing an image file for optical character recognition comprises:
- separating the image file containing a pair of pages of the image into two separate files of each page of the image;
- deskewing each of the separated image files;
- and
- applying each of the deskewed image file to an optical character recognition software.
A method of operating a reading system comprises:
- scanning a source document to produce an image file containing an image of a left page and a right page of a document;
- determining probable regions of text of the image file;
- determining from the probable regions of text a page boundary between the regions of text;
- and
- splitting the image file into two separate image files corresponding to an image of the left hand page of the image file and the right hand page of the image file.
A computer program product residing on a computer readable medium for separating an image file containing a pair of pages into separate image files of each page and for synthesizing speech for the separated image files comprises instructions for causing a computer to:
- scan a source document to produce an image file containing an image of a left page and a right page of a document;
- determine probable regions of text of the image file;
- determine from the probable regions of text a page boundary between the regions of text;
- split the image file into two separate image files corresponding to an image of the left hand page of the image file and the right hand page of the image file;
- produce separate OCR files from the image file for the left and right pages;
- synthesize speech for the separate OCR files.
A method of performing optical character recognition on an image file comprised of a left side page and a right side page, the method comprising:
- determining probable regions of text from the image file;
- determining a page boundary between the regions of text;
- splitting the image file about the determined page boundary into two separate image files corresponding to an image of the left hand page and the right hand page;
- converting the two separate image files into two text files corresponding to the left page and the right page.
Dependencies are inferred from the claim text.