Model-Based Dewarping Method And Apparatus

• US 20100239165A1
• Filed: 03/02/2007
• Published: 09/23/2010
• Est. Priority Date: 03/02/2006
• Status: Active Grant

• Current Assignee: Compulink Management Center Incorporated
• Original Assignee: Compulink Management Center Incorporated
• Inventors: Fu, Bin, Feng, Bin, Heaney, Edward P. JR., Chan, Karl M., Li, Wenxin, Wu, Minghui, Li, Rongfeng, Rapelje, Kurt A.
• Granted Patent: US 8,406,476 B2
• Time in Patent Office: Days
• US Class Current: 382/176
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 3/06 Topological mapping of higher dimensional structures onto lower dimensional surfaces
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 5/80 Geometric correction
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
• CPC Class Codes: G06V 30/1478 of characters or characters lines
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: H04N 1/387 Composing, repositioning or otherwise geometrically modifying originals

Abstract

An apparatus and method for processing a captured image and, more particularly, for processing a captured image comprising a document. In one embodiment, an apparatus comprising a camera to capture documents is described. In another embodiment, a method for processing a captured image that includes a document comprises the steps of distinguishing an imaged document from its background, adjusting the captured image to reduce distortions created from use of a camera and properly orienting the document is described.

Claims

1. A method for processing a captured image that comprises an imaged document;

said method comprising;

detecting graphical information in the captured image relating to the transition between said imaged document and the remainder of said captured image;

selecting one or more lines from said graphical information corresponding to edges of said imaged document;

calculating corners of said imaged document based on intersection of one or more lines corresponding to edges of said imaged document;

isolating said imaged document from background of said captured image based on one or more lines corresponding to edges of said imaged document;

setting a curved coordinate net on said imaged document;

stretching said curved coordinate net to a rectangle coordinate net;

adjusting said rectangle coordinate net to a well-proportional rectangle coordinate net.

2. The method recited in claim 1, further comprising the steps of:

mapping coordinates of pixels of said imaged document to coordinates corresponding to a non-distorted perspective of said imaged document based on said computed deviation.

3. The method recited in claim 2, further comprising the steps of:

rotating said non-distorted imaged document according to said determination of format of said non-distorted imaged document.

4. A system for processing a captured image, said captured image comprising an imaged document, said system comprising:

means for selecting one or more lines from said graphical information corresponding to edges of said imaged document;

means for calculating corners of said imaged document based on intersection of one or more lines corresponding to edges of said imaged document;

means for isolating said imaged document from background of said captured image based on one or more lines corresponding to edges of said imaged document;

means for setting a curved coordinate net on said imaged document;

means for stretching said curved coordinate net to a rectangle coordinate net; and

means for adjusting said rectangle coordinate net to a well-proportional rectangle coordinate net.

5. A computer readable medium for processing captured image, the computer readable medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause the one or more processors to perform the computer-implemented steps of:

detecting graphical information in the captured image relating to the transition between said imaged document and the remainder of said captured image;

selecting one or more lines from said graphical information corresponding to edges of said imaged document;

calculating corners of said imaged document based on intersection of one or more lines corresponding to edges of said imaged document;

isolating said imaged document from background of said captured image based on one or more lines corresponding to edges of said imaged document;

setting a curved coordinate net on said imaged document;

stretching said curved coordinate net to a rectangle coordinate net;

adjusting said rectangle coordinate net to a well-proportional rectangle coordinate net.

resampling pixels of said imaged document based on said computed deviations;

6. The method recited in claim 5, further comprising the steps of:

mapping coordinates of pixels of said imaged document to coordinates corresponding to a non-distorted perspective of said imaged document based on said computed deviation.

7. The method recited in claim 6, further comprising the steps of:

rotating said non-distorted imaged document according to said determination of format of said non-distorted imaged document.

8. A method for processing a captured image that comprises an imaged document;

said method comprising;

separating text areas from the remainder of said captured image;

enhancing the direction of text lines in said text areas;

extracting said text lines;

selecting a polynomial function to fit said text lines.

9. The method recited in claim 8, wherein said enhancing step further comprising the steps of:

detecting distance between said text lines;

compressing said captured image under a compression rate;

computing direction for each pixel in said text lines;

eliminating gaps between characters so that characters in the same text line connect together, but characters not in the same text line are separated.

10. The method recited in claim 9, wherein the direction for each pixel in said text of lines is determined using a plurality of 9×

9 directional templates, where each template comprises a black block in the center representing the pixel and eight gray block blocks that extend from the black block that describe a direction of the pixel, and the gray level values are summed for each of the plurality of directional templates to determine the direction of the pixel.