IP Library Granted Patent US 8,244,062
Granted Patent B2
US 8,244,062 · App. 12/234,719 · Granted Aug 14, 2012

Correction of distortion in captured images

Assignee: Hewlett-Packard Development Company, L.P.
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,244,062
App. No.
12/234,719
Granted
Aug 14, 2012
Kind
B2
Abstract

An image processing method comprises analyzing an image of a portion of text, and detecting the inter-line spacing and the inter-word spacing across the area of the image. Based on the inter-line and inter-word spacings, a quadrilateral shape is derived which represents the deformation of the text image from an undistorted image. The image is modified to perform perspective correction based on the derived quadrilateral.

Claims (21)

1. An image processing method comprising:

analyzing, by an image processing apparatus, an image of a portion of text having at least one line;

detecting, by the image processing apparatus, inter-line spacing and inter-word spacing across an area of the image;

based on the detected inter-line spacing and the inter-word spacing, deriving a quadrilateral shape, the quadrilateral shape representing a deformation of the image from an undistorted image; and

modifying, by the image processing apparatus, the image to perform perspective correction based on the derived quadrilateral shape.

2. A method as claimed in claim 1 , further comprising, before detecting the inter-line and inter-word spacing, performing an image rotation for skew correction.

3. A method as claimed in claim 1 , wherein detecting inter-line spacing comprises determining a number of lines and detecting a start and end locations of the lines along a vertical direction of the image.

4. A method as claimed in claim 3 , wherein detecting inter-line spacing comprises using a horizontal projection profile analysis.

5. A method as claimed in claim 1 , wherein detecting inter-word spacing comprises detecting text and non-text areas in each line and determining word boundaries.

6. A method as claimed in claim 5 , wherein detecting inter-word spacing comprises using a vertical projection profile analysis.

7. A method as claimed in claim 1 , wherein deriving a quadrilateral shape comprises defining quadrilateral sides using a best fit approach to a set of inter-word spacing values.

8. A method as claimed in claim 1 , further comprising performing character recognition on the modified image.

9. A non-transitory computer readable medium comprising computer program code that when executed by a computer, causes the computer to:

analyze an image of a portion of text having at least one line;

detect inter-line spacing and inter-word spacing across an area of the image;

derive a quadrilateral shape based on the inter-line spacing and the inter-word spacing, the quadrilateral shape representing a deformation of the image from an undistorted image; and

modify the image to perform perspective correction based on the derived quadrilateral Shape.

10. An image processing apparatus comprising:

means for analyzing an image of a portion of text, the image defining an area, and detecting inter-line spacing and inter-word spacing across the area of the image;

means for deriving a quadrilateral shape, the quadrilateral shape representing a deformation of the image from an undistorted image based on the inter-line spacing and the inter-word spacing; and

means for modifying the image to perform perspective correction based on the derived quadrilateral shape.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 11, 2012
From: PRASENJIT, DEY; SALARPURIA, ANBUMANI
To: HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.
Reel/Frame 028531/0887 →
Priority Claims (1)
IN 2388/CHE/2007 · Oct 22, 2007 · national
Continuity (1)
Related Publication 20090103808A1 · Apr 23, 2009