IP Library Granted Patent US 8,238,666
Granted Patent B2
US 8,238,666 · App. 11/946,602 · Granted Aug 7, 2012

Recognition of parameterised shapes from document images

Assignee: Canon Kabushiki Kaisha
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 8,238,666
App. No.
11/946,602
Granted
Aug 7, 2012
Kind
B2
Abstract

A method ( 1100 ) of creating a document comprising a modifiable shape, is disclosed. The method analyzes an image to detect at least a graphical object. The method matches the detected graphical object with at least one of a plurality of predetermined modifiable closed-form non-textual template shapes (e.g., 420 ) comprising control parameters for modifying the closed-form non-textual template shape in a non-affine manner. The number of control parameters of the predetermined modifiable closed-form non-textual template shape is less than the number of sections making up the modifiable closed-form non-textual template shape. The method creates a document comprising the at least one modifiable closed-form non-textual template shape.

Claims (39)

1. A method of creating a document comprising a modifiable shape, the method comprising the steps of:

analysing an image to detect at least a graphical object;

matching the detected graphical object with at least one of a plurality of predetermined modifiable closed-form non-textual template shapes, each said predetermined template shape comprising at least one control parameter for modifying the closed-form non-textual template shape in a non-affine manner, wherein the number of control parameters of the predetermined modifiable closed-form non-textual template shape is less than a number of sections making up the modifiable closed-form non-textual template shape; and

creating a document comprising the at least one modifiable closed-form non-textual template shape.

2. The method according to claim 1 , wherein said at least one of the plurality of template shapes is a set of candidate template shapes selected from a set of template shapes.

3. The method according to claim 2 , wherein the candidate template shapes are selected using a machine learning classifier.

4. The method according to claim 1 , the matching step comprises the sub-steps of:

estimating an optimal set of control parameters;

estimating an optimal set of affine parameters based on said graphical object and said estimated control parameters; and

computing a match score between said graphical object and said template shape wherein said template shape uses said estimated affine parameters and said control parameters.

5. The method according to claim 1 , wherein the image is a bitmap image.

6. The method according to claim 1 , further comprising the step of modifying the at least one modifiable closed-form non-textual template shape to match said graphical object.

7. The method according to claim 1 , wherein each of the template shapes comprises at most four control parameters.

8. The method according to claim 1 , wherein each of the template shapes comprises line thickness parameters.

9. The method according to claim 1 , wherein the template shape is one of the Microsoft® AutoShapes.

10. The method as recited in claim 1 , wherein the template shape is one of the template shapes defined by the OpenOffice™ application.

11. The method as recited in claim 1 , wherein the template shape is one of the template shapes defined by the VISIO® application.

12. The method as recited in claim 1 , wherein the template shape is one of the template shapes defined by the SmartDraw® application.

13. The method according to claim 1 , wherein each of the template shapes further comprises affine parameters.

14. The method according to claim 13 , wherein the affine parameters define modifications to the template shape.

15. The method according to claim 14 , wherein the modifications are described by a linear matrix transform.

16. The method according to claim 15 , wherein the modifications include scaling.

17. The method according to claim 15 , wherein the modifications include rotation.

18. The method according to claim 15 , wherein the modifications include offset.

19. The method according to claim 15 , wherein the modifications include skew.

20. An apparatus for creating a document comprising a modifiable shape, the apparatus comprising:

analysing means for analysing an image to detect at least a graphical object;

matching means for matching the detected graphical object with at least one of a plurality of predetermined modifiable closed-form non-textual template shapes, each said predetermined template shape comprising at least one control parameter for modifying the closed-form non-textual template shape in a non-affine manner, wherein the number of control parameters of the at least one modifiable closed-form non-textual template shape is less than a number of sections making up the at least one modifiable closed-form non-textual template shape; and

creation means for creating a document comprising the at least one modifiable closed-form non-textual template shape.

21. A non-transitory computer readable medium, having a program recorded thereon, where the program is configured to make a computer execute a procedure to create a document comprising a modifiable shape, the program comprising:

code for analysing an image to detect at least a graphical object;

code for matching the detected graphical object with at least one of a plurality of predetermined modifiable closed-form non-textual template shape, each said predetermined template shape comprising at least one control parameter for modifying the closed-form non-textual template shape in a non-affine manner, wherein the number of control parameters of the at least one modifiable closed-form non-textual template shape is less than a number of sections making up the at least one modifiable closed-form non-textual template shape; and

code for creating a document comprising the at least one modifiable closed-form non-textual template shape.

22. A system for creating a document comprising a modifiable shape, the system comprising:

a memory for storing data and a computer program;

a processor coupled to said memory for executing said computer program, said computer program comprising instructions for:

analysing an image to detect at least a graphical object;

matching the detected graphical object with at least one of a plurality of predetermined modifiable closed-form non-textual template shapes, each predetermined template shape comprising at least one control parameter for modifying the closed-form non-textual template shape in a non-affine manner, wherein the number of control parameters of the predetermined modifiable closed-form non-textual template shape is less than a number of sections making up the modifiable closed-form nontextual template shape; and

creating a document comprising at least one modifiable closed-form non-textual template shape.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 20, 2008
From: BESLEY, JAMES AUSTIN; CHONG, ERIC WAI-SHING; VAN DOAN, KHANH PHI; IRRGANG, STEVEN RICHARD
To: CANON KABUSHIKI KAISHA
Reel/Frame 020567/0301 →
Priority Claims (1)
AU 2006252025 · Dec 13, 2006 · national
Continuity (1)
Related Publication 20080144942A1 · Jun 19, 2008