Decoding distorted symbols

• US 8,322,620 B2
• Filed: 01/06/2011
• Issued: 12/04/2012
• Est. Priority Date: 12/20/2005
• Status: Active Grant

• Current Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Original Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Inventors: Ye, Xiangyun, Nadabar, Sateesha
• Primary Examiner(s): Haupt, Kristy A
• Application Number:
  US12/985,831
• Publication Number:
  US 20110101101A1
• Time in Patent Office: 698 Days
• Field of Search: 235/462.09, 235/462.1, 382/199, 382/149, 382/218
• US Class Current: 235/462.09
• CPC Class Codes: G06K 7/14 using light without selection of wavelength, e.g. sensing reflected white light G06K7/10831 - G06K7/1097 take precedence
• CPC Class Codes: G06T 3/00 Geometric image transformations in the plane of the image

Abstract

A method is provided for reading distorted optical symbols using known locating and decoding methods, without requiring a separate and elaborate camera calibration procedure, without excessive computational complexity, and without compromised burst noise handling. The invention exploits a distortion-tolerant method for locating and decoding 2D code symbols to provide a correspondence between a set of points in an acquired image and a set of points in the symbol. A coordinate transformation is then constructed using the correspondence, and run-time images are corrected using the coordinate transformation. Each corrected run-time image provides a distortion-free representation of a symbol that can be read by traditional code readers that normally cannot read distorted symbols. The method can handle both optical distortion and printing distortion. The method is applicable to “portable” readers when an incident angle with the surface is maintained, the reader being disposed at any distance from the surface.

Claims

1. A method for decoding distorted symbols, the method comprising acquiring a run-time image of a symbol, the symbol showing distortion in the run-time image;

obtaining a coordinate transformation that describes the distortion shown in the image of the symbol; and

using a processor, where the processor corrects distortion shown in the run-time image using the coordinate transformation so as to provide a corrected image;

running a run-time symbol reader on the corrected image; and

wherein the coordinate transformation is constructed using a correspondence between at least two 2D coordinates of points within a train-time image and two 2D coordinates of points within a 2D code symbol, the correspondence being provided by a symbol reader that can detect and tolerate distortion of the 2D code symbol.

2. The method of claim 1 wherein the run-time symbol reader includes the processor.

3. A method for decoding distorted symbols, the method comprising the steps of:

at train-time;

acquiring a training image of a code symbol disposed on a train-time surface using a camera with an optical axis forming an incident angle with respect to the train-time surface;

running a code symbol reader that can detect and tolerate distortion so as to provide a correspondence between at least two coordinates of points within the training image and at least two coordinates of points within the code symbol;

using the correspondence to construct a coordinate transformation;

at run-time;

acquiring a run-time image of a symbol disposed on a run-time surface using a camera with an optical axis forming substantially the incident angle with respect to the run-time surface;

correcting distortion of the run-time image using the coordinate transformation to provide a corrected representation of the symbol; and

running a run-time symbol reader on the corrected image.

4. The method of claim 3, wherein the code symbol disposed on the train-time surface is of a type that is different from the symbol disposed on the run-time surface.

5. The method of claim 3 wherein the code symbol disposed on the train-time surface is a stacked code symbol.

6. The method of claim 3 wherein the code symbol disposed on the train-time surface is a linear bar code symbol.

7. The method of claim 3 wherein the code symbol disposed on the train-time surface is a text block.

8. The method of claim 3, wherein the corrected representation of the symbol is a corrected image of the symbol.

9. The method of claim 3 wherein the coordinate points in the train-time image and in the run-time image are 2D coordinate points.

10. The method of claim 3, wherein the train-time surface includes a non-planar surface.

11. A method for decoding distorted symbols, the method comprising the steps of:

at train-time;

acquiring a train-time image of a code symbol disposed on a train-time surface;

generating a coordinate transformation that describes distortion shown in the train-time image;

at run-time;

acquiring a run-time image of a symbol, the symbol showing distortion in the run-time image;

correcting distortion shown in the run-time image using the coordinate transformation so as to provide a corrected representation of the symbol; and

running a run-time symbol reader on the corrected image.

12. The method of claim 11, wherein the step of generating a coordinate transformation is constructed using a correspondence between at least two coordinates of points within a train-time image and two coordinates of points within a code symbol, the correspondence being provided by a symbol reader that can detect and tolerate distortion of the code symbol.

13. The method of claim 11, wherein the distortion includes at least one of an optical distortion and a printing distortion.

14. The method of claim 11, wherein the code symbol is a two-dimensional (2D) code symbol.

15. The method of claim 11, wherein the train-time image is acquired using a camera having an optical axis that forms an incident angle with respect to the train-time surface and wherein the run-time image is acquired using a camera having an optical axis that forms substantially the incident angle with respect to the train-time surface.

16. An apparatus for decoding distorted symbols, the apparatus comprising:

at least a first processor programmed to perform the steps of, at train-time;

acquiring a training image of a code symbol disposed on a train-time surface using a camera with an optical axis having an incident angle with respect to the train-time surface;

identifying a correspondence between at least two coordinates of points within the training image and at least two coordinates of points within the code symbol;

using the correspondence to construct a coordinate transformation;

at run-time;

acquiring a run-time image of a symbol disposed on a run-time surface using a camera with an optical axis having substantially the incident angle with respect to the run-time surface;

correcting distortion of the run-time image using the coordinate transformation to provide a corrected representation of the symbol; and

running a run-time symbol reader on the corrected image.

17. The apparatus of claim 16, wherein the code symbol disposed on the train-time surface is of a type that is different from the symbol disposed on the run-time surface.

18. An apparatus for decoding distorted symbols, the apparatus comprising:

at least a first processor programmed to perform the steps of,

at train-time;

acquiring a train-time image of a code symbol disposed on a train-time surface;

generating a coordinate transformation that describes distortion shown in the train-time image;

at run-time;

acquiring a run-time image of a symbol, the symbol showing distortion in the run-time image;

correcting distortion shown in the run-time image using the coordinate transformation so as to provide a corrected representation of the symbol; and

running a run-time symbol reader on the corrected image.

19. The apparatus of claim 18, wherein the processor generates a coordinate transformation by using a correspondence between at least two coordinates of points within a train-time image and two coordinates of points within a code symbol, the correspondence being provided by a symbol reader that can detect and tolerate distortion of the code symbol.

20. The apparatus of claim 18, wherein the train-time image is acquired using a camera having an optical axis that forms an incident angle with respect to the train-time surface and wherein the run-time image is acquired using a camera having an optical axis that forms substantially the incident angle with respect to the train-time surface.

21. The apparatus of claim 18, wherein the corrected representation of the symbol is a corrected image of the symbol.

22. The apparatus of claim 18, wherein the corrected representation of the symbol is a corrected feature of the symbol.

23. The apparatus of claim 18, wherein the code symbol disposed on the train-time surface is of a type that is different from the symbol disposed on the run-time surface.