Feature recognition using loose gray scale template matching

• US 20030161534A1
• Filed: 12/26/2000
• Published: 08/28/2003
• Est. Priority Date: 02/17/2000
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Handley, John C., Loce, Robert P., Cuciurean-Zapan, Clara
• Granted Patent: US 6,807,304 B2
• Time in Patent Office: Days
• US Class Current: 382/209
• CPC Class Codes: G06V 10/36 Applying a local operator, i.e. means to operate on image points situated in the vicinity of a given point; Non-linear local filtering operations, e.g. median filtering
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: H04N 1/40075 Descreening, i.e. converting a halftone signal into a corresponding continuous-tone signal; Rescreening, i.e. combined descreening and halftoning

Abstract

What is presented is a method for feature recognition using loose-gray-scale template matching including at least an initial point for locating within the received image a plurality of pixel points in gray-scale surrounding an initial point. The method has the steps of first locating the initial point and the plurality of pixel points to define feature boundaries and then generating a looseness interval about the located initial point with template information being associated therewith. The next step involves determining which one of a plurality of templates for fitting fits within a threshold looseness interval, and then outputting a signal associated with that recognized feature.

Claims

1. A method for feature recognition using loose-gray-scale template matching including at least an initial point for locating within the received image a plurality of pixel points in gray-scale surrounding said initial point, said method comprising the steps of:

locating said initial point and said plurality of pixel points to define feature boundaries;

generating a looseness interval about said located initial point with template information associated therewith;

determining which one of a plurality of templates for fitting fits within a threshold looseness interval; and

outputting a signal associated with said recognized feature.

2. A method as in claim 1 further comprising the step of normalizing said feature boundaries to M×

N.

3. A method as in claim 1 wherein a recognized feature is one of:

serifs, corners, vertical strokes, horizontal strokes, diagonal strokes, glyphs, platen cover marks, ink traps, paper edges, registration marks, binding holes and marks, or presence of adjacent color edges.

4. A method as in claim 1 wherein said outputted signal associated with the said recognized feature is used in subsequent processing to perform recognition of a larger global feature such as financial or secure documents, bonds, stamps, or passports.

5. A method as in claim 1 wherein the output signal associated with the recognized feature is used in subsequent processing to enhance the appearance of the feature.

6. A method as in claim 5 wherein said wherein said enhancement is performed by increasing the contrast of a fine feature.

7. A method as in claim 5 wherein said wherein said enhancement darkens or widens the feature.

8. A method as in claim 5 wherein said wherein said enhancement lightens or thins the feature.

9. A method as in claim 1 wherein said outputted signal associated with said recognized feature is used in subsequent processing to achieve image restoration.

10. A method as in claim 9 wherein said image restoration is achieved by using the output signals to suppress noise in the image.

11. A method as in claim 9 wherein said restoration darkens or widens the feature.

12. A method as in claim 9 wherein said restoration lightens or thins the feature.

13. A method as in claim 1 wherein said step of matching is performed using image data from multiple color planes.

14. A method as in claim 13 wherein said matched feature is the presence of adjacent colored edged.

15. A method as in claim 14 wherein said outputted signal modifies the feature to perform a trapping operation.