Method and apparatus for detection of parallel edges in image processing

• US 5,142,592 A
• Filed: 12/17/1990
• Issued: 08/25/1992
• Est. Priority Date: 12/17/1990
• Status: Expired due to Fees

• Current Assignee: Keith E. Moler
• Original Assignee: Keith E. Moler
• Inventors: Moler, Keith E.
• Primary Examiner(s): Boudreau, Leo H.
• Assistant Examiner(s): Stellrecht, Barry
• Application Number:
  US07/629,259
• Time in Patent Office: 617 Days
• Field of Search: 382/22, 382/25
• US Class Current: 382/200
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06V 10/20 Image preprocessing

Abstract

A method and apparatus for detection of parallel edges in image processing systems is shown. A video source producing an image which is operated upon by Laplacian of Gaussian operator to produce an LOG image within which sign changes are detected to produce a zero crossing edge detected image. A vector gradient field of the LOG image is computed and subjected to a gradient field smoothing operation to produce a smoothed gradient field. The smoothed gradient field is examined to detect scaler minima within the field and the results thereof used to compute parallelism strength in accordance with preestablished criteria to generate a parallelism line image which is printed using a conventional printer.

Claims

1. For use in detecting parallel and near parallel edges in an image, parallel edge detection means comprising:

edge detection means for detecting the edges within the image corresponding to image contrast changes and for producing an edge detected image;

edge gradient means for constructing a gradient vector field for the edge detected image;

gradient field smoothing means for smoothing the gradient vector field to a smoothed gradient vector field;

minima detection means for detecting the magnitude minima within the smoothed gradient vector field; and

parallelism strength means for determining parallelism strength of the smoothed vector field and for producing a parallelism line image.

2. Parallel edge detection means as set forth in claim 1 wherein said edge detection means include:

LOG means convolving the image using a Laplacian of Gaussian edge detection operator; and

sign detection means operative upon the convolved image to detect sign changes and establish an image edge coinciding with detected sign changes.

3. Parallel edge detection means as set forth in claim 2 wherein said edge gradient means determine the gradient at each pixel along the detected edge of the established image edges as

4. Parallel edge detection means as set forth in claim 3 wherein said gradient field smoothing means convolve the vector gradient field in accordance with a two dimensional Gaussian function.

5. Parallel edge detection means as set forth in claim 4 wherein the two dimensional Gaussian function is ##EQU5## wherein r represents radius, and σ

represents the standard deviation of the Gaussian function and e represents 2.718.

6. Parallel edge detection means as set forth in claim 5 wherein said minima detection means include:

means for determining the second derivative of the smoothed gradient field in X and Y directions;

means for establishing a direction for local minima corresponding to the most positive second derivative; and

means for examining the smoothed gradient field for local minima in the selected direction.

7. Parallel edge detection means as set forth in claim 6 wherein said parallelism strength means employ a first criteria to determine parallelism strength responsive to the magnitude of the smoothed gradient field and a second criteria determined as ##EQU6## wherein i and j are the point coordinates and V is the magnitude of the smoothed gradient vector field.

8. Parallel edge detection means as set forth in claim 1 further including:

divergence means operative upon said smoothed gradient field for producing joint detection indicia at points of an image corresponding to curve maxima, stroke ends, corners and intersections.

9. Parallel edge detection means as set forth in claim 8 wherein the joint indicia are used to resolve and interpret image elements.

10. For use in detecting parallel and near parallel edges in an image, parallel edge detection means comprising:

edge detection means for detecting the edges within the image corresponding to image contrast changes and for producing an edge detected image;

edge gradient means for producing a gradient vector field for the edge detected image;

gradient field smoothing means for smoothing the gradient vector field to a smoothed gradient vector field;

minima detection means for detecting the magnitude minima within the smoothed gradient vector field; and

divergence means operative upon said smoothed gradient field for producing joint detection indicia.

11. Parallel edge detection means as set forth in claim 10 wherein said joint detection indicia are produced at image points corresponding to curve maxima, stroke ends, corners and intersections.

12. Parallel edge detection means as set forth in claim 11 wherein the joint indicia are used to resolve and interpret image elements.