METHOD AND APPARATUS FOR DETERMININGOFFSETS OF A PART FROM A DIGITAL IMAGE

• US 20060056732A1
• Filed: 08/26/2005
• Published: 03/16/2006
• Est. Priority Date: 08/28/2004
• Status: Active Grant

• Current Assignee: David Holmes
• Original Assignee: David Holmes
• Inventors: Holmes, David
• Granted Patent: US 7,522,163 B2
• Time in Patent Office: Days
• US Class Current: 382/286
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/0006 using a design-rule based approach
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/33 using feature-based methods

Abstract

A method for image recognition of a material object that utilizes graphical modeling of the corner points of a vertex which includes projecting a point on a digital display to an inward depth, a one half pixel distance in the plane of the display, with a conic to a digital display, and a square block containing one half size child blocks that are scaled to depth, projecting the corner points of a vertex and replacing the bisecting points of edge features detected in a digital display scaled at an increasing rate of congruency to the dimensions of an object. The method may further include producing a digital image of the material object, providing a central processing unit, providing memory associated with a central processing unit; providing a display associated with a central processing unit; loading the digital image into the memory; defining the edges of features within the digital image; and a finding fight crucial points from registrations projected on to an edge feature display.

Claims

1. A method for image recognition of a material object that utilizes graphical modeling of the corner points of a vertex which comprises:

projecting a point on a digital display to an inward depth, a ½

pixel distance in the plane of the display, with a conic to a digital display, and a square block containing ½

size child blocks that are scaled to depth;

projecting the corner points of a vertex; and

replacing the bisecting points of edge features detected in a digital display scaled at an increasing rate of congruency to the dimensions of an object.

2. The method as described in claim 1 further including:

producing a digital image of the material object;

providing a central processing unit;

providing memory associated with the central processing unit;

providing a display associated with the central processing unit;

loading the digital image into the memory;

defining the edges of features within the digital image; and

defining fiducial points from registrations projected onto an edge feature display.

3. The method as described in claim 2 further including:

overlaying perpendicular axes to a line through a pair of fiducial points; and

setting projection points on the intersection points of the perpendiculars and edge feature intersections.

4. The method as described in claim 3 further including:

separating the relative offset of the overlaid edges into levels of deviation;

calculating the arc quadric angular offset from the base case conic arc data and projecting this data onto a display screen;

calculating a cubic in screen depth offset from the combined offset of two database conic arc data; and

producing a two-dimensional offset of a pair of image features perpendicular to intersection points on an edge feature.

5. The method as described in claim 4 further including:

calculating the offset of the projected features of the half edge decomposition directions of symmetry;

locating the position of the normal distribution of the perspective distortion on the image edge features;

removing the perspective distortion offset and increasing the incline deviation about the symmetry of the normal distribution;

sorting maximum deviations and highlighting least deviations; and

using the position and orientation of the detected edge features to identify the primitive on a display.

6. The method as described in claim 5 further including:

determining projection repeatable pattern of block edge features with detected edge feature blocks;

comparing database primitive blocks to the pattern of this image edge feature or block to provide an affine transformation;

expanding the node space and child elements holding primitives hidden feature contained in child elements as increments of primitive patterns to common based parent;

defining block convergence holding coordinate axes and align orientation that fits within the surrounding volume context of the base case primitive blocks; and

separating nodes of primitives into composite volumes.

7. The method as described in claim 6 further including:

reducing the complexity of primitives with respect to existing base case linear depth;

scaling block to one half increment of features and dividing the blocks in half in a hiearchy of features projected on centroids of comparator features;

detecting multiply connected regions from the overlay node connectivity producing corner vertex points of hidden features;

translating comparator blocks to positions relative to volumes;

converging block centroids to outer triangles; and

qualifying the translation on two-dimensional block topology.

8. The method as described in claim 7 further including:

grid surface edge features;

calculating the right angle line of sight on triangle axis; and

qualifying the inward projection.

9. A method as described in claim 1 further including:

manually adjusting fiducial points utilizing an interactive computer display.

10. A method as described in claim 1 further including:

setting projection points on the intersection points of the perpendiculars and edge feature intersections; and

setting to local Cartesian coordinate axes at both intersection points.

11. A method as described in claim 1 further including:

using the position and orientation of the detected edge features to identify the primitive on a display.

16. A method as described in claim 1 further including:

manually selecting the midpoints of a detected edge.

12. A method for measuring the dimensions of a material object by graphical modeling of the corner points of a vertex which comprises:

providing an electronic computer, the electronic computer including a memory having stored therein instructions and data for performing steps (a)-(b);

performing the steps (a)-(b) by means of executing the instructions and data within the computer;

(a) projecting a point on a digital display to an inward depth, a ½

pixel distance in the plane of the display, with a conic to a digital display, and a square block containing ½

size child blocks that are scaled to depth and

(b) projecting the corner points of a vertex to be coincident with the bisecting points of edge features detected in a digital display scaled at an increasing rate of congruency to the dimensions of an object.

13. A method as described in claim 12, wherein the memory further includes instructions and data for performing steps (c)-(g) in the computer system:

(c) producing a digital image of the material object;

(d) providing a display associated with the central processing unit;

(e) loading the digital image into the memory;

(f) defining the edges of features within the digital image; and

(g) defining fiducial points from registrations projected onto an edge feature display.

14. A method as described in claim 12 wherein the memory further includes instructions and data for performing steps (h)-(j) in the computer system:

(h) overlaying a perpendicular axes to a line through a pair of fiducial points;

(i) setting projection points on the intersection points of the perpendiculars and edge feature intersections; and

(j) separating the relative offset of the overlaid edges into levels of deviation.

15. A method as described in claim 12 wherein the memory further includes instructions and data for performing steps (k)-(q) in the computer system:

(k) calculating the arc quadric angular offset from the base case conic arc data and projecting this data onto a display screen;

(l) calculating a cubic in and out screen depth offset from the combined offset of two database conic arc data;

(m) producing a two-dimensional symmetric offset of a pair of image features perpendicular to intersection points on an edge feature;

(n) calculating the offset of the projected features of the half edge decomposition directions of symmetry;

(o) locating the position of the normal distribution of the perspective distortion on the image edge features;

(p) removing the perspective distortion and increasing the incline deviation about the symmetry of the normal distribution;

(q) sorting maximum deviations and highlighting least deviations; and

using the position and orientation of the detected edge features to identify a primitive on a display.

17. An article of manufacture comprising:

a computer useable medium having a computer readable code means embodied in said medium for image recognition of a material object, the computer readable program code in said article of manufacture comprising;

computer readable program code for causing the computer to project a point on a digital display to an inward depth, a ½

pixel distance in the plane of the display, with a conic to a digital display, and a square block containing ½

size child blocks that are scaled to depth;

computer readable program code for causing the computer to project the corner points of a vertex; and

computer readable program code for causing the computer to replace bisecting points of edge features detected in a digital display scaled at an increasing rate of congruency to the dimensions of an object.

18. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for image recognition of a material object that utilizes graphical modeling of the corner points of a vertex, said method steps comprising:

projecting a point on a digital display to an inward depth, a ½

pixel distance in the plane of the display, with a conic to a digital display, and a square block containing ½

size child blocks that are scaled to depth;

projecting the corner points of a vertex; and

replacing the bisecting points of edge features detected in a digital display scaled at an increasing rate of congruency to the dimensions of an object.

19. A method for constructing a replica of a material object utilizing the following method steps:

projecting a point on a digital display to an inward depth, a one half pixel distance in the plane of the display, with a conic to a digital display, and a square block containing 2'"'"'s child blocks that are scaled to depth;

projecting the corner points of a vertex; and

replacing the bisecting points of age features detected in a digital display scaled at an increasing rate of congruency to the dimensions of an object.