IP Library Granted Patent US 9,305,344
Granted Patent B2
US 9,305,344 · App. 14/258,432 · Granted Apr 5, 2016

Method for improving linear feature detectability in digital images

Inventors: Gary E. Georgeson (Tacoma, WA); Morteza Safai (Newcastle, WA); William T. Edwards (Wentzville, MO); Matthew T. Grimshaw (Seattle, WA); James E. Engel (Huntington Beach, CA); Yuan-Jye Wu (Issaquah, WA)
Assignee: The Boeing Company
G06T7/0004G06T7/001G06T2207/10012G06T2207/10116G06T2207/20224G06T2207/30164
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 9,305,344
App. No.
14/258,432
Granted
Apr 5, 2016
Kind
B2
Abstract

The present disclosure is generally directed to of method linear feature detection in a structure by providing a first digital image of the structure, creating a second corresponding digital image of the structure from the first digital image and determining a direction to shift pixels of the second corresponding digital image. A pixel shift value may be input to shift pixels of the second corresponding digital image, and pixels of the second corresponding digital image are shifted by the input pixel shift value in the determined direction. A third corresponding digital image of the structure may be calculated by subtracting the second corresponding digital image of the structure from the first digital image of the structure.

Claims (47)

1. A method of linear feature detection in a structure comprising:

providing a first digital image of a structure;

providing a second corresponding digital image of the structure from the first digital image;

shifting the second digital image by at least 1 pixel in a direction substantially perpendicular to a linear feature; and

determining a third corresponding digital image of the structure by subtracting the second corresponding digital image of the structure from the first digital image of the structure.

2. The method of linear feature detection according to claim 1 , where the third corresponding digital image being capable of graphically enhancing a linear feature on the structure imaged in the first digital image by increasing a signal-to-noise pixel ratio of the imaged linear feature on the structure in the first digital image.

3. The method of linear feature detection according to claim 1 , wherein the first digital image of the structure includes one of:

an X-ray backscatter image; or

a three-dimensional image.

4. The method of linear feature detection according to claim 1 , wherein determining the direction to shift pixels of the second corresponding image comprises selecting an angle perpendicular to a direction of a linear feature in the structure.

5. The method of linear feature detection according to claim 1 , wherein determining the direction to shift pixels of the second corresponding image comprises an iterative process of determining, by the computing device, an angle of a linear feature in the structure and selecting a direction perpendicular to the angle of the linear feature in the structure.

6. The method of linear feature detection according to claim 1 , wherein inputting the pixel shift value to shift pixels of the second corresponding digital image includes inputting a shift value between 1 to 5 pixels.

7. The method of linear feature detection according to claim 1 , further comprising:

inputting a new incremented pixel shift value to shift pixels of the third corresponding digital image;

shifting, by the computing device, pixels of the third corresponding digital image by the input new incremented pixel shift value in the determined direction; and

providing, by the computing device, a fourth corresponding digital image of the structure by subtracting the third corresponding digital image of the structure from the first digital image of the structure, where the fourth corresponding digital image capable of further graphically enhancing a linear feature on the structure imaged in the first digital image.

8. A system, comprising:

one or more computer processors; and

a memory containing computer program code that, when executed by the one or more computer processors, performs an operation for linear feature detection in a structure, the operation comprising:

providing a first digital image of a structure;

providing a second corresponding digital image of the structure from the first digital image;

shifting the second digital image by at least 1 pixel in a direction substantially perpendicular to a linear feature; and

determining a third corresponding digital image of the structure by subtracting the second corresponding digital image of the structure from the first digital image of the structure.

9. The system of claim 8 , where the third corresponding digital image being capable of graphically enhancing a linear feature on the structure imaged in the first digital image by increasing a signal-to-noise pixel ratio of the imaged linear feature on the structure in the first digital image.

10. The system of claim 8 , wherein the first digital image of the structure includes one of:

an X-ray backscatter image; or

a three-dimensional image.

11. The system of claim 8 , wherein determining the direction to shift pixels of the second corresponding image comprises selecting an angle perpendicular to a direction of a linear feature in the structure.

12. The system of claim 8 , wherein determining the direction to shift pixels of the second corresponding image comprises an iterative process of determining, by the computing device, an angle of a linear feature in the structure and selecting a direction perpendicular to the angle of the linear feature in the structure.

13. The system of claim 8 , wherein inputting the pixel shift value to shift pixels of the second corresponding digital image includes inputting a shift value between 1 to 5 pixels.

14. The system of claim 8 , the operation further comprising:

inputting a new incremented pixel shift value to shift pixels of the third corresponding digital image;

shifting, by the computing device, pixels of the third corresponding digital image by the input new incremented pixel shift value in the determined direction; and

providing, by the computing device, a fourth corresponding digital image of the structure by subtracting the third corresponding digital image of the structure from the first digital image of the structure, where the fourth corresponding digital image capable of further graphically enhancing a linear feature on the structure imaged in the first digital image.

15. A non-transitory computer-readable medium containing computer program code that, when executed by operation of one or more computer processors, performs an operation for linear feature detection in a structure, the operation comprising:

providing a first digital image of a structure;

providing a second corresponding digital image of the structure from the first digital image;

shifting the second digital image by at least 1 pixel in a direction substantially perpendicular to a linear feature; and

determining a third corresponding digital image of the structure by subtracting the second corresponding digital image of the structure from the first digital image of the structure.

16. The non-transitory computer-readable medium of claim 15 , where the third corresponding digital image being capable of graphically enhancing a linear feature on the structure imaged in the first digital image by increasing a signal-to-noise pixel ratio of the imaged linear feature on the structure in the first digital image.

17. The non-transitory computer-readable medium of claim 15 , wherein determining the direction to shift pixels of the second corresponding image comprises selecting an angle perpendicular to a direction of a linear feature in the structure.

18. The non-transitory computer-readable medium of claim 15 , wherein determining the direction to shift pixels of the second corresponding image comprises an iterative process of determining, by the computing device, an angle of a linear feature in the structure and selecting a direction perpendicular to the angle of the linear feature in the structure.

19. The non-transitory computer-readable medium of claim 15 , wherein inputting the pixel shift value to shift pixels of the second corresponding digital image includes inputting a shift value between 1 to 5 pixels.

20. The non-transitory computer-readable medium of claim 15 , the operation further comprising:

inputting a new incremented pixel shift value to shift pixels of the third corresponding digital image;

shifting, by the computing device, pixels of the third corresponding digital image by the input new incremented pixel shift value in the determined direction; and

providing, by the computing device, a fourth corresponding digital image of the structure by subtracting the third corresponding digital image of the structure from the first digital image of the structure, where the fourth corresponding digital image capable of further graphically enhancing a linear feature on the structure imaged in the first digital image.

Assignments (2)
CONFIRMATORY LICENSE Recorded Oct 20, 2017
From: BOEING
To: NAVY, DEPARTMENT OF THE
Reel/Frame 044347/0275 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 22, 2014
From: GEORGESON, GARY E.; SAFAI, MORTEZA; EDWARDS, WILLIAM T.; GRIMSHAW, MATTHEW T.; ENGEL, JAMES E.; WU, YUAN-JYE
To: THE BOEING COMPANY
Reel/Frame 032728/0040 →
Continuity (1)
Related Publication 20150302572A1 · Oct 22, 2015