System and method for identifying objects of interest in image data

• US 7,496,218 B2
• Filed: 05/25/2005
• Issued: 02/24/2009
• Est. Priority Date: 05/26/2004
• Status: Expired due to Fees

• Current Assignee: Applied Visual Sciences, Inc.
• Original Assignee: Guardian Technologies LLC (Lasko Holdings, Inc.)
• Inventors: Ramsay, Thomas E., Ramsay, Eugene B., Hamilton, Victor, Richard, Martin, Felteau, Gerard
• Primary Examiner(s): Carter; Aaron W
• Application Number:
  US11/136,406
• Publication Number:
  US 20060013463A1
• Time in Patent Office: 1,371 Days
• Field of Search: 382128-134, 382/173, 382/282, 378/44, 378/57, 378/62, 378/87, 378/163
• US Class Current: 382/128
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

A system and method for identifying objects of interest in image data is provided. The present invention utilizes principles of dynamic discontinuity in which objects in images, when subjected to special transformations, will exhibit radically different responses based on the chemical properties of the imaged objects. Using the system and methods of the present invention, certain objects that appear indistinguishable from other objects to the eye or computer recognition systems, or are otherwise statistically identical, generate radically different and statistically significant differences that can be easily measured.

Claims

1. A method of identifying a threat object of interest in X-ray image data, wherein the image data comprises a plurality of grey-scale or color pixel values, comprising:

receiving the X-ray image data; and

applying at least one predetermined bifurcation transform to the X-ray image data to effect divergence of the threat object of interest from other objects, wherein said at least one predetermined bifurcation transform is determined by applying at least one initial bifurcation transform to X-ray image data containing a known threat object that is substantially similar to said threat object of interest, and adjusting said at least one initial bifurcation transform so that the known threat object diverges from other objects in the X-ray image data once said predetermined bifurcation transform is applied to said X-ray image data.

2. The method of claim 1, wherein the at least one predetermined bifurcation transform comprises a series of predetermined bifurcation transforms.

3. The method of claim 1, wherein the at least one predetermined bifurcation transform comprises at least one point operation.

4. The method of claim 3, wherein the at least one point operation is at least partially a non-linear point operation.

5. The method of claim 3, wherein the at least one point operation comprises at least one nodal point.

6. The method of claim 5, wherein the at least one nodal point is adjusted so as to effect the divergence of the threat object of interest from other objects.

7. The method of claim 1, wherein the at least one predetermined bifurcation transform is adapted to maintain an integrity of the threat object of interest during divergence of the threat object of interest from other objects.

8. The method of claim 1, further comprising generating a threat output image based on the results of the at least one predetermined bifurcation transform.

9. The method of claim 8, wherein the threat object of interest is distinguished from other objects in the output image by adjusting a visual parameter of the threat object of interest and other objects based on the results of the at least one predetermined bifurcation transform.

10. The method of claim 1, wherein the X-ray image data comprises nonparametric image data.

11. The method of claim 1, wherein the X-ray image data comprises parametric image data.

12. The method of claim 1, wherein the threat object of interest is statistically indistinguishable from other objects in the X-ray image data.

13. The method of claim 1, wherein the threat object of interest comprises a plurality of types of threat objects, wherein each type of threat object comprises at least one member.

14. The method of claim 13, wherein the at least one predetermined bifurcation transform is generated for each member of the threat objects.

15. The method of claim 13, wherein the type of threat objects include explosives, weapons, restricted items, biological agent or materials, or chemical materials.

16. The method of claim 1, wherein the X-ray image data is scanner data.

17. The method of claim 1, wherein the X-ray image data includes a portion of an interior of a container.

18. The method of claim 17, wherein the container includes baggage, clothing or a person.

19. The method of claim 1, wherein the X-ray data comprises results from dual energy X-rays, at least one X-ray source or multiple scans of an input object.

20. An apparatus configured to identify a threat object of interest in X-ray image data wherein the image data comprises a plurality of grey-scale or color pixel values, comprising:

an input device configured to receive the X-ray image data; and

an image transformation recognition system configured to apply at least one predetermined bifurcation transform to the X-ray image data to effect divergence of the threat object of interest from other objects, wherein said at least one predetermined bifurcation transform is determined by applying at least one initial bifurcation transform to X-ray image data containing a known threat object that is substantially similar to said threat object of interest, and adjusting said at least one initial bifurcation transform so that the known threat object diverges from other objects in the X-ray image data once said predetermined bifurcation transform is applied to said X-ray image data.

21. A method of creating a bifurcation transform for a class of threat objects, comprising:

selecting a point operation;

performing said point operation on a subset of images, wherein said subset of images includes at least one image comprising a plurality of grey-scale or color pixels and containing an object in said class of threat objects; and

adjusting said point operation and repeating said selecting and said performing step until said point operation bifurcates said object.

22. The method of claim 21, wherein said point operation bifurcates said object by increasing differentials in response characteristics among objects in said class of threat objects relative to other objects in said subset of images.

23. The method of claim 21, wherein said class of threat objects comprises a plurality of types of threat objects, wherein each type of threat object comprises at least one member.