Stationary tomographic X-ray imaging systems for automatically sorting objects based on generated tomographic images

Patent metadata

Field	Value
Publication number	US-10976271-B2
Application number	US-202016997309-A
Country	US
Kind code	B2
Filing date	Aug 19, 2020
Priority date	Dec 16, 2005
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

An X-ray imaging inspection system for inspecting items comprises an X-ray source 10 extending around an imaging volume 16, and defining a plurality of source points 14 from which X-rays can be directed through the imaging volume. An X-ray detector array 12 also extends around the imaging volume 16 and is arranged to detect X-rays from the source points which have passed through the imaging volume, and to produce output signals dependent on the detected X-rays. A conveyor 20 is arranged to convey the items through the imaging volume 16.

First claim

I claim:

1. An X-ray imaging system for scanning an object, the system comprising:
stationary X-ray sources configured at least partially around an imaging volume;
detectors configured at least partially around the imaging volume, wherein the detectors are configured to detect X-rays emitted from the stationary X-ray sources and are configured to generate X-ray image data;
at least one processor configured to execute programmatic instructions that, when executed, receive the X-ray image data and generate at least a tomographic image from the X-ray image data, wherein the at least one processor is further configured to execute the programmatic instructions to:
determine a plurality of parameters from the X-ray image data;
apply one or more decision trees to the determined plurality of parameters to generate an output;
construct information based on the output;
determine if the information is indicative of a threat;
allocate the object to a category indicative of safety based on a probability of the threat being present; and
cause the object to be automatically sorted based on the category.

2. The X-ray imaging system of claim 1 , wherein the information comprises an extent of volume contiguity.

3. The X-ray imaging system of claim 1 , wherein the plurality of parameters comprise at least one of a constant gray level of the X-ray image data or a texture of the X-ray image data.

4. The X-ray imaging system of claim 1 , wherein the X-ray image data comprises data representative of two-dimensional images and wherein the plurality of parameters are determined from at least one of the two-dimensional images and the tomographic image.

5. The X-ray imaging system of claim 1 , wherein the plurality of parameters comprise more than one parameter and wherein the at least one processor is configured to execute the programmatic instructions that, when executed, determine, from the X-ray image data, each of the more than one parameter in parallel.

6. The X-ray imaging system of claim 1 , wherein the at least one processor is configured to execute the programmatic instructions that, when executed, cause the object to be automatically sorted into at least one of clear or not clear based on the category.

7. The X-ray imaging system of claim 1 , wherein each of the detectors is positioned in two or more detector arrays and wherein each of the two or more detector arrays is configured in a form of a linear array of detectors.

8. The X-ray imaging system of claim 1 , wherein the at least one processor is configured to execute the programmatic instructions that, when executed, identify one or more separate regions within the tomographic image by calculating a mean X-ray intensity of a set of pixels within the tomographic image, determining a standard deviation of X-ray intensities of the set of pixels, determining an X-ray intensity of a pixel proximate to the set of pixels, and adding the pixel to the set of pixels to form a region if the X-ray intensity of the pixel is within the standard deviation.

9. The X-ray imaging system of claim 1 , wherein the at least one processor is configured to execute the programmatic instructions that, when executed, identify one or more separate regions within the tomographic image by calculating a mean X-ray intensity of a set of pixels within the tomographic image, determining an X-ray intensity of a pixel adjacent to the set of pixels, comparing the X-ray intensity of the pixel to the mean X-ray intensity of the set of pixels, and adding the pixel to the set of pixels to form a region based on said comparing.

10. The X-ray imaging system of claim 1 , wherein the at least one processor is configured to execute the programmatic instructions that, when executed, identify a region of the tomographic image by defining an initial area of the region, identifying a pixel outside the initial area, determining a first value associated with the pixel, determining a corresponding second value of the initial area, comparing the first value and second value, and if a predetermined relationship is found between the first value and second value, including the pixel in the region.

11. The X-ray imaging system of claim 10 , wherein the first value and second value are X-ray intensity values.

12. The X-ray imaging system of claim 10 , wherein the predetermined relationship comprises an X-ray intensity of the pixel being within a predetermined range of an average X-ray intensity of the initial area.

13. The X-ray imaging system of claim 1 , wherein the at least one processor is configured to execute the programmatic instructions that, when executed, identify one or more separate regions within the tomographic image by using a statistical edge detection method.

14. The X-ray imaging system of claim 1 , wherein extracting a plurality of parameters from the X-ray tomographic image data comprises measuring a variance of a pixel intensity within one or more regions of the X-ray tomographic image data.

Assignees

• Rapiscan Systems Inc

Inventors

• Morton Edward James

Classifications

• G01V5/20

  Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects · CPC title

• G01T1/2985 Primary

  In depth localisation, e.g. using positron emitters; Tomographic imaging (longitudinal and transverse section imaging; apparatus for radiation diagnosis sequentially in different planes, steroscopic radiation diagnosis); (using external radiation sources A61B6/02) · CPC title

• G01V5/00

  Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity · CPC title

• G01N2223/421

  digitised image, analysed in real time (recognition algorithms) · CPC title

• G01N2223/3307

  source and detector fixed; object moves · CPC title