Search

KR-102961278-B1 - DUAL ENERGY TYPE X-RAY INSPECTION SYSTEM, METHOD AND APPARATUS FOR PROVIDING IMAGE CLASSIFICATION OF DUAL ENERGY TYPE X-RAY INSPECTION SYSTEM, METHOD OF LEARNING ARTIFICIAL NEURAL NETWORK FOR IMAGE CLASSIFICATION

KR102961278B1KR 102961278 B1KR102961278 B1KR 102961278B1KR-102961278-B1

Abstract

The present invention relates to a dual-energy X-ray inspection system and may include: an X-ray generator that generates and radiates a first X-ray and a second X-ray having different output intensities; an X-ray detector that detects the first X-ray and the second X-ray after they have been transmitted through an object and are attenuated, and converts the attenuated first X-ray and the attenuated second X-ray into electrical signals to generate a first X-ray detection signal and a second X-ray detection signal, respectively; and an image classification device that converts the first X-ray detection signal and the second X-ray detection signal into a first image and a second image, respectively, generates a material classification map of the object from the first image and the second image, classifies categories of the object by material characteristics based on the material classification map, and determines a specific category item in the categories by material characteristics.

Inventors

  • 임동악
  • 장성은
  • 이진로

Assignees

  • (주) 본테크

Dates

Publication Date
20260507
Application Date
20250825

Claims (10)

  1. An X-ray generator that generates and radiates first X-rays and second X-rays having different output intensities; An X-ray detector that detects the attenuated first X-ray and the attenuated second X-ray after the first X-ray and the second X-ray are transmitted through an object, respectively, and converts the attenuated first X-ray and the attenuated second X-ray into electrical signals to generate a first X-ray detection signal and a second X-ray detection signal, respectively; and An image classification device comprising: converting the first X-ray detection signal and the second X-ray detection signal into a first image and a second image, respectively; generating a material classification map of the object from the first image and the second image; classifying categories of the object by material characteristics based on the material classification map; and determining a specific category item in the categories by material characteristics. The image classification device separates an object region and a background region in the first image and the second image, sets the background region as a reference value for estimating the incident intensity of X-rays, calculates the relative attenuation coefficient ratio and transmission ratio of the object region based on the reference value, and generates the material classification map by mapping the attenuation coefficient ratio and the transmission ratio. Dual-energy X-ray inspection system.
  2. delete
  3. In Article 1, The above image classification device classifies the categories based on the material characteristics into organic matter, inorganic matter, metallic matter, other matter, and unknown matter. Dual-energy X-ray inspection system.
  4. In an image classification device of a dual-energy X-ray inspection system that converts a first X-ray detection signal and a second X-ray detection signal having different output intensities into a first image and a second image, respectively, The first X-ray detection signal and the second X-ray detection signal are attenuated signals after at least two X-rays having different output intensities are transmitted through an arbitrary object, and The above image classification device is, An acquisition unit for acquiring the first image and the second image; and A memory including instructions for generating a classification result for classifying categories by material properties of the object from the first image and the second image; and A control unit that generates a material classification map of the object in the first image and the second image by executing the above command, and processes to output the classification result based on the material classification map; Based on the above classification results, determine specific category items, and The above control unit is, An extraction unit that separates an object region and a background region in the first image and the second image; A classification map generation unit that generates the material classification map for the object area by setting the background area as a reference value; and A category classification unit that classifies the categories according to the material characteristics into organic, inorganic, metallic, other materials, and unidentified materials, respectively, based on the material classification map using a previously trained artificial neural network; The classification map generation unit sets the background area as the reference value for estimating the incident intensity of X-rays, calculates the relative attenuation coefficient ratio and transmission ratio of the object area based on the reference value, and generates the material classification map by mapping the attenuation coefficient ratio and the transmission ratio. Image classification device of a dual-energy X-ray inspection system.
  5. delete
  6. The 4th In the clause, The above control unit is, It further includes a post-processing unit, and The above post-processing unit is, A detection unit that detects whether a shielding material region exists within an object image based on the above classification result; A correction unit that corrects the attenuation coefficient ratio and the transmission ratio when the above shielding material region exists; A characteristic generation unit that generates material classification characteristics based on the result value obtained from the above correction; and A similarity calculation unit that calculates material classification similarity based on the above material classification characteristics; Image classification device of a dual-energy X-ray inspection system.
  7. In an image classification method of an image classification device that converts a first X-ray detection signal and a second X-ray detection signal having different output intensities into a first image and a second image, respectively, The first X-ray detection signal and the second X-ray detection signal are attenuated signals after at least two X-rays having different output intensities are transmitted through an arbitrary object, and The above image classification method is, A step of acquiring the first image and the second image; A step of separating the object region and the background region in the first image and the second image, respectively; A step of generating a material classification map for the object area by setting the background area as a reference value; A step of generating a classification result that classifies the categories of the object by material properties based on the material classification map above; and The method includes the step of determining a specific category item in the category by material properties based on the above classification results; The step of generating the above material classification map is, A step of setting the above background region as the above reference value for estimating the incident intensity of X-rays; A step of calculating the relative attenuation coefficient ratio and transmission ratio of the object area based on the above reference value; and A step of generating the material classification map by mapping the damping coefficient ratio and the transmission ratio. Image classification method of an image classification device.
  8. delete
  9. In Article 7, The above image classification method further includes a step of post-processing the classification result, and The above post-processing step is, A step of detecting whether a shielding material region exists within an object image based on a classification result; A step of correcting the attenuation coefficient ratio and the transmission ratio when the above shielding material region exists; A step of generating material classification characteristics based on the result value obtained by the above correction; and A step of calculating material classification similarity based on the above material classification characteristics; Image classification method of an image classification device.
  10. delete

Description

Dual-energy type X-ray inspection system, image classification apparatus and image classification method of a dual-energy type X-ray inspection system, method of training an artificial neural network for image classification {DUAL ENERGY TYPE X-RAY INSPECTION SYSTEM, METHOD AND APPARATUS FOR PROVIDING IMAGE CLASSIFICATION OF DUAL ENERGY TYPE X-RAY INSPECTION SYSTEM, METHOD OF LEARNING ARTIFICIAL NEURAL NETWORK FOR IMAGE CLASSIFICATION} The present invention relates to X-ray inspection technology, and in particular to image classification technology using dual-energy X-rays. Explosive Ordnance Disposal (EOD) systems are utilized to inspect luggage or items suspected of being explosive in situations such as airport security screenings, mail inspections, and military and police training. These EOD systems primarily utilize X-rays to identify the internal structure and contents of hazardous materials sealed in bags or cases. In particular, since explosives and similar materials are mostly composed of organic substances, active research and development is underway on X-ray-based material classification to improve the efficiency of hazardous material handling by distinguishing between organic and inorganic materials. Meanwhile, dual-energy X-ray analysis technology, which utilizes X-rays of different output intensities, is primarily used for cargo screening in the MeV-level high-energy range. However, there are limitations, such as the large size of the system, radiation safety concerns, and the difficulty of applying it to emergency situations, like explosive detection, when used outdoors. In particular, portable X-ray generators used for explosive detection mainly use only energies of 300 keV or less, and under these conditions, the difference in attenuation between materials and the difference in energy are small, so there are limitations in applying general dual-energy material classification methods. The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as publicly known technology disclosed to the general public prior to the filing of the present invention. FIG. 1 is a block diagram illustrating an exemplary dual-energy X-ray inspection system according to an embodiment of the present invention. FIG. 2 is a block diagram exemplarily illustrating the function of an image classification device according to an embodiment of the present invention, such as an image classification device included in the dual-energy X-ray inspection system of FIG. 1. Figure 3 is a block diagram illustrating the detailed functions of a control unit included in the image classification device of Figure 2. FIG. 4 is a block diagram explaining the detailed functions of the post-processing unit included in the control unit of FIG. 3. FIG. 5 is a flowchart exemplarily illustrating an image classification method of a dual-energy X-ray inspection system according to an embodiment of the present invention. Figure 6 is a flowchart that exemplarily illustrates the detailed process of the post-processing process of Figure 5. FIG. 7 is a diagram illustrating an exemplary case of training an artificial neural network for image classification of a dual-energy X-ray inspection system according to an embodiment of the present invention. Figure 8 is a diagram illustrating an exemplary case of classifying images of a dual-energy X-ray inspection system using an artificial neural network learned in Figure 7. The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the scope of the present invention is defined only by the claims. In describing the embodiments of the present invention, specific descriptions of known functions or configurations will be omitted unless actually necessary for describing the embodiments of the present invention. Furthermore, the terms described below are defined in consideration of the functions in the embodiments of the present invention, and these may vary depending on the intentions or practices of the user or operator. Therefore, such definitions should be based on the content throughout this specification. Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. FIG. 1 is a block diagram illustrating an exemplary dual-energy X-ray inspection system (1) according to an embodiment of the present invention. As illustrated in FIG. 1, a dual-