X-ray inspection device
The X-ray inspection apparatus addresses false detection and productivity issues by analyzing X-ray images in divided regions with multiple luminance thresholds, ensuring accurate detection of foreign objects regardless of their posture.
Patent Information
- Application Number
- JP2024006746
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-01-19
- Publication Date
- 2025-08-01
AI Technical Summary
Conventional X-ray inspection apparatuses face challenges in accurately detecting foreign matter of an elongated shape due to variations in posture, leading to false negatives or reduced productivity when adjusting density thresholds for improved detection.
The X-ray inspection apparatus employs a conveyance unit, X-ray source, detection unit, and determination unit that analyze X-ray transmission images by dividing them into regions based on luminance differences and using multiple luminance thresholds to accurately detect foreign objects, regardless of their posture.
This approach effectively prevents false detections and enhances productivity by accurately identifying foreign objects, including those with elongated shapes, through precise image analysis.
Smart Images

Figure 2025112491000001_ABST
Abstract
Description
Technical Field
[0001] One aspect of the present invention relates to an X-ray inspection apparatus.
Background Art
[0002] As a conventional X-ray inspection apparatus, for example, the apparatus described in Patent Document 1 below is known. The X-ray inspection apparatus described in Patent Document 1 below includes a radiation irradiation unit that irradiates a subject with radiation, a radiation detection unit that is disposed opposite to the radiation irradiation unit with the subject interposed therebetween and detects the radiation that has passed through the subject, an image forming unit that forms a first image based on a detection signal of the radiation detected by the radiation detection unit, and an image processing unit that performs image processing on the first image based on the density of pixels in a predetermined density range extracted from the first image to form a second image.
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Patent Document 2
Summary of the Invention
Problems to be Solved by the Invention
[0004] By the way, depending on the article, foreign matter smaller than a predetermined size may not need to be removed. Therefore, in the X-ray inspection apparatus described in Patent Document 1 above, if the density threshold is simply lowered to increase the detection accuracy of foreign matter, an article that should be determined to have no foreign matter may be determined to have foreign matter, resulting in a decrease in the productivity of the article. Here, depending on the posture of foreign matter having an elongated shape such as a bone, the foreign matter shown in the image formed by the image forming unit may appear small and dark (or bright). In this case, the calculated density becomes small. Therefore, even if the productivity of the article is reduced and the inspection accuracy of foreign matter is increased, there is a concern that an article that should be determined to have foreign matter may be determined to have no foreign matter.
[0005] An object of one aspect of the present invention is to provide an X-ray inspection apparatus capable of achieving both prevention of false detection and improvement of productivity.
Means for Solving the Problems
[0006] (1) The X-ray inspection apparatus according to one aspect of the present invention includes a conveyance unit that conveys an article, an X-ray source that irradiates the article conveyed by the conveyance unit with X-rays, an X-ray detection unit that detects X-rays, an X-ray image generation unit that generates an X-ray transmission image based on the X-ray detection result by the X-ray detection unit, and a determination unit that determines whether the article is normal or abnormal based on the X-ray transmission image. The determination unit divides the X-ray transmission image into a plurality of regions based on the luminance difference between adjacent pixels, and determines that the article is abnormal when the length, area, or density of pixels having a first luminance or higher in at least one of the plurality of regions is equal to or greater than a first threshold value. When the length, area, or density of pixels having a first luminance or higher in all of the plurality of regions is less than the first threshold value, it is determined whether the article is normal or abnormal based on the luminance change value and / or pixels having a second luminance or higher that is greater than the first luminance in at least one of the plurality of regions.
[0007] In this X-ray inspection apparatus, the determination unit determines whether an article is normal or abnormal based not only on the length, area, or density of pixels having a first luminance or higher in each of a plurality of regions obtained by dividing an X-ray transmission image, but also on the luminance change value and / or pixels having a second luminance or higher that is greater than the first luminance. As a result, compared with the conventional case, detection of a foreign object that exists in the article and has an elongated shape can be accurately performed regardless of the posture of the foreign object. Therefore, by using the above X-ray inspection apparatus, it is possible to achieve both prevention of false detection and improvement in productivity.
[0008] (2) In the X-ray inspection apparatus according to (1) above, when the length, area, or density of pixels having a first luminance or higher is less than a first threshold value in all of the plurality of regions, and the length, area, or density of pixels having a second luminance or higher is less than a second threshold value in all of the plurality of regions, the determination unit may determine that the article is normal. When the length, area, or density of pixels having a second luminance or higher is equal to or greater than the second threshold value in at least one of the plurality of regions, the determination unit may determine that the article is abnormal. In this case, it is possible to accurately achieve both prevention of false detection and improvement in productivity.
[0009] (3) In the X-ray inspection apparatus according to (1) or (2) above, the X-ray image generation unit generates an X-ray transmission image using a first image processing algorithm that is easy to determine a foreign object derived from a living body and a second image processing algorithm that is easy to determine a foreign object derived from the outside and not from a living body. When there are pixels having a first luminance or higher in at least one of a plurality of regions of the X-ray transmission image generated by the second image processing algorithm, the determination unit may determine that the article is abnormal. In this case, false detection of a foreign object derived from the outside can be well prevented.
[0010] (4) An X-ray inspection apparatus according to another aspect of the present invention includes a conveyance unit that conveys an article, an X-ray source that irradiates the article conveyed by the conveyance unit with X-rays, an X-ray detection unit that detects the X-rays, an X-ray image generation unit that generates an X-ray transmission image based on the detection result of the X-rays by the X-ray detection unit, and a determination unit that determines whether the article is normal or abnormal based on the X-ray transmission image. The determination unit divides the X-ray transmission image into a plurality of regions based on the luminance difference between adjacent pixels, and determines that the article is abnormal when the length, area, or density of the pixels below the first luminance in at least one of the plurality of regions is equal to or greater than the first threshold value. When the length, area, or density of the pixels below the first luminance in all of the plurality of regions is less than the first threshold value, it is determined whether the article is normal or abnormal based on the luminance change value and / or the pixels below the second luminance that is less than the first luminance in at least one of the plurality of regions.
[0011] In this X-ray inspection apparatus, the determination unit determines whether the article is normal or abnormal based not only on the length, area, or density of the pixels below the first luminance in each of the plurality of regions obtained by dividing the X-ray transmission image, but also on the luminance change value and / or the pixels below the second luminance that is less than the first luminance. Thereby, compared with the conventional case, detection of a foreign object that exists in the article and has an elongated shape can be performed with high accuracy regardless of the posture of the foreign object. Therefore, by using the above X-ray inspection apparatus, it is possible to achieve both prevention of false detection and improvement in productivity.
[0012] (5) In the X-ray inspection apparatus described in (4) above, when the length, area, or density of the pixels below the first luminance in all of the plurality of regions is less than the first threshold value, and the length, area, or density of the pixels below the second luminance in all of the plurality of regions is less than the second threshold value, the determination unit may determine that the article is normal. When the length, area, or density of the pixels below the second luminance in at least one of the plurality of regions is equal to or greater than the second threshold value, the determination unit may determine that the article is abnormal. In this case, it is possible to accurately achieve both prevention of false detection and improvement in productivity.
[0013] (6) In the X-ray inspection apparatus according to (4) or (5) above, the X-ray image generation unit generates an X-ray transmission image using a first image processing algorithm that is easy to determine foreign substances derived from a living body and a second image processing algorithm that is easy to determine foreign substances derived from the outside and not from a living body. The determination unit may determine that the article is abnormal if pixels having a luminance equal to or lower than the first luminance exist in at least one of a plurality of regions of the X-ray transmission image generated by the second image processing algorithm. In this case, false detection of foreign substances derived from the outside can be preferably prevented.
[0014] (7) In the X-ray inspection apparatus according to any one of (1) to (6) above, the X-ray image generation unit generates an X-ray transmission image using a first image processing algorithm that is easy to determine foreign substances derived from a living body and a second image processing algorithm that is easy to determine foreign substances derived from the outside and not from a living body. Each of the first luminance and the second luminance may be different for each image processing algorithm. In this case, an optimal determination can be made according to the type of foreign substance and the like.
Advantages of the Invention
[0015] According to one aspect of the present invention, it is possible to provide an X-ray inspection apparatus capable of achieving both prevention of false detection and improvement in productivity.
Brief Description of the Drawings
[0016]
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
[0017] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or corresponding elements are denoted by the same reference numerals, and redundant descriptions are omitted. Also, "A or B" in this specification means that either one of A and B may be included, and it does not exclude the case where both A and B are included.
[0018] As shown in FIG. 1, the X-ray inspection apparatus 1 includes an apparatus main body 2, support legs 3, a shield box 4, a conveyance unit 5, an X-ray irradiation unit 6 (X-ray source), an X-ray detection unit 7, a display operation unit 8, and a control unit 10. The X-ray inspection apparatus 1 generates an X-ray transmission image of the article G while conveying the article G, and inspects the article G based on the X-ray transmission image. The article G before inspection is carried into the X-ray inspection apparatus 1 by the carry-in conveyor 51. The article G after inspection is carried out of the X-ray inspection apparatus 1 by the carry-out conveyor 52.
[0019] The apparatus main body 2 houses the control unit 10 and the like. The support legs 3 support the apparatus main body 2. The shield box 4 is provided on the apparatus main body 2. The shield box 4 is a housing that prevents leakage of X-rays (electromagnetic waves) to the outside. Inside the shield box 4, an inspection chamber R where inspection of the article G by X-rays is performed is provided. The shield box 4 is formed with a carry-in port 4a and a carry-out port 4b. The article G before inspection is carried into the inspection chamber R from the carry-in conveyor 51 through the carry-in port 4a. The article G after inspection is carried out from the inspection chamber R to the carry-out conveyor 52 through the carry-out port 4b.
[0020] The conveying unit 5 is a member that conveys the article G, and is arranged so as to penetrate the center of the shield box 4. The conveying unit 5 conveys the article G along the conveying direction A from the loading port 4a through the inspection chamber R to the unloading port 4b. The speed (conveying speed) at which the conveying unit 5 conveys the article G is set by, for example, the control unit 10. The conveying unit 5 is, for example, a belt conveyor stretched between the loading port 4a and the unloading port 4b. Note that the conveying unit 5 may protrude outside the loading port 4a and the unloading port 4b.
[0021] As shown in FIGS. 1 and 2, the X-ray irradiation unit 6 is an electromagnetic wave irradiation unit arranged in the shield box 4, and irradiates the article G conveyed to the conveying unit 5 with X-rays. The X-rays include X-rays in various energy regions from low energy (long wavelength) to high energy (short wavelength). For this reason, the X-ray irradiation unit 6 irradiates the article G conveyed to the conveying unit 5 with X-rays in a plurality of energy regions. After the X-ray inspection apparatus 1 is activated and before the inspection of the article G, X-ray irradiation by the X-ray irradiation unit 6 (that is, idling of the X-ray irradiation unit 6) may be performed. Note that the “low” and “high” in the above-described low energy and high energy indicate relatively “low” and “high” among a plurality of energy regions irradiated from the X-ray irradiation unit 6, and do not indicate a specific range.
[0022] The X-ray detection unit 7 is a sensor member (electromagnetic wave sensor) that detects electromagnetic waves and is disposed inside the shield box 4. The X-ray detection unit 7 detects X-rays in each of a plurality of energy bands that have passed through the article G. In the present embodiment, the X-ray detection unit 7 is configured to detect X-rays in a low energy band (first energy band) and X-rays in a high energy band (second energy band). That is, the X-ray detection unit 7 includes a first line sensor 11 and a second line sensor 12. Note that the sensor member may be a member that detects X-rays in one energy band or a member (multi-energy sensor member) that detects X-rays in a plurality of energy bands. Each of the first line sensor 11 and the second line sensor 12 includes a plurality of X-ray detection elements arranged linearly along a horizontal direction perpendicular to the conveyance direction A. The first line sensor 11 detects X-rays in the low energy band that have passed through the article G and the conveyance belt of the conveyance unit 5. The second line sensor 12 detects X-rays in the high energy band that have passed through the article G, the conveyance belt of the conveyance unit 5, and the first line sensor 11. Note that the X-ray detection unit 7 may be a member having a single line sensor or a direct conversion type detection unit capable of detecting X-rays by a photon counting method. When the X-ray detection unit 7 is the direct conversion type detection unit, for example, the configuration, settings, operations, etc. of the X-ray detection unit 7 are made by the method described in JP-A-2023-132587.
[0023] As shown in FIG. 1, the display operation unit 8 is a member (display unit) provided in the apparatus main body 2. The display operation unit 8 displays various information and receives input operations of various conditions from the outside. The display operation unit 8 is, for example, a liquid crystal display and displays an operation screen as a touch panel. In this case, the operator can input various conditions via the display operation unit 8. For example, the operator can set the operation mode of the X-ray inspection apparatus 1, the conveyance speed of the conveyance unit 5, the power (at least one of current and voltage) supplied to the X-ray irradiation unit 6, the sensitivity of the X-ray detection unit 7, etc. via the display operation unit 8. The input operation received by the display operation unit 8 is output to the conveyance unit 5, the X-ray detection unit 7, the control unit 10, etc.
[0024] The control unit 10 is arranged inside the apparatus main body 2. The control unit 10 controls the operations of each part of the X-ray inspection apparatus 1. The control unit 10 is composed of a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), etc. Programs for controlling the X-ray inspection apparatus 1, operation modes of the X-ray inspection apparatus 1, etc. are stored in the ROM.
[0025] Figure 3 is a functional configuration diagram of the control unit. As shown in Figure 3, the control unit 10 includes a detection result acquisition unit 21, an X-ray image generation unit 22, a determination unit 23, an output unit 24, and a storage unit 25.
[0026] The detection result acquisition unit 21 acquires the detection result signal output from the X-ray detection unit 7. The detection result acquisition unit 21 transmits the acquired detection result signal to the X-ray image generation unit 22.
[0027] The X-ray image generation unit 22 is mainly constituted by, for example, a GPU (Graphics Processing Unit), and develops the detection result signal into a two-dimensional image on a memory. The memory where the two-dimensional image is developed is, for example, a memory included in the GPU, but is not limited thereto. The X-ray image generation unit 22 generates one or more types of X-ray transmission images used for inspecting the article G based on, for example, the X-ray detection result by the X-ray detection unit 7 (see, for example, FIGS. 4 and 5 described later). As one of the X-ray transmission images, the X-ray image generation unit 22 generates, for example, an overall transmission image corresponding to all the X-rays in the plurality of energy bands based on the detection result. The overall transmission image is generated based on, for example, all the information included in the detection result signal. Information regarded as noise may be excluded in advance when generating the overall transmission image. In this case, the overall transmission image is generated based on a part of the information included in the detection result signal. In addition to the overall transmission image, the X-ray image generation unit 22 may generate one or more types of transmission images corresponding to a part of the X-rays in the plurality of energy bands. In this case, as the transmission images, the X-ray image generation unit 22 may generate a first transmission image generated based on the X-ray detection result of the first line sensor 11 included in the detection result signal, a second transmission image generated based on the X-ray detection result of the second line sensor 12 included in the detection result signal, and a difference image obtained by subtraction processing between the first transmission image and the second transmission image.
[0028] The X-ray image generation unit 22 generates the above-described X-ray transmission image using, for example, an image processing algorithm. The image processing algorithm is a type indicating the processing procedure of the image processing to be performed on the X-ray transmission image. The image processing algorithm is constituted by one image processing filter or a combination of a plurality of image processing filters. A plurality of image processing algorithms can be acquired from the outside via a network such as the Internet. Also, a plurality of image processing algorithms can be acquired from an external storage medium such as a USB memory or a removable hard disk. At least one or more of the plurality of image processing algorithms adopt a genetic algorithm (GA = Genetic Algorithms), which is a method applying the mechanisms of inheritance and evolution in the biological world, and can be automatically generated from a plurality of image processing filters based on the specifications or inspection conditions of the X-ray inspection apparatus 1. At least a part of the plurality of image processing algorithms can also be appropriately set by an operator via the display operation unit 8.
[0029] In the present embodiment, the X-ray image generation unit 22 generates at least an X-ray transmission image using a first image processing algorithm that easily determines a foreign object derived from a living body and a second image processing algorithm that easily determines a foreign object derived from the outside and not from a living body. In other words, in the present embodiment, the X-ray image generation unit 22 generates an X-ray transmission image using the first image processing algorithm and at least generates another X-ray transmission image using the second image processing algorithm. When the first image processing algorithm is used, a foreign object derived from a living body is likely to be shown in the X-ray transmission image. When the second image processing algorithm is used, a foreign object derived from the outside is likely to be shown in the X-ray transmission image. Foreign objects derived from a living body are, for example, bone, muscle, tooth, nail, hair, shell (such as crustacean shell, shellfish shell, eggshell, etc.). Foreign objects derived from the outside and not from a living body are, for example, metal, plastic, glass, ceramic, piece of wood, fiber, etc. At least one of the first image processing algorithm and the second image processing algorithm may exist in a plurality of types.
[0030] Instead of using the above image processing algorithm, the X-ray image generation unit 22 may use a program automatically set by machine learning. Such a program is a prediction model (trained model) generated by machine learning and is an inference program incorporating parameters (trained parameters) obtained as a result of machine learning. Examples of machine learning used for the trained model include neural networks, support vector machines, genetic algorithms, and the like. The trained model may include a convolutional neural network or may include a neural network having a plurality of layers (for example, eight or more layers). That is, the trained model corresponding to the above program may be generated by deep learning.
[0031] Based on the X-ray transmission image generated by the X-ray image generation unit 22, the determination unit 23 determines whether the article G is normal or abnormal. When the X-ray image generation unit 22 generates a plurality of X-ray transmission images, the determination unit 23 determines whether the article G is normal or abnormal based on at least a part of the plurality of X-ray transmission images. The determination unit 23 determines whether the article G is normal or abnormal based on, for example, the overall transmission image and each of the above transmission images. Alternatively, the determination unit 23 determines whether the article G is normal or abnormal based on each of the X-ray transmission image generated using the first image processing algorithm and another X-ray transmission image generated using the second image processing algorithm. When a plurality of X-ray transmission images are generated, the determination of the article G based on each image may be performed simultaneously or at different timings. For example, during the generation of the above transmission image by the X-ray image generation unit 22, the determination of the article G based on the overall transmission image may be made.
[0032] The determination by the determination unit 23 as to whether the article G is normal or abnormal is performed based on inspection results such as the presence or absence of foreign matter and cracks in the article G. For example, when an inspection result indicating that the article G contains a problem-causing foreign matter is obtained, or when an inspection result indicating that a problem-causing crack is formed in the article G is obtained, etc., the determination unit 23 determines that the article G is abnormal (i.e., the article G is a defective product). The problem-causing foreign matter is, for example, a foreign matter larger than a predetermined size and needs to be removed from the article G. In other words, foreign matter with a size equal to or smaller than the predetermined size is regarded as non-problematic foreign matter and does not need to be removed from the article G. Therefore, an article G that contains only non-problematic foreign matter as foreign matter is determined to be normal and can become a non-defective product without removing the foreign matter. Note that even when the article G contains only non-problematic foreign matter as foreign matter, if a large number of such foreign matters are contained, the article G may be determined to be abnormal. The above threshold value for the number of foreign matters can be appropriately set according to the type of the article G and the like.
[0033] Hereinafter, with reference to FIGS. 4(a), (b), FIGS. 5(a), (b), and FIG. 6, an example of a method for determining the presence or absence of problem-causing foreign matter in the article G will be described. Each of FIGS. 4(a), (b) and FIGS. 5(a), (b) shows an X-ray transmission image including the imaged article. FIG. 6 is a flowchart showing an example of a method for determining the presence or absence of problem-causing foreign matter in the article G.
[0034] Figs. 4(a), (b) and Figs. 5(a), (b) respectively show X-ray transmission images P1 to P4. Articles G1 to G4 are respectively shown in the X-ray transmission images P1 to P4. When the determination unit 23 determines the presence or absence of a foreign object in the article G, as a preprocessing, the determination unit 23 divides the X-ray transmission image into a plurality of regions based on the luminance difference between adjacent pixels (step ST1). For example, after step ST1, the X-ray transmission image P1 shown in Fig. 4(a) is divided into regions R1 to R4. In the pixels included in each of the regions R1 to R4, the luminance difference between adjacent pixels is less than a predetermined threshold value. On the other hand, for example, the luminance difference between a pixel included in the region R1 and adjacent to the region R2 and a pixel adjacent to the said pixel and included in the region R2 is equal to or more than the predetermined threshold value. In another example, each of the X-ray transmission images P1 to P4 may be divided into a region where pixels with a luminance less than a first luminance described later are adjacent to each other, a region where pixels with a luminance equal to or more than the first luminance are adjacent to each other, and a region where pixels with a luminance equal to or more than a second luminance described later are adjacent to each other. In Fig. 4(a), the luminance of all the pixels included in the region R1 is substantially the same, the luminance of all the pixels included in the region R2 is substantially the same, the luminance of all the pixels included in the region R3 is substantially the same, and the luminance of all the pixels included in the region R4 is substantially the same, but it is not limited thereto.
[0035] In Fig. 4(a), the average luminance of the region R1 is the lowest, and the average luminances of the regions R3 and R4 are the highest. The region R1 shows an imaged portion other than the article G. The luminance of at least a part of the pixels included in the region R3 and the luminance of at least a part of the pixels included in the region R4 are respectively equal to or more than a first luminance described later and less than a second luminance described later. Note that the above-mentioned predetermined threshold value can be appropriately adjusted according to, for example, the type of the article G, the type of foreign object that may be included in the article G, the type of image processing algorithm, etc. Thereby, dividing the X-ray transmission image into a plurality of regions can be favorably carried out according to the type of the article G and the like.
[0036] Similar to the X-ray transmission image P1, the X-ray transmission image P2 shown in FIG. 4(b) is divided into regions R11 to R14, the X-ray transmission image P3 shown in FIG. 5(a) is divided into regions R21 to R24, and the X-ray transmission image P4 shown in FIG. 5(b) is divided into regions R31 to R34. In one example, the luminances of the pixels included in regions R1, R11, R21, and R31 are the same as each other, and the luminances of the pixels included in regions R2, R12, R22, and R32 are the same as each other. In FIG. 4(b), the luminances of regions R13 and R14 are substantially the same, are equal to or higher than a first luminance described later, and are less than a second luminance described later. In FIG. 5(a), the luminance of the pixels included in region R24 is the highest, and the luminance of at least a part of the pixels included in region R24 is equal to or higher than the first luminance described later and equal to or higher than the second luminance described later. In FIG. 5(b), the luminance of some of the pixels included in region R34 is the highest and is equal to or higher than the first luminance and less than the second luminance. In the pixels included in region R34, the luminance difference between adjacent pixels is less than a predetermined threshold value.
[0037] In the determination of the presence or absence of foreign matter in the article G by the determination unit 23, first, as a first step, the determination unit 23 determines whether the length, area, or density of pixels with a first luminance or higher in at least one of a plurality of regions is equal to or greater than a first threshold value (step ST12). In step ST12, when the length, area, or density of pixels with a first luminance or higher in at least one of the plurality of regions is equal to or greater than the first threshold value (step ST12: YES), the determination unit 23 determines that the article G is abnormal. That is, the determination unit 23 determines that there is a problematic foreign matter in the article G (step ST13). On the other hand, when the length, area, or density of pixels with a first luminance or higher in all of the plurality of regions is less than the first threshold value (step ST12: NO), the process proceeds to a second step described later. At least one of the first luminance and the first threshold value can be appropriately adjusted according to the type of the article G, the type of foreign matter that can be included in the article G, the type of image processing algorithm, and the like. Thereby, the determination of the presence or absence of foreign matter in the article G can be favorably performed according to the type of the article G and the like. For example, the first luminance when the first image processing algorithm is used and the first luminance when the second image processing algorithm is used can be different from each other.
[0038] The above-mentioned density is data that serves as the basis for the determination of the presence or absence of foreign matter by the determination unit 23, and is calculated, for example, in accordance with the method disclosed in Japanese Patent Application Laid-Open No. 2005-172510. As an example, as shown in FIG. 7, in a part of the X-ray transmission image, the degree of aggregation of the pixels detected as foreign matter (hereinafter, the pixel is referred to as the target pixel 31) included in a predetermined area (hereinafter, the area is referred to as the region of interest 32) is determined as the density. In FIG. 7, the target pixel 31 is a pixel having a luminance smaller than a predetermined threshold value among the pixels included in the image obtained by binarizing the X-ray transmission image, but is not limited thereto. As combined with FIGS. 4 and 5, the target pixel 31 may be a pixel having a luminance larger than a predetermined threshold value. The region of interest 32 is an area centered on the target pixel 31. In one example, the density is calculated as the density of the pixels detected as foreign matter included in the region of interest 32 centered on the target pixel 31. As another example, the density is calculated using the luminance values of adjacent pixels included in a specific area where a smoothing filter process is performed.
[0039] As described above, at least a part of the luminance of the pixels included in the regions R3 and R4 included in the X-ray transmission image P1, at least a part of the luminance of the pixels included in the regions R13 and R14 included in the X-ray transmission image P2, at least a part of the luminance of the pixels included in the regions R23 and R24 included in the X-ray transmission image P3, and at least a part of the luminance of the pixels included in the regions R33 and R34 included in the X-ray transmission image P4 are each equal to or higher than the first luminance. Here, the area and density of each of the regions R3, R4, R13, R23, R24, R33, and R34 are less than the first threshold value. That is, in the X-ray transmission images P1, P3, and P4, the area and density of the pixels having a luminance equal to or higher than the first luminance in all of the plurality of regions are less than the first threshold value. On the other hand, the length, area, or density of the region R14 is equal to or higher than the first threshold value. Therefore, in the first stage, the articles G1, G3, and G4 are determined to be normal, and the article G2 is determined to be abnormal.
[0040] Next, as a second step, the determination unit 23 determines whether the article G is normal or abnormal based on the luminance change value in at least one of the plurality of regions and / or pixels having a second luminance greater than the first luminance. In one example, in the second step after the first step, the determination unit 23 determines whether the length, area, or density of the pixels having a second luminance or higher in at least one of the plurality of regions is equal to or greater than a second threshold value (step ST14). In step ST14, when the length, area, or density of the pixels having a second luminance or higher in at least one of the plurality of regions is equal to or greater than the second threshold value (step ST14: YES), the determination unit 23 determines that the article G is abnormal. That is, the determination unit 23 determines that there is a foreign object in the article G (step ST13). On the other hand, when the length, area, or density of the pixels having a second luminance or higher in all of the plurality of regions is less than the second threshold value (step ST14: NO), the determination unit 23 determines that the article G is normal. That is, the determination unit 23 determines that there is no problematic foreign object in the article G (step ST15). At least one of the second luminance and the second threshold value can be appropriately adjusted according to the type of the article G, the type of foreign objects that can be included in the article G, the type of the image processing algorithm, and the like. Thereby, the determination of the presence or absence of foreign objects in the article G can be satisfactorily performed according to the type of the article G and the like. For example, the second luminance when the first image processing algorithm is used and the second luminance when the second image processing algorithm is used can be different from each other.
[0041] As described above, the luminance of at least a part of the pixels included in the region R24 included in the X-ray transmission image P3 is equal to or greater than the second luminance. When the length, area, or density of the region R24 is equal to or greater than the second threshold value, the article G3 is determined to be abnormal. On the other hand, when the area and density of the region R24 are less than the second threshold value, the article G3 is determined to be normal. On the other hand, as described above, in the X-ray transmission images P1 and P4, there are no pixels showing a second luminance or higher. Therefore, the article G3 can be determined to be normal.
[0042] In addition to or separately from the above example, at the second stage, the determination unit 23 determines whether the luminance change value in at least one of the plurality of regions is equal to or greater than a third threshold value. For example, when the luminance change value in at least one of the plurality of regions is equal to or greater than the third threshold value, the determination unit 23 determines that the article G is abnormal. In this case, the determination unit 23 determines that there is a foreign object in the article G. On the other hand, when the luminance change value in all of the plurality of regions is less than the third threshold value, the determination unit 23 determines that the article G is normal. Therefore, depending on the luminance change value of the region R34 of the X-ray transmission image P4, the article G4 may be determined to be abnormal. The luminance change value corresponds to the difference between the maximum luminance and the minimum luminance in the region including the pixels of the first luminance abnormality. The third threshold value can be appropriately adjusted according to the type of the article G, the type of foreign object that may be included in the article G, the type of image processing algorithm, and the like. Thereby, the determination of the presence or absence of a foreign object in the article G can be satisfactorily performed according to the type of the article G and the like. For example, the third threshold value when the first image processing algorithm is used and the third threshold value when the second image processing algorithm is used may be different from each other. Note that the luminance change value may be calculated by an output value obtained by performing differential filter processing on a specific region.
[0043] In the second stage described above, when the determination unit 23 determines that the length, area, or density of the pixels having a second luminance or higher in at least one of the plurality of regions is equal to or greater than a second threshold value, or when the determination unit 23 determines that the luminance change value in at least one of the plurality of regions is equal to or greater than a third threshold value, the article G may be determined to be abnormal. Alternatively, the article G may be determined to be abnormal only when the determination unit 23 determines that the length, area, or density of the pixels having a second luminance or higher in at least one of the plurality of regions is equal to or greater than a second threshold value and determines that the luminance change value in at least one of the plurality of regions is equal to or greater than a third threshold value.
[0044] Returning to FIG. 3, in the case where the article G is wrapped by a sheet-like packaging material, etc., the determination unit 23 can also inspect for breakage of the packaging material, poor sealing (sealing bite) of the packaging material, etc. In the case where the article G is accommodated in a package, etc., the determination unit 23 can perform a foreign object confirmation inspection, a shortage confirmation inspection, a storage quantity confirmation inspection, a cavity confirmation inspection, etc. inside the package. The determination unit 23 transmits the determination result as to whether the article G is normal or not to the output unit 24 and the storage unit 25.
[0045] The output unit 24 outputs the determination result of the determination unit 23 to at least one of a part other than the control unit 10 in the X-ray inspection apparatus 1 and an apparatus different from the X-ray inspection apparatus 1. Thereby, at least one of the X-ray inspection apparatus 1 and an apparatus different from the X-ray inspection apparatus 1 (for example, a sorting apparatus arranged downstream of the X-ray inspection apparatus 1) can execute an operation when the article G is a defective product. Another example of the apparatus different from the X-ray inspection apparatus 1 includes, for example, a carry-in conveyor 51, a carry-out conveyor 52, a notification apparatus, etc.
[0046] The storage unit 25 records signals, data, etc. generated by the control unit 10. For example, the storage unit 25 records a detection result signal transmitted from the detection result acquisition unit 21, image data transmitted from the X-ray image generation unit 22, and data regarding the determination result transmitted from the determination unit 23.
[0047] According to the X-ray inspection apparatus 1 according to the present embodiment described above, based not only on the length, area, or density of pixels having a first luminance or higher in each of a plurality of regions obtained by dividing the X-ray transmission image, but also on the luminance change value and / or pixels having a second luminance or higher that is greater than the first luminance, it is determined whether the article G is normal or abnormal. Thereby, foreign objects that do not pose a problem in terms of the size shown in the X-ray transmission image but that can actually pose a problem (for example, foreign objects that exist inside the article G and have an elongated shape) are detected. That is, regardless of the posture of the foreign object inside the article G, foreign objects that pose a problem can be accurately detected. Therefore, by using the X-ray inspection apparatus 1, it becomes possible to achieve both prevention of false detection and improvement in productivity.
[0048] In one example, when the length, area, or density of pixels with a first luminance or higher is less than a first threshold value in all of the plurality of regions, and the length, area, or density of pixels with a second luminance or higher is less than a second threshold value in all of the plurality of regions, the determination unit 23 determines that the article is normal, and when the length, area, or density of pixels with a second luminance or higher is equal to or greater than the second threshold value in at least one of the plurality of regions, the determination unit 23 determines that the article is abnormal. In this case, it is possible to accurately achieve both prevention of false detection and improvement in productivity.
[0049] In one example, the X-ray image generation unit 22 generates an X-ray transmission image using a first image processing algorithm that makes it easy to determine a foreign object derived from a living body and a second image processing algorithm that makes it easy to determine a foreign object derived from the outside and not from a living body, and each of the first luminance and the second luminance may be different for each image processing algorithm. In this case, it is possible to perform an optimal determination according to the type of foreign object or the like.
[0050] Hereinafter, the X-ray inspection apparatus according to the modified example will be described. In the following description, descriptions overlapping with the above-described embodiment will be omitted, and portions different from the above-described embodiment will be described. That is, within the technically possible range, the description of the above-described embodiment may be appropriately used in the modified example described below.
[0051] When the article G inspected by the X-ray inspection apparatus 1 is food or the like, the detection accuracy of foreign matter derived from the outside such as a wire may be set higher than the detection accuracy of foreign matter derived from a living body. In such a case, the determination of the presence or absence of foreign matter based on the X-ray transmission image generated using the second image processing algorithm may be strictly performed. FIG. 8 is a flowchart showing another example of a method for determining the presence or absence of foreign matter in an article by a determination unit. As shown in FIG. 8, in this modification, first, an X-ray transmission image is generated using the second image processing algorithm (step ST21). Subsequently, the above step ST11 is performed. Subsequently, the determination unit 23 determines whether or not there are pixels having a first luminance or higher in at least one of a plurality of regions of the X-ray transmission image generated by the second image processing algorithm (step ST22). When there are pixels having a first luminance or higher in at least one of the plurality of regions (step ST22: YES), the determination unit 23 determines that the article G is abnormal. That is, the determination unit 23 determines that there is a foreign matter (particularly, a foreign matter derived from the outside) that poses a problem in the article G. On the other hand, when there are no pixels having a first luminance or higher in all of the plurality of regions (step ST22: NO), the determination unit 23 determines that the article G is normal. That is, the determination unit 23 determines that there is no foreign matter that poses a problem in the article G.
[0052] According to the modification described above, false detection of foreign matter derived from the outside can be preferably prevented. In the above modification, the presence or absence of foreign matter is determined based on the presence or absence of pixels having a first luminance or higher, but the present invention is not limited thereto. For example, it may be determined whether or not the length, area, or density of pixels having a first luminance or higher in at least one of the plurality of regions is equal to or greater than a predetermined threshold value. The predetermined threshold value may be the same as or different from the first threshold value.
[0053] As described above, the embodiments of the present invention have been described. However, the present invention is not necessarily limited to the above-described embodiments, and various modifications can be made without departing from the gist thereof.
[0054] In the above embodiment, the foreign object shown in the X-ray transmission image appears dark, but it is not limited to this. For example, as shown in FIGS. 9(a) to 9(d), the foreign object shown in the X-ray transmission image may appear bright. Each of the X-ray transmission images P11 to P14 shown in FIGS. 9(a) to 9(d) is a negative-positive inverted image of the X-ray transmission images P1 to P4. Therefore, in FIGS. 9(a) to 9(d), the luminance of the pixels indicating the problematic foreign object is smaller. When the X-ray transmission images P11 to P14 are used, in step ST12 above, when the length, area, or density of the pixels below the first luminance in at least one of the plurality of regions is equal to or greater than the first threshold, the determination unit 23 determines that the article G is abnormal. In addition, when the length, area, or density of the pixels below the first luminance in all of the plurality of regions is less than the first threshold, the determination unit 23 determines whether the article G is normal or abnormal based on the luminance change value in at least one of the plurality of regions and / or the pixels below the second luminance that is smaller than the first luminance. As a specific example, in step ST13 above, when the length, area, or density that is below the second luminance in all of the plurality of regions is less than the second threshold, it is determined that the article G is normal, and when the length, area, or density of the pixels below the second luminance in at least one of the plurality of regions is equal to or greater than the second threshold, it is determined that the article G is abnormal. In addition, when the above modification example and the negative-positive inverted image are used for determining the presence or absence of a foreign object, in step ST22 above, when there are pixels below the first luminance in at least one of the plurality of regions of the X-ray transmission image generated by the second image processing algorithm, the determination unit 23 determines that the article is abnormal. Note that the negative-positive inverted image may also be appropriately applied to the above modification example.
[0055] In the above-described embodiment, the X-ray inspection apparatus has a control unit that performs image processing, but the present invention is not limited thereto. For example, functions such as performing image processing in the control unit, determining the presence or absence of foreign matter contained in an article, and displaying X-ray inspection results may not be included in the X-ray inspection apparatus. Instead, they may be implemented in a control device capable of wired communication or wired communication with respect to the above-described X-ray inspection apparatus. In this case, an X-ray inspection system including the X-ray inspection apparatus and the control device into which the inspection results of the X-ray inspection apparatus are input can be realized. Such an X-ray inspection system also exhibits the same operational effects as those of the above-described embodiment. In addition, the configuration of the control unit included in the X-ray inspection apparatus can be simplified. Furthermore, even when the user is at a location away from the X-ray inspection apparatus, the inspection results and the like can be confirmed. Note that the control device is not particularly limited, and examples thereof include a laptop PC and a tablet.
Explanation of Reference Numerals
[0056] 1... X-ray inspection apparatus, 3... support leg, 4... shield box, 4a... loading port, 4b... unloading port, 5... conveying unit, 6... X-ray irradiation unit, 7... X-ray detection unit, 8... display operation unit, 21... detection result acquisition unit, 22... X-ray image generation unit, 23... determination unit, 24... output unit, 25... storage unit, A... conveying direction, G... article, P1 to P4, P11 to P14... X-ray transmission images.
Claims
1. A conveying unit for conveying an article, An X-ray source for irradiating the article conveyed to the conveying unit with X-rays, An X-ray detection unit for detecting the X-rays, An X-ray image generation unit for generating an X-ray transmission image based on the detection result of the X-rays by the X-ray detection unit, A determination unit for determining whether the article is normal or abnormal based on the X-ray transmission image, comprising: The determination unit: Divides the X-ray transmission image into a plurality of regions based on the luminance difference between adjacent pixels, When the length, area, or density of pixels having a first luminance or higher in at least one of the plurality of regions is equal to or greater than a first threshold value, determines that the article is abnormal, When the length, area, or density of pixels having a first luminance or higher in all of the plurality of regions is less than the first threshold value, determines whether the article is normal or abnormal based on the luminance change value in at least one of the plurality of regions and / or pixels having a second luminance or higher that is greater than the first luminance. An X-ray inspection apparatus.
2. The determination unit, when the length, area, or density of pixels having a first luminance or higher in all of the plurality of regions is less than the first threshold value, When the length, area, or density of pixels having a second luminance or higher in all of the plurality of regions is less than a second threshold value, determines that the article is normal, The X-ray inspection apparatus according to claim 1, wherein when the length, area, or density of pixels having a second luminance or higher in at least one of the plurality of regions is equal to or greater than the second threshold value, determines that the article is abnormal.
3. The X-ray image generation unit generates the X-ray transmission image using a first image processing algorithm that is easy to determine foreign matter derived from a living body and a second image processing algorithm that is easy to determine foreign matter derived from the outside and not from a living body, The determination unit determines that the article is abnormal when pixels having a first luminance or higher exist in at least one of the plurality of regions of the X-ray transmission image generated by the second image processing algorithm. The X-ray inspection apparatus according to claim 1 or 2.
4. A conveying unit for conveying an article, An X-ray source for irradiating the article conveyed to the conveying unit with X-rays, An X-ray detection unit for detecting the X-rays, An X-ray image generation unit for generating an X-ray transmission image based on the detection result of the X-rays by the X-ray detection unit, A determination unit for determining whether the article is normal or abnormal based on the X-ray transmission image, comprising: The determination unit: The X-ray transmission image is divided into a plurality of regions based on the luminance difference between adjacent pixels, when the length, area, or density of pixels below a first luminance in at least one of the plurality of regions is equal to or greater than a first threshold value, it is determined that the article is abnormal, when the length, area, or density of pixels below the first luminance in all of the plurality of regions is less than the first threshold value, it is determined whether the article is normal or abnormal based on the luminance change value in at least one of the plurality of regions and / or pixels below a second luminance smaller than the first luminance, An X-ray inspection apparatus.
5. The determination unit is a case where the length, area, or density of pixels below the first luminance in all of the plurality of regions is less than the first threshold value, when the length, area, or density of pixels below the second luminance in all of the plurality of regions is less than a second threshold value, it is determined that the article is normal, The X-ray inspection apparatus according to claim 4, wherein when the length, area, or density of pixels below the second luminance in at least one of the plurality of regions is equal to or greater than the second threshold value, it is determined that the article is abnormal.
6. The X-ray image generation unit generates the X-ray transmission image using a first image processing algorithm that easily determines a foreign object derived from a living body and a second image processing algorithm that easily determines a foreign object derived from the outside and not from a living body, The determination unit determines that the article is abnormal when pixels below the first luminance exist in at least one of the plurality of regions of the X-ray transmission image generated by the second image processing algorithm. The X-ray inspection apparatus according to claim 4 or 5.
7. The X-ray image generation unit generates the X-ray transmission image using a first image processing algorithm that easily determines a foreign object derived from a living body and a second image processing algorithm that easily determines a foreign object derived from the outside and not from a living body, Each of the first luminance and the second luminance is different for each image processing algorithm. The X-ray inspection apparatus according to any one of claims 1, 2, 5, and 6.
Citation Information
Patent Citations
Radiation foreign matter inspection apparatus and radiation foreign matter inspection method
JP2005172510A
X-ray inspection device
JP2012073056A