Product inspection device and method for verifying its performance

Abstract

The present invention provides an item inspection device and a method for verifying its performance that can automatically detect a decline in inspection performance, thereby reliably maintaining inspection performance while reducing the number of manual performance checks required. [Solution] This X-ray inspection apparatus determines whether an item is good or bad based on the output of an image processing unit 33 that outputs a processed image having image features indicating the quality state of the item, and includes a sensitivity correction unit 32 that performs light receiving sensitivity correction of the X-ray detector 23 and outputs a corrected X-ray inspection image Dpw, an image quality change detection unit 37 that detects changes in image quality or the occurrence of factors causing changes, a reference image storage unit 36 ​​that stores a reference image Pmw of a good item, an evaluation image generation unit 38 that generates an evaluation image Pev by combining the reference image Pmw and the sensitivity-corrected X-ray inspection image Ptd when an image quality change factor is detected, and an inspection performance evaluation unit 39 that performs image processing on the evaluation image Pev in the image processing unit 33 and then determines whether the judgment result of the determination unit 35 is OK or NG.

Description

Technical Field

[0001] The present invention relates to an article inspection apparatus and a performance confirmation method thereof, and particularly relates to an article inspection apparatus that performs predetermined image processing on an X-ray inspection image of an article to determine the quality state of the article, and a performance confirmation method for confirming whether there is performance degradation accompanied by image quality degradation of the X-ray inspection image.

Background Art

[0002] In an article inspection apparatus using X-rays (electromagnetic waves that penetrate articles), generally, X-rays are irradiated onto an inspection object within an inspection area in an article conveyance section, and the X-rays that have penetrated the inspection object enter an X-ray detector and are detected, whereby a detection signal enabling image formation is output from the X-ray detector, and image data of an X-ray inspection image of the inspection object is generated based on the output signal.

[0003] In such an article inspection apparatus, generally, an X-ray detector having a flat array of sensor elements is used, and sensitivity correction of the X-ray detector is performed before the start of inspection operation, and calibration processing to suppress blurring of the X-ray transmission image, unnecessary gradation and the like is often performed. At that time, operation confirmation for checking the inspection performance of the article inspection apparatus (hereinafter, also simply referred to as performance confirmation) is executed.

[0004] As this type of article inspection apparatus, there is, for example, one comprising: a foreign matter determination unit that determines whether foreign matter is contained in an inspection object based on a detection signal from an X-ray detection unit that outputs a detection signal of an X-ray transmission amount that has penetrated the inspection object; and an operation confirmation processing unit that determines whether the X-ray detection unit and the foreign matter determination unit operate correctly using a foreign matter sample. In the operation confirmation processing unit, in order to determine whether the X-ray detection unit and the foreign matter determination unit operate correctly, it checks whether the signal level of the detection signal from the X-ray detection unit falls within a predetermined allowable range that can identify a foreign matter sample specified for each type of inspection object, and executes operation confirmation regarding inspection performance (see, for example, Patent Document 1).

[0005] As a means for detecting the passage of an item during transport, a first passage detection means is positioned upstream of the X-ray inspection unit in the transport direction, and a second passage detection means is positioned upstream of the first passage detection means in the transport direction. When a foreign object sample is placed in the transport section between the passage positions of the first and second passage detection means, if the second passage detection means does not detect the passage of the item to be inspected, and the first passage detection means detects the passage of the item to be inspected, the system is known to automatically switch the operating mode from normal inspection mode to operation confirmation mode (see, for example, Patent Document 2). [Prior art documents] [Patent Documents]

[0006] [Patent Document 1] Japanese Patent Publication No. 2009-031149 [Patent Document 2] Japanese Patent Publication No. 2013-113784 [Overview of the project] [Problems that the invention aims to solve]

[0007] However, with conventional material inspection equipment as described above, not only is preparation work such as foreign object samples required, but performance verification cannot be performed during the operation in which the material inspection is being carried out. Therefore, time-consuming performance verification had to be performed before the start of operation, at the end of operation, or at predetermined intervals after the start of operation.

[0008] Furthermore, the inspection performance of product inspection equipment can deteriorate with continued operation, and the factors contributing to this deterioration can also vary depending on the environment in which the product inspection equipment is installed and its operating conditions. Therefore, in order to maintain stable inspection performance for each product inspection device, time-consuming performance checks must be performed, for example, daily at relatively short intervals. This has made it difficult to improve production efficiency in manufacturing lines for food, pharmaceuticals, and other products where product inspection equipment is installed.

[0009] Furthermore, mistakes such as forgetting to return foreign object samples used for performance verification could cause downtime in the product manufacturing line, leading to a decrease in production efficiency.

[0010] Therefore, the present invention aims to provide an article inspection device and a method for verifying its performance that can accurately and automatically detect a decline in inspection performance, thereby reliably maintaining inspection performance while effectively reducing the number of time-consuming manual performance checks required. [Means for solving the problem]

[0011] (1) To achieve the above objective, the X-ray inspection apparatus according to the present invention comprises: a conveyor belt for transporting an article with an article placed on it; an X-ray detector that detects X-rays that have passed through the article and outputs a detection signal capable of forming an image; an image processing unit that performs predetermined image processing on an X-ray inspection image based on the detection signal and outputs a processed image having image features indicating the quality state of the article; and a determination unit that determines whether the quality state of the article is good or bad based on the processed image, wherein the X-ray inspection apparatus performs light receiving sensitivity correction to adjust the value of the detection signal from the X-ray detector when the X-rays pass through the conveyor belt without passing through the article to a predetermined reference value for a plurality of light receiving elements, The system further comprises: a sensitivity correction unit that outputs the corrected X-ray inspection image; an image quality change detection unit that detects changes in the image quality of the X-ray inspection image or the occurrence of factors causing such changes; a reference image storage unit that stores a reference image of a good product of the article; an evaluation image generation unit that generates an evaluation image by combining at least the reference image and the corrected X-ray inspection image output from the sensitivity correction unit when the image quality change detection unit detects a change in image quality or factors causing such changes; and an inspection performance evaluation unit that performs predetermined image processing on the evaluation image generated by the evaluation image generation unit using the image processing unit and then determines whether the judgment result of the judgment unit is appropriate or not.

[0012] With this configuration, in the present invention, when a change in the image quality of an X-ray inspection image or a factor causing such a change occurs, and this change or factor is detected by the image quality change detection unit, the evaluation image generation unit generates an evaluation image by combining at least a reference image and the corrected X-ray inspection image output from the sensitivity correction unit. The inspection performance evaluation unit then causes the image processing unit to perform predetermined image processing on the evaluation image and then causes the judgment unit to determine whether the item is good or bad, thereby determining whether the judgment result is appropriate. Therefore, it becomes possible to accurately and automatically detect whether or not there is a decrease in inspection performance. As a result, it becomes possible to reliably maintain inspection performance while effectively reducing the number of time-consuming manual performance checks.

[0013] (2) In a preferred embodiment of the present invention, the reference image storage unit may be configured to store at least the master work image used for setting the predetermined image processing conditions as a reference image for determining changes in the image quality of the X-ray inspection image.

[0014] This approach makes it possible to create evaluation images using reference images that reliably meet predetermined image processing conditions, and enables more accurate automatic detection of whether or not there is a decrease in inspection performance when a change in the image quality of an X-ray inspection image or the occurrence of a factor causing such a change is detected.

[0015] (3) In a preferred embodiment of the present invention, the reference image storage unit may be configured to store good product images of articles that the determination unit has determined to be good products as reference images for determining changes in the image quality of the X-ray inspection image.

[0016] This configuration can be used when a good image of an item that is equivalent to or better than the masterwork item can be created through predetermined image processing, for example, when inspecting other types of items similar to the masterwork item under predetermined image processing conditions. When a change in the image quality of the X-ray inspection image or the occurrence of a factor causing such a change is detected, it becomes possible to more accurately and automatically detect whether there is a decrease in inspection performance for other types of items.

[0017] (4) In a preferred embodiment of the present invention, the image quality change detection unit may be configured to detect a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the total X-ray irradiation time by the X-ray generator that irradiates the article with X-rays has elapsed for a predetermined time.

[0018] This configuration can be used in cases where the equipment characteristics cause a significant deterioration in the image quality of X-ray examination images once a predetermined total X-ray irradiation time by the X-ray generator has elapsed, and it enables effective automatic detection of this deterioration in image quality before it occurs.

[0019] (5) In a preferred embodiment of the present invention, the image quality change detection unit may be configured to detect a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the brightness value indicated by the detection signal of the X-ray detector falls below a predetermined value at the start of sensitivity correction of the X-ray detector.

[0020] This configuration allows for the accurate and automatic detection of a decline in inspection performance when the brightness value indicated by the X-ray detector's detection signal falls below a predetermined value at the start of sensitivity correction of the X-ray detector, resulting in a very high probability of a decrease in the image quality of the X-ray inspection image.

[0021] (6) In a preferred embodiment of the present invention, the image quality change detection unit may be configured to acquire a brightness detection signal of X-rays that have passed through only the non-article-placed area of ​​the transport belt from the X-ray detector, and to detect a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the average value of the brightness detection signal of X-rays that have passed through only the non-article-placed area falls outside a predetermined range.

[0022] In this case, when the average value of the brightness detection signal of X-rays transmitted only through the non-object-placed area of ​​the conveyor belt falls outside a predetermined range, and there is a very high probability that the image quality of the X-ray inspection image will deteriorate, it becomes possible to accurately and automatically detect the deterioration of inspection performance in advance.

[0023] (7) In a preferred embodiment of the present invention, the image quality change detection unit acquires, from the X-ray detector, a luminance detection signal of X-rays that have transmitted only through an article non-placement region of the conveyor belt, and may be configured to detect a change in image quality of the X-ray inspection image or occurrence of a factor causing the change when a noise level of the luminance detection signal of X-rays that have transmitted only through the article non-placement region exceeds a predetermined level value.

[0024] In this case, when the noise level of the luminance detection signal of X-rays that have transmitted only through the article non-placement region of the conveyor belt exceeds a predetermined level value and the probability that the image quality of the X-ray inspection image will degrade is extremely high, a reduction in inspection performance can be accurately and automatically detected in advance before it occurs.

[0025] (8) In a preferred embodiment of the present invention, the image quality change detection unit calculates a defect occurrence rate for a predetermined number of inspected articles W based on the quality determination result of the determination unit, and may be configured to detect a change in image quality of the X-ray inspection image or occurrence of a factor causing the change when the defect occurrence rate exceeds a predetermined defect occurrence rate.

[0026] In this case, when the defect occurrence rate for a predetermined number of inspected articles W suddenly increases, it is estimated that there is a high probability that degradation of the image quality of the X-ray inspection image has occurred, and by detecting the occurrence of a factor causing a change in image quality, a reduced performance state can be quickly and accurately automatically detected and confirmed.

[0027] (9) In a preferred embodiment of the present invention, the image quality change detection unit may be configured to detect a change in image quality of the X-ray inspection image or occurrence of a factor causing the change when the temperature of the atmosphere surrounding the X-ray detector has changed by a predetermined amount compared to the temperature at the time of sensitivity correction of the X-ray detector.

[0028] In this case, for example, a temperature sensor for monitoring the temperature of the atmosphere surrounding the X-ray detector is provided, and when the temperature changes beyond a predetermined allowable range from the temperature at the time of sensitivity correction, it is estimated that there is a high probability that degradation of the image quality of the X-ray inspection image has occurred, and by detecting the occurrence of a factor causing a change in image quality, a reduced performance state can be quickly and accurately automatically detected and confirmed.

[0029] (10) A method for confirming the performance of an article inspection apparatus according to the present invention, in order to achieve the above objective, a method for confirming the inspection performance of an X-ray inspection apparatus comprising: a conveyor belt for transporting an article with an article placed on it; an X-ray detector that detects X-rays that have passed through the article and outputs a detection signal capable of forming an image; an image processing unit that performs predetermined image processing on an X-ray inspection image based on the detection signal and outputs a processed image having image features indicating the quality state of the article; and a determination unit that determines whether the quality state of the article is good or bad based on the processed image, wherein the method is to perform photosensitivity correction to adjust the values ​​of the detection signals from the X-ray detector when the X-rays pass through the conveyor belt without passing through the article to a predetermined reference value for a plurality of photoreceiving elements. The present invention further includes: a sensitivity correction step of outputting the corrected X-ray inspection image; an image quality change detection step of detecting the occurrence of factors that cause changes in the image quality of the X-ray inspection image; a reference image storage step of storing a reference image of a good product of the article; an evaluation image generation step of generating an evaluation image by combining at least the reference image and the corrected X-ray inspection image output in the sensitivity correction step when a change in image quality or factors that cause changes in image quality are detected by the image quality change detection step; and an inspection performance evaluation step of performing predetermined image processing on the evaluation image generated in the evaluation image generation step and then determining whether the determination result in the determination unit is appropriate.

[0030] With this configuration, in the present invention, when a change in the image quality of an X-ray inspection image or a factor causing such a change occurs, and this change or factor is detected in the image quality change detection step, an evaluation image is generated in the evaluation image generation step by combining at least a reference image and a corrected X-ray inspection image output from the sensitivity correction unit. In the inspection performance evaluation step, the image processing unit is made to perform predetermined image processing on the evaluation image, and then the judgment unit is made to determine whether the item is good or bad, thereby determining whether the judgment result is appropriate or not. Therefore, it becomes possible to accurately and automatically detect whether or not there is a decrease in inspection performance, and as a result, it becomes possible to reliably maintain inspection performance while effectively reducing the number of time-consuming manual performance checks. [Effects of the Invention]

[0031] According to the present invention, it is possible to provide an article inspection device and a method for verifying its performance that can accurately and automatically detect a decline in inspection performance, thereby reliably maintaining inspection performance while effectively reducing the number of time-consuming manual performance checks. [Brief explanation of the drawing]

[0032] [Figure 1] This is a schematic diagram of the main components of an article inspection device according to one embodiment of the present invention. [Figure 2] This is an explanatory diagram of the setting operation screen for automatic setting of each product type in an item inspection device according to one embodiment of the present invention. [Figure 3] This flowchart shows the general setting procedure for automatic setting of each product type in an item inspection device according to one embodiment of the present invention. [Figure 4] This flowchart shows the processing procedure for performance verification in sensitivity correction immediately after starting operation or product changeover in an item inspection device according to one embodiment of the present invention. [Figure 5] This flowchart shows the process for verifying performance during inspection operation after starting operation or product changeover in an item inspection device according to one embodiment of the present invention. [Figure 6] This is an explanatory diagram of the image files of defective parts for each product type used to generate evaluation images for NG judgment in an item inspection device according to one embodiment of the present invention. [Modes for carrying out the invention]

[0033] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings.

[0034] [One embodiment] Figures 1 to 6 show an article inspection device according to one embodiment of the present invention.

[0035] First, let me explain the structure.

[0036] As shown in Figure 1, an article inspection device 1 according to one embodiment of the present invention has an article transport unit 10, an X-ray imaging unit 20, a control unit 30, and a display operation unit 40, and constitutes part of an article inspection system that includes a sorting device and the like (details not shown) located downstream of the article transport unit 10.

[0037] This item inspection device 1 is a device that inspects an item W to be inspected using penetrating X-rays. For example, it has a foreign object detection function that can determine whether or not foreign matter is mixed in the item W to be inspected using X-rays, or it has functions such as missing item inspection, mass inspection, inspection of the shape of the item W to be inspected, such as thickness and length, and detection of packaging defects such as contents getting caught in the seal.

[0038] The item transport unit 10 is an inspection conveyor that transports items W in the direction of the rightward arrow (transport direction) in Figure 1. For example, by motor-driving one of the rollers 12 or 13 that are stretched over a loop-shaped inspection belt 11, the item W placed on the transport path 11a, which is the section above the belt, is transported in that position and passed through the inspection area of ​​the X-ray imaging unit 20. In addition, a front conveyor 14 and a rear conveyor 15 that operate at the same transport speed are provided before and after the item transport unit 10, and an item detection sensor 28 is provided immediately after the transfer section from the front conveyor 14 to the item transport unit 10 to detect the item W immediately after it has been brought onto the transport path 11a.

[0039] The X-ray imaging unit 20 has an X-ray generator 21 and an X-ray detector 23 positioned with the transport path 11a of the article transport unit 10 in between. In this case, the X-ray generator 21 and X-ray detector 23 are positioned opposite each other while being separated vertically, but they may also be positioned so as to be separated both vertically and horizontally.

[0040] The X-ray generator 21, although not shown in detail, has, for example, an X-ray tube 22 inside a metal box, and the X-ray tube 22 is immersed in insulating oil for cooling inside the box. This X-ray generator 21 is an X-ray irradiation unit that irradiates X-rays from the X-ray tube 22 toward a predetermined inspection area in the transport path 11a of the article W.

[0041] The X-ray tube 22 is positioned such that its axial direction is oriented approximately parallel to the predetermined transport direction. On its cathode side, a negative DC potential is applied to light up a filament to a high temperature, causing electrons to be emitted and focused by a focusing electrode. On its anode side, a positive DC potential is applied to the target, accelerating the electrons from the filament with a high voltage and causing them to collide with the target, thereby generating X-rays within a predetermined energy range from the target.

[0042] The X-rays generated by the X-ray tube 22 are irradiated in a fan-beam shape, directed downwards from the X-ray window at the bottom of the box towards the inspection area into which the item W is loaded, and spreading in a line scanning direction perpendicular to the transport direction. The anode of the X-ray tube 22 may be of a fixed or rotating type.

[0043] The X-ray imaging unit 20 also includes a filament power supply circuit (not shown) and a high-voltage circuit that applies a high voltage between the filament of the X-ray tube 22 and the target.

[0044] The X-ray detector 23, although not shown in detail, is a line sensor positioned, for example, directly beneath the transport path 11a of the inspection belt 11. It comprises a scintillator that absorbs and emits X-rays of a predetermined energy (wavelength, penetrating power), and a photodiode array consisting of N (for example, several hundred) light-receiving elements arranged in a direction perpendicular to the transport direction of the article W to receive light (scintillation light) from the scintillator. This X-ray detector 23 absorbs X-rays that are irradiated onto the article W and transmitted through it, causing it to emit light according to the transmission intensity of the X-rays, and outputs an electrical signal corresponding to the amount of light received by the photodiode at predetermined scanning cycles. It should be noted that the X-ray detector 23 is not limited to this indirect conversion method that indirectly converts X-rays into electrical signals; a direct conversion method is also possible.

[0045] The photodiode array of the X-ray detector 23 stores the photocurrents generated simultaneously by each of the N photodetectors for a predetermined storage time, and outputs a brightness detection signal Lx, which is a voltage signal, based on the charge corresponding to the product of the photocurrent and the storage time.

[0046] The control unit 30, although its detailed configuration is not shown, is hardware-configured to include, for example, a microcomputer having a CPU, ROM, RAM, and I / O interface, an auxiliary storage device that stores control programs for performing various functions in a readable format in cooperation with the ROM, and timer circuits, driver circuits, etc. The CPU executes predetermined arithmetic processing and the control program while exchanging data with the RAM, etc., according to the software such as control programs and setting information stored in the ROM, etc. The hardware may also include FPGA (Field Programmable Gate Array) or DSP (Digital Signal Processor), etc. Furthermore, the various functions referred to herein are the functions of the various functional units and means for X-ray output control, X-ray image data generation, inspection control, and display output control, etc., as described below.

[0047] This control unit 30 has a transport control function that controls the transport speed and transport interval of articles W by the inspection belt 11 in the article transport unit 10, and an inspection control function that controls the X-ray irradiation intensity and irradiation period in the X-ray imaging unit 20, and controls the X-ray detection period of the X-ray detector 23 and the detection period of each article W according to the transport speed of the articles W. The configuration of the transport control function is the same as known, so its detailed illustration is omitted here.

[0048] First, the control unit 30, which comprises multiple functional units required for the performance of the inspection control function, is configured to include an inspection image acquisition unit 31, a belt surface correction unit 32, an image processing unit 33, an inspection parameter variable setting unit 34, and a determination unit 35.

[0049] Specifically, the inspection image acquisition unit 31 sequentially detects X-rays passing through the item to be inspected W during transport using an X-ray line sensor, an X-ray detector 23, and outputs a brightness detection signal Lx from the photodiode array of the X-ray detector 23, enabling the acquisition of multi-level X-ray inspection image Dpx image data corresponding to the X-ray transmission amount distribution.

[0050] Furthermore, the belt surface correction unit 32 is a sensitivity correction unit that corrects the value of the brightness detection signal Lx from the X-ray detector 23 to a white reference value for each of the multiple photoreceiving elements when the X-rays from the X-ray generator 21 pass only through the transport path 11a, which is the belt surface before the item W is loaded (when there is no item W), that is, it performs light reception sensitivity correction on the belt surface (so-called shading correction), and outputs the X-ray inspection image Dpw after the light reception sensitivity correction. Hereinafter, the light reception sensitivity correction on the belt surface by the belt surface correction unit 32 will be simply referred to as belt surface correction.

[0051] The image processing unit 33 performs a predetermined filter process on the X-ray inspection image Dpx, which has been corrected for light reception sensitivity and is acquired from the inspection image acquisition unit 31 via the belt surface correction unit 32. This process extracts image features corresponding to the morphological characteristics of the defective parts that are the target of the product inspection, and performs image processing to facilitate the measurement of the feature quantities of the extracted image features. Specifically, the image processing unit 33 has a predetermined inspection algorithm set and stored, which combines multiple image processing filters, in order to perform a predetermined product inspection based on the image data of the X-ray inspection image Dpx after light reception sensitivity correction. It outputs a processed image Dpf that has undergone such filtering.

[0052] The inspection algorithm referred to herein is a processing program for extracting image features necessary for detecting defective parts during inspection from the image data of the X-ray inspection image Dpx of item P. If the inspection algorithm includes a filter for detecting foreign objects, that filter is, for example, a feature extraction filter that enhances the contours (edges) of foreign objects in the X-ray inspection image Dpx after light sensitivity correction, such as a differential filter like a Sobel filter, which enhances the edges of foreign objects by applying differential processing based on a predetermined calculation formula to the neighborhood region of the pixel of interest.

[0053] Furthermore, feature measurement, which determines the feature quantities of image features, is a process that measures the image feature quantities necessary for the judgment process in the judgment unit 35 by performing calculations on the X-ray inspection image Dpx, which has been processed in a way that is advantageous for feature extraction by the image processing unit 33, for example, grayscale features, color features, shape features, etc.

[0054] The determination unit 35 performs a determination process to determine whether or not an item P has a predetermined quality state based on the measurement data of feature quantities extracted by the image processing unit 33. For example, it performs a determination process to determine whether or not there are foreign objects mixed in, whether or not there are missing parts, and whether or not the shape, size, or storage condition of the contents is acceptable. Based on the measurement data of feature quantities of the processed image Dpf, the determination unit 35 detects the characteristic shapes of defective parts and foreign objects detected in the item P, and compares the characteristic quantities of the detected target, such as area, contour length, and density sum, with predetermined judgment criteria values ​​(hereinafter referred to as predetermined judgment criteria). This determines whether or not a local characteristic shape corresponding to a foreign object or defective part that satisfies the judgment conditions is included in the item P.

[0055] The determination unit 35 further displays and outputs the pass / fail information (OK or NG) for each item W using the display output means 41 of the operation display unit 40, or it can also perform other types of output (notification sound, message voice, data transmission output to an external source) in conjunction with that output.

[0056] The control unit 30 also includes a reference image storage unit 36, an image quality change factor detection unit 37, an evaluation image generation unit 38, and an inspection performance evaluation unit 39 as a performance verification control function unit capable of performing inspection performance verification.

[0057] Here, the reference image storage unit 36 ​​is a means for storing X-ray image data acquired as an inspection image of a representative workpiece of the item W, and stores at least the image of the master workpiece used for setting conditions for predetermined image processing such as filtering used in the image processing unit 33 as a reference image Pmw for determining changes in the image quality of the X-ray inspection image Dpx.

[0058] The reference image storage unit 36 ​​may store one of the good product images of the item W that the determination unit 35 has determined to be good (OK) as a reference image Pmw for each product type to determine changes in the image quality of the X-ray inspection image Dpx.

[0059] Specifically, as shown in the reference image registration operation screen 50 in Figures 1 and 2, when automatically setting various inspection parameters in the variable inspection parameter setting unit 34 according to the type of item W, the item W (product) is transported multiple times and X-ray images are taken multiple times, and the images are saved in the reference image storage unit 36. From the multiple work images Pw (overall images) which are multiple X-ray inspection images of the captured item W, a master work image or other reference image Pmw that can be used as a good product image suitable for inspection is selected, and the detection level of the image density (luminance value) suitable for image acquisition can be set and saved. The automatic setting referred to here will be described later.

[0060] In Figure 2, for example, with the work image Pw in the thick-bordered area of ​​the operation screen 50 selected by touch operation, the master work save button 54b is pressed to save the reference image Pmw. In the same figure, the operation screen 50 has a display area 52 below the uppermost operating status display area 51 where the current operating mode is displayed, and below that, an inspection image display area 53 where the X-ray inspection image Dpx of the X-ray imaged item W is displayed, and a display area 54 where information on the operation content and target of the operation related to the current operating mode is displayed. In addition, the operation input section display area 55 at the bottom of the operation screen 50 displays operation input sections such as a "Next" button to transition the display screen content of the operation screen 50 in a predetermined procedure, and a "Cancel" button to instruct the cancellation of the current operation. Then, in the operating status display area 51, the leftmost side of the diagram shows whether the item inspection device 1 is operating or stopped, and common information applicable to both states is displayed to the right of it. The X-ray inspection image Dpx of the item W is displayed in the inspection image display area 53, and the number of stored work images Pw captured during automatic setup (in the display bar 54a of the same diagram, the number of stored images is 9, and the number of images that can be stored is 10) is displayed in the display area 54. Under these conditions, the selection and saving operation of the image to be used as the reference image Pmw is performed.

[0061] Returning to Figure 1, the image quality change factor detection unit 37 is a means (image quality change detection unit) for detecting changes in the image quality of an X-ray inspection image or the occurrence of factors causing such changes. For example, when the total power supply time to the X-ray detector 23 has elapsed for a predetermined time set as the service life, it is assumed that a factor causing an image quality change that degrades the image quality of the X-ray inspection image Dpx has occurred, and the unit detects, or estimates, the occurrence of such a factor.

[0062] Furthermore, the image quality change factor detection unit 37 detects the occurrence of an image quality change factor when the brightness value indicated by the brightness detection signal Lx from the X-ray detector 23 falls below a predetermined value at the start of sensitivity correction of the X-ray detector 23, which is considered to be a cause of change in the image quality of the X-ray inspection image Dpx.

[0063] Furthermore, the image quality change factor detection unit 37 acquires a portion of the brightness detection signal Lx of X-rays that have passed through only the non-article-placed area of ​​the transport belt 11 (the area close to the white reference level during sensitivity correction) from the X-ray detector 23. When the average value of the portion of the brightness detection signal Lx of X-rays that have passed through only the non-article-placed area falls outside a predetermined range, the unit detects the occurrence of an image quality change factor, which is considered to be a change in the image quality of the X-ray inspection image Dpx.

[0064] In addition, the image quality change factor detection unit 37 acquires a portion of the brightness detection signal Lx of X-rays that have passed through only the non-article-placed area of ​​the transport belt 11 from the X-ray detector 23. When the noise level of that portion of the brightness detection signal Lx of X-rays that have passed through only the non-article-placed area exceeds a predetermined level value that causes image quality degradation, the unit detects the occurrence of an image quality change factor, which is considered to be a factor that degrades the image quality of the X-ray inspection image Dpx.

[0065] The image quality change factor detection unit 37 also calculates the defect rate for the most recent predetermined number of items W based on the pass / fail judgment results of the judgment unit 35 for multiple items W. When this defect rate exceeds a predetermined defect rate, it detects the occurrence of an image quality change factor that degrades the image quality of the X-ray inspection image Dpx.

[0066] The image quality change factor detection unit 37 is also equipped with a temperature sensor (not shown) near the X-ray detector 23 to monitor the temperature of the atmosphere surrounding the X-ray detector 23. When a predetermined temperature change (a temperature change exceeding a predetermined allowable range) occurs compared with the temperature at the time of sensitivity correction of the X-ray detector 23, the unit detects the occurrence of an image quality change factor that degrades the image quality of the X-ray inspection image Dpx.

[0067] The evaluation image generation unit 38 is a means for generating an evaluation image Pev (=Pmw+Pdt) by combining the belt surface corrected image Pdt from the belt surface correction unit 32 and the reference image Pmw from the reference image storage unit 36 ​​through a predetermined image synthesis process when the image quality change factor detection unit 37 detects a change in image quality or the occurrence of a factor causing a change in image quality, or a means for generating an evaluation image PwNgi (=Pmw+Pdt+Ngi) which further combines an image Ngi containing only a predetermined defective area to give it the characteristics of a defective image. The predetermined image synthesis process referred to herein is, for example, an image processing process in which a portion of the pixel region in the image area of ​​the belt surface image in the reference image Pmw, where the luminance is within a predetermined range effective for synthesis, is converted into a portion of the pixel values ​​of the belt surface corrected image Pdt from the belt surface correction unit 32 when the occurrence of an image quality change factor is detected by the image quality change factor detection unit 37, or an image processing process that further deforms the image Ngi of a predetermined defective area to have image characteristics. More specifically, this can be a process that replaces or interpolates the pixel values ​​(luminance values) in that pixel region, or performs texture synthesis. The number and position of the belt surface images synthesized when an image quality change factor occurs relative to the reference image Pmw are not particularly limited, but it is preferable that at least one be set in a position suitable for the above-mentioned synthesis process and quality judgment according to the reference image Pmw.

[0068] In order to obtain the image characteristics of a predetermined defective area image Ngi, the image Ngi of only the predetermined defective area is, for example, as shown in Figure 6, a plurality of images prepared as images of foreign samples to be detected, substitute test pieces, or other defective areas. In the same figure, images of multiple spherical test pieces made of Sus (stainless steel) with diameters from 0.3 mm to 1.0 mm are prepared as defective area image Ng1, which corresponds to a foreign object that should be detected if it is mixed into product W of type 1. Also in the same figure, images of multiple spherical test pieces made of glass with diameters from 1.0 mm to 8.0 mm are prepared as defective area image Ng2, which corresponds to a foreign object that should be detected if it is mixed into product W of type 2. Images of bone samples that may remain in product W are prepared as defective area image Ng3, which corresponds to a foreign object that should be detected if it is mixed into product W of type 3. Images of defective areas that may occur in product W, such as defective seals on packaging packages, are prepared as defective area image Ng9, which corresponds to a defective area that should be detected if it occurs in product W of type 9. Of course, other images of defects may be included.

[0069] When the image quality change factor detection unit 37 detects a change in the image quality of the inspection image Dpx, the inspection performance evaluation unit 39 has the image processing unit 33 perform predetermined image processing on the evaluation image Pev and / or PwNgi generated by the evaluation image generation unit 38, and then determines whether the judgment result of the judgment unit 35 is OK / NG, that is, whether the evaluation image Pev that should be judged as OK is judged as OK, or / or the judgment result of the evaluation image PwNgi that should be judged as NG is judged as NG, and whether an accurate performance judgment has been made.

[0070] The display operation unit 40 is composed of a touch panel having a display output means 41 and an operation input means 42. However, the display output means 41 may also have the functions of an output means for voice or notification sound or a data transmission output means, as described above. Furthermore, the operation input means 42 may also have the functions of an audio input or data reception means (not shown).

[0071] The article inspection apparatus 1 of this embodiment includes, as described above, a reference image storage unit 36 ​​that stores a reference image Pmw of a good article W, an image quality change factor detection unit 37, an evaluation image generation unit 38 that can generate an evaluation image Pev (=Pmw+Pdt) by combining the belt surface corrected image Pdt when an image quality change factor occurs, as detected by the image quality change factor detection unit 37, with the reference image Pmw, and an inspection performance evaluation unit 39 that causes the image processing unit 33 to perform predetermined image processing on the evaluation image Pev for OK judgment and / or the evaluation image PwNgi for NG judgment generated by the evaluation image generation unit 38 when an image quality change factor is detected, and determines and verifies whether the judgment result OK / NG of the judgment unit 35 is appropriate.

[0072] Next, we will describe one embodiment of a method for verifying the inspection performance of this X-ray inspection device.

[0073] The method for verifying the performance of the article inspection apparatus according to this embodiment includes: an image quality change detection step for detecting the occurrence of factors that cause changes in the image quality of the X-ray inspection image Dpx; a reference image storage step for storing a reference image Pmw of a good article W in a reference image storage unit 36; an evaluation image generation step for generating an evaluation image Pev (=Pmw+Pdt) by combining the belt surface corrected image Pdt at the time the image quality change factor detection unit 37 detects the occurrence of a factor that causes changes in image quality with the reference image Pmw, and / or further generating an evaluation image PwNgi (=Pmw+Pdt+Ngi) by additionally combining an image Ngi of a predetermined defective part to give it defective image characteristics; and an inspection performance evaluation step for determining whether the judgment result is OK or NG in the judgment unit 35 after performing predetermined image processing on the evaluation image Pev or / or PwNgi generated in the evaluation image generation step when a factor that causes changes in image quality is detected in the image quality change detection step.

[0074] Below, one embodiment of the method for verifying the inspection performance of this X-ray inspection device will be described in relation to the specific control processing details in this embodiment, as shown in Figures 3 to 5.

[0075] In the automatic setting process shown in Figure 3, first, product information such as the product name of item W is set (step S11), and after the transport conditions such as the transport speed and transport form (boxed, loose) of item W are set (step S12), inspection items such as foreign object detection algorithm, shape inspection, jamming inspection, and mask setting are set (step S13). Next, the product is actually transported and the X-ray output is set using the operation screen 50 shown in Figure 2, and the detection limits of the foreign object detection algorithm are adjusted (step S14). Next, sorting conditions are set, such as the operating timing of the subsequent sorting device (not shown) (step S15).

[0076] When such automatic settings are performed for the product being inspected, the performance verification process shown in Figure 4 is executed at the start of operation or when switching product varieties, and during the subsequent inspection operation, the performance inspection process shown in Figure 5 is executed.

[0077] First, as shown in Figure 4, when the operation of the item inspection device 1 is started or the type of item W is changed (step S21), in order to perform sensitivity correction in the belt surface correction unit 32, X-rays irradiated from the X-ray generator 21 that have passed only through the non-item-placed area of ​​the transport path 11a are detected by the X-ray detector 23, and the brightness detection signal Lx output from the X-ray detector 23 is acquired by the inspection image acquisition unit 31 (step S22).

[0078] Next, based on the luminance detection signal Lx values ​​from the N photodetectors of the X-ray detector 23 acquired by the inspection image acquisition unit 31 for sensitivity correction, the image quality change factor detection unit 37 performs a process to detect image quality changes or factors causing image quality changes, and determines whether or not at least a factor causing image quality changes has occurred (step S23 (image quality change detection step)).

[0079] The factors causing changes in image quality include, as mentioned above, the total power supply time to the X-ray detector 23 exceeding a predetermined time set as the service life, the brightness value indicated by the brightness detection signal Lx of the X-ray detector 23 falling below a predetermined value at the start of sensitivity correction of the X-ray detector 23, the average value of a portion of the brightness detection signal Lx of X-rays transmitted only through the non-article-placed area of ​​the conveyor belt 11 falling outside a predetermined range, the noise level of a portion of the brightness detection signal Lx of X-rays transmitted only through the non-article-placed area exceeding a predetermined level value that causes a decrease in image quality, and the defect rate of the most recent predetermined number of items W exceeding a predetermined defect rate.

[0080] If it is determined that an image quality change factor has occurred (if YES in step S23), then an evaluation image Pev (=Pmw+Pdt) is generated by combining at least the belt surface corrected image Pdt at that time with the reference image Pmw, and / or an evaluation image PwNgi (=Pmw+Pdt+Ngi) is created by further combining an image Ngi of a predetermined defective area to give it the characteristics of a defective image (step S24 (evaluation image generation step)). The inspection performance evaluation unit 39 then uses the evaluation image Pev for OK determination and / or the evaluation image PwNgi for NG determination to have the image processing unit 33 perform predetermined image processing, and then the determination unit 35 determines whether the determination result is OK or NG (step S25 (inspection performance evaluation step)).

[0081] In this case, if the judgment result of the judgment unit 35 for the evaluation image Pev used for OK judgment is OK, the inspection performance evaluation unit 39 determines that the good product detection performance of the product inspection device 1 is normal and there is no performance degradation. Also, when using the evaluation image PwNgi used for NG judgment, if the judgment result of the judgment unit 35 for the evaluation image PwNgi which has defective image characteristics is NG, the inspection performance evaluation unit 39 determines that the defective product detection performance of the product inspection device 1 is normal and there is no performance degradation (if NO is obtained in step S26).

[0082] On the other hand, if the judgment result of the judgment unit 35 for the evaluation image Pev for OK judgment is NG, or if the judgment result of the judgment unit 35 for the evaluation image PwNgi for NG judgment is OK, then the inspection performance evaluation unit 39 determines that the inspection performance of the item inspection device 1 is not normal and that there is a performance degradation (if YES in step S26), and outputs an operation confirmation request to the display operation unit 40 (step S27).

[0083] Furthermore, based on the brightness detection signal Lx values ​​from the N photodetectors of the X-ray detector 23 acquired by the inspection image acquisition unit 31 for sensitivity correction, the image quality change factor detection unit 37 performs image quality change factor detection processing. If it is determined that no image quality change factors have occurred (if NO in step S23), then a sensitivity correction process is performed to align each of the N photodetectors to the white reference value based on the brightness detection signal Lx values ​​from the X-ray detector 23 acquired by the inspection image acquisition unit 31 for sensitivity correction (step S28).

[0084] Next, by performing the aforementioned X-ray output settings using the operation screen 50 shown in Figure 2, a master image that will become the reference image Pmw for the selected product W can be stored in the reference image storage unit 36 ​​(step S29 (reference image storage step)).

[0085] When proceeding to the subsequent inspection run, as shown in Figure 5, the first step is to check whether the predetermined inspection completion conditions have been met. It goes without saying that the process shown in Figure 5 is coupled to the process shown in Figure 4 by connector (A), and is executed immediately following the process shown in Figure 4.

[0086] If the predetermined inspection termination conditions are met during this inspection termination condition check (if YES is found in step S30), the process will be terminated without proceeding to the inspection run.

[0087] On the other hand, if the predetermined inspection completion conditions are not met at this time (if the result is NO in step S30), the following process, which involves checking the inspection performance during the inspection run, can be executed.

[0088] First, the item W is transported and X-ray imaged within the inspection area (step S31). After belt surface correction by the belt surface correction unit 32, the image processing unit 33 performs predetermined image processing such as filtering on the image Pdt (step S32). Based on the judgment image data after the image processing, the judgment unit 35 performs a pass / fail judgment (step S33), and the judgment result OK / NG is displayed by the display operation unit 40 (step S34).

[0089] Next, it is determined whether the number of inspections requiring check has been reached (step S35). This number of inspections requiring check is the predetermined interval for checking inspection performance, which is the number of inspections required from the previous inspection performance check until the next inspection performance check is needed.

[0090] At this point, if the number of items requiring inspection has not been reached (the result is NO in step S35), the determination step S30 to determine whether the inspection completion condition is met is executed again, and then steps S31 to S35 for inspecting each item W are repeated.

[0091] On the other hand, if the number of items requiring check has been reached at this point (if the result is YES in step S35), then a determination is made as to whether or not a factor causing a change in image quality has occurred (step S36 (image quality change detection step)).

[0092] The occurrence of image quality change factors here may be the same as in the inspection performance confirmation process at the start of operation, but it is also possible to directly detect changes in image data that can be considered as image quality degradation based on the image data of the X-ray inspection image Dpx already acquired by the inspection image acquisition unit 31, and determine the occurrence of the image quality change itself. In either case, the image quality change factor detection unit 37 performs a process to detect the image quality change or the factor causing the image quality change, thereby determining at least whether or not an image quality change factor has occurred.

[0093] If it is determined at this point that no change in image quality or factors causing a change in image quality have occurred (i.e., NO in step S36), the current process is terminated.

[0094] On the other hand, if it is determined that an image quality change or an image quality change factor has occurred (if YES in step S36), then an evaluation image Pev (=Pmw+Pdt) is generated by combining at least the belt surface corrected image Pdt at that time with the reference image Pmw, and / or an evaluation image PwNgi (=Pmw+Pdt+Ngi) is created by further combining an image Ngi of a predetermined defective area to give it the characteristics of a defective image (step S37 (evaluation image generation step)). The inspection performance evaluation unit 39 then uses the evaluation image Pev for OK judgment and / or the evaluation image PwNgi for NG judgment as evaluation images, respectively, and performs a performance evaluation to determine whether the judgment result in the judgment unit 35 is OK or NG after having the image processing unit 33 perform predetermined image processing (step S38 (inspection performance evaluation step)).

[0095] The performance evaluation at this time is the same as described above (when NO is obtained in step S26), and if the judgment result of the judgment unit 35 for the evaluation image Pev for OK judgment is OK, then it is determined that there is no performance degradation, or / or if the judgment result of the judgment unit 35 for the evaluation image PwNgi for NG judgment is NG, then it is determined that there is no performance degradation (when NO is obtained in step S39).

[0096] On the other hand, during this performance evaluation, if the judgment result of the judgment unit 35 for the evaluation image Pev used for OK judgment is NG, or if the judgment result of the judgment unit 35 for the evaluation image PwNgi used for NG judgment is OK, then the inspection performance of the item inspection device 1 is determined to be abnormal and there is a performance degradation (if YES is obtained in step S39), and a request for operation confirmation during operation is output to the display operation unit 40 (step S40).

[0097] Next, I will explain the mechanism of action.

[0098] In the article inspection apparatus 1 of this embodiment, configured as described above, when a change in the image quality of the X-ray inspection image Dpx occurs or a factor causing a change occurs, and the image quality change factor detection unit 37 detects the change or factor causing a change, the evaluation image generation unit 38 generates an evaluation image Pev (=Pmw+Pdt) by combining at least the belt surface corrected image Pdt at that time with the reference image Pmw, and / or, an evaluation image PwNgi (=Pmw+Pdt+Ngi) is generated by further combining an image Ngi of a predetermined defective area to give it the characteristics of a defective image. The inspection performance evaluation unit 39 then causes the image processing unit 33 (image processing unit) to perform predetermined image processing and then causes the determination unit 35 to determine whether the article W is good or bad, thereby determining and evaluating whether the determination result is OK or NG. Therefore, it becomes possible to accurately and automatically detect whether or not there is a decrease in inspection performance. As a result, it becomes possible to reliably maintain inspection performance while effectively reducing the number of manual operation checks required for performance verification.

[0099] Furthermore, in this embodiment, the reference image storage unit 36 ​​can store at least the master work image used to set predetermined image processing conditions as a reference image Pmw for determining changes in the image quality of the X-ray inspection image. This makes it possible to create an evaluation image Pev and / or PwNgi using a reference image Pmw that reliably conforms to the predetermined image processing conditions, and enables more accurate automatic detection of whether or not there is a decrease in inspection performance when a change in the image quality of the X-ray inspection image Dpx or the occurrence of a factor causing a change is detected.

[0100] Furthermore, in this embodiment, the good image of the item W that the determination unit 35 has determined to be OK can also be used as the reference image Pmw. Therefore, if a good image of the item W that is equivalent to or better than the master work item W can be created through predetermined image processing, this can be used, for example, when inspecting other types of items W that are similar to the master work under predetermined image processing conditions. When a change in the image quality of the X-ray inspection image Dpx or the occurrence of a factor causing a change is detected, it becomes possible to more accurately and automatically detect whether there is a decrease in inspection performance for other types of items W.

[0101] In addition, in this embodiment, if the device configuration and characteristics are such that the image quality of the X-ray inspection image Dpx begins to deteriorate significantly after a predetermined total energizing time (total X-ray irradiation time) to the X-ray generator 21 has elapsed, it becomes possible to effectively and automatically detect the deterioration of the image quality of the X-ray inspection image Dpx in advance.

[0102] Furthermore, in this embodiment, when the brightness value indicated by the brightness detection signal Lx of the X-ray detector 23 falls below a predetermined value at the start of sensitivity correction of the X-ray detector 23, and the probability of a decrease in the image quality of the X-ray inspection image Dpx becomes very high, a decrease in inspection performance can be accurately and automatically detected in advance.

[0103] In this embodiment, if the average brightness value of the brightness detection signal Lx of X-rays transmitted only through the non-article-placed area of ​​the conveyor belt 11 falls outside a predetermined range, and the probability of a decrease in the image quality of the X-ray inspection image Dpx becomes very high, this is detected as the occurrence of a performance degradation factor, thus enabling accurate and proactive automatic detection of a decline in inspection performance.

[0104] Furthermore, in this embodiment, when the noise level of the luminance detection signal Lx of X-rays transmitted only through the non-article-placed area of ​​the conveyor belt 11 exceeds a predetermined level value, and the probability of a decrease in the image quality of the X-ray inspection image Dpx becomes very high, this is detected as the occurrence of a performance degradation factor, thus enabling accurate and proactive automatic detection of a decline in inspection performance.

[0105] Furthermore, in this embodiment, if the defect rate of an item W with a predetermined number of inspections, for example, the number of inspections requiring checks corresponding to the interval for checking the inspection performance described above, suddenly increases, it is estimated that there is a high probability that the image quality of the X-ray inspection image Dpx has deteriorated. This allows for the detection of the cause of the change in image quality, enabling rapid and accurate automatic detection and confirmation of the performance deterioration state.

[0106] In addition, in this embodiment, by monitoring the ambient temperature of the X-ray detector 23 using a temperature sensor provided in the image quality change factor detection unit 37, it is estimated that there is a high probability that the image quality of the X-ray inspection image Dpx has deteriorated when the ambient temperature changes beyond a predetermined tolerance range from the temperature at the time of sensitivity correction. By detecting the occurrence of an image quality change factor, the performance degradation state can be quickly and accurately automatically detected and confirmed.

[0107] Thus, according to the performance verification method for the article inspection device 1 of this embodiment, it is possible to accurately and automatically detect a decline in the inspection performance of the article inspection device 1, and to reliably maintain its inspection performance while effectively reducing the number of manual operation checks required for performance verification.

[0108] In the above-described embodiment, the image processing unit 33 extracts and measures image features specific to foreign objects by performing filtering and other predetermined image processing for foreign object detection, but it is not limited to this. For example, the image processing unit 33 may, as an image processing unit, measure the volume using equivalent thickness image data of the X-ray inspection image Dpx and convert it to mass. However, in that case, the inspection performance evaluation unit 39 can use the evaluation image Pw for OK judgment, but the evaluation image PwNgi for NG judgment, which has defective image features, will not be used. On the other hand, when foreign object detection is performed, the image processing unit 33 performs image processing suitable for detecting and measuring predetermined foreign object features in the article W, and the judgment unit 35 uses only the evaluation image PwNgi for NG judgment to determine whether or not there are foreign objects in the article W depending on whether or not the predetermined foreign object features are detected and measured, and if there are foreign objects, it can be determined that there is no decrease in foreign object detection performance. Of course, the image processing unit 33 may also perform image processing suitable for detecting image features of any type of defective part.

[0109] As described above, the present invention provides an article inspection device and a performance verification method that can accurately and automatically detect a decline in inspection performance, thereby effectively reducing the number of time-consuming manual performance checks while reliably maintaining inspection performance. The present invention is useful in general for article inspection devices that perform predetermined image processing on X-ray inspection images of articles to determine the quality state of the articles, and for performance verification methods that confirm whether there is any performance decline accompanied by a decrease in the image quality of the X-ray inspection images. [Explanation of Symbols]

[0110] 1. Item inspection device 10. Goods transport section 11. Inspection belt (conveyor belt) 11a Conveyor path (section running on the belt, area where no items are placed) 12, 13 Laura 14 Front Conveyor 15. Downstream conveyor 20 X-ray imaging section 21 X-ray generator 22 X-ray tube 23 X-ray detector 28. Item detection sensor 30 Control Unit 31. Inspection Image Acquisition Unit 32 Belt surface correction unit (sensitivity correction unit) 33 Image Processing Unit 34. Variable setting unit for inspection parameters 35 Judgment section 36 Reference Image Storage Unit 37 Image quality change factor detection unit (Image quality change detection unit) 38 Evaluation Image Generation Unit 39. Inspection Performance Evaluation Department 40 Display operation section 50 Operation screen 51 Operating status display area 52 Display area 53. Inspection image display area 54 Display area 54a Display bar 54b Save Masterwork button 55 Operation Input Unit Display Area X-ray inspection image after Dpw light sensitivity correction (normal belt surface correction image) DPX X-ray examination images Lx Brightness detection signal (detection signal) NGI images (images of only the defective parts, images of the defective parts) Images of defective parts Ng1, Ng2, Ng3, and Ng9. NG (Not Acceptable / Defective) Information (Judgment Result, Defective Product Judgment) OK Pass / Fail Information (Judgment Result, Good Product Judgment) PDT belt surface correction image (corrected X-ray inspection image, X-ray inspection image after correction of light receiving sensitivity when image quality degradation factors are detected) Pev evaluation images (evaluation images for OK judgment, evaluation images for sensitivity degradation) PMW reference image (masterwork image, image of an item judged to be good quality) Pw Work Image (Overall image of the item) PwNgi evaluation images (evaluation images for NG judgment, evaluation images for sensitivity degradation) S23, S36 Step (Image quality change detection step) Steps S24 and S37 (Evaluation image generation step) S25, S38 Step (Inspection Performance Evaluation Step) S29 Step (Reference Image Storage Step) t Thickness (thickness of the article) W Goods (products to be inspected)

Claims

1. A conveyor belt (11) that transports an item (W) while it is placed on it, An X-ray detector (23) that detects X-rays transmitted through the article (W) and outputs a detection signal (Lx) capable of forming an image, An image processing unit (33) performs predetermined image processing on an X-ray inspection image (Dpx) based on the detection signal and outputs a processed image (Dpf) having image features that indicate the quality state of the article, An X-ray inspection apparatus comprising a determination unit (35) that determines whether the quality of the article is good or bad based on the processed image, A sensitivity correction unit (32) performs light receiving sensitivity correction to adjust the values ​​of the detection signals from the X-ray detector to a predetermined reference value for multiple light receiving elements when the X-rays pass through the conveyor belt without passing through the article, and outputs the corrected X-ray inspection image (Dpw). The image quality change detection unit (37) detects changes in the image quality of the X-ray inspection image or the occurrence of factors causing such changes, A reference image storage unit (36) that stores a reference image (Pmw) of a good product of the aforementioned article, When the image quality change detection unit detects a change in image quality or a factor causing the change, an evaluation image generation unit (38) generates an evaluation image (Pev and / or PwNgi) by combining at least the reference image and the corrected X-ray inspection image (Pdt) output from the sensitivity correction unit, An article inspection apparatus further comprising: an inspection performance evaluation unit (39) that performs predetermined image processing on the evaluation image generated by the evaluation image generation unit using the image processing unit and then determines whether the determination result of the determination unit is appropriate or not.

2. The article inspection apparatus according to claim 1, characterized in that the reference image storage unit stores at least the image of the master work used for setting the predetermined image processing conditions as a reference image for determining changes in the image quality of the X-ray inspection image.

3. The article inspection apparatus according to claim 1, characterized in that the reference image storage unit stores images of good articles determined by the determination unit to be good articles as reference images for determining changes in the image quality of the X-ray inspection images.

4. The article inspection apparatus according to any one of claims 1 to 3, characterized in that the image quality change detection unit detects a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the total X-ray irradiation time by the X-ray generator that irradiates the article with X-rays has elapsed for a predetermined time.

5. The article inspection apparatus according to any one of claims 1 to 3, characterized in that the image quality change detection unit detects a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the brightness value indicated by the detection signal of the X-ray detector falls below a predetermined value at the start of sensitivity correction of the X-ray detector.

6. The article inspection apparatus according to any one of claims 1 to 3, characterized in that the image quality change detection unit acquires a brightness detection signal of X-rays that have passed through only the non-article-placed area (11a) of the conveyor belt from the X-ray detector, and detects a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the average value of the brightness detection signal of the X-rays that have passed through only the non-article-placed area falls outside a predetermined range.

7. The article inspection apparatus according to any one of claims 1 to 3, characterized in that the image quality change detection unit acquires a brightness detection signal of X-rays that have passed through only the non-article-placed area of ​​the conveyor belt from the X-ray detector, and detects a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the noise level of the brightness detection signal of X-rays that have passed through only the non-article-placed area exceeds a predetermined level value.

8. The article inspection apparatus according to any one of claims 1 to 3, characterized in that the image quality change detection unit calculates the defect rate based on the good / bad judgment result of the judgment unit, and detects a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the defect rate exceeds a predetermined defect rate.

9. The article inspection apparatus according to any one of claims 1 to 3, characterized in that the image quality change detection unit detects a change in the image quality of the X-ray inspection image or the occurrence of a factor causing a change when the temperature of the atmosphere of the X-ray detector has changed by a predetermined temperature compared to the temperature at the time of sensitivity correction of the X-ray detector.

10. A method for confirming the inspection performance of an X-ray inspection apparatus comprising: a conveyor belt (11) for transporting an article (W) on which an article (W) is placed; an X-ray detector (23) for detecting X-rays that have passed through the article and outputting a detection signal capable of forming an image; an image processing unit (33) for performing predetermined image processing on an X-ray inspection image (Dpx) based on the detection signal and outputting a processed image (Dpf) having image features indicating the quality state of the article; and a determination unit (35) for determining whether the quality state of the article is good or bad based on the processed image, wherein Sensitivity correction step (S28) is performed to adjust the detection signal values ​​from the X-ray detector to a predetermined reference value for multiple photoreceiving elements when the X-rays pass through the conveyor belt without passing through the article, and to output the corrected X-ray inspection image (Dpw). Image quality change detection step (S26, S36) for detecting the occurrence of factors that cause changes in the image quality of the X-ray inspection image, A reference image storage step (S29) is performed to store a reference image (Pmw) of a good product of the aforementioned article, When a change in image quality or a factor causing the change is detected by the image quality change detection step, an evaluation image generation step (S24, S37) is performed to generate an evaluation image (Pev and / or PwNgi) by combining at least the reference image and the corrected X-ray inspection image output in the sensitivity correction step. A method for verifying the performance of an article inspection apparatus, further comprising: an inspection performance evaluation step (S25, S38) in which the image processing unit performs predetermined image processing on the evaluation image generated in the evaluation image generation step, and then determines whether the determination result in the determination unit is appropriate or not.

Images