JP6746142B2 - Optical inspection system and image processing algorithm setting method - Google Patents

Description

The present disclosure relates to an optical inspection system and an image processing algorithm setting method.

2. Description of the Related Art There is known an optical inspection device that generates a light transmission image by detecting light (X-rays, near-infrared rays, and other electromagnetic waves) transmitted through an article and inspects the article by performing image processing on the light transmission image. (For example, see Patent Document 1).

JP2012-137387A

In the optical inspection device as described above, the light transmission image is subjected to image processing based on a preset image processing algorithm. However, since the inspection conditions such as the type of the article are various, the image inspection based on the preset image processing algorithm may not be able to properly inspect the article.

Therefore, it is an object of one embodiment of the present disclosure to provide an optical inspection system and an image processing algorithm setting method capable of easily setting an image processing algorithm suitable for inspection of an article.

An optical inspection system according to an aspect of the present disclosure includes a light irradiation unit that irradiates an article with light, a light detection unit that detects light transmitted through the article, and a light transmission image based on a signal output from the light detection unit. Of the plurality of image processing algorithms classified using the inspection condition as an index, and an operator that inspects the article based on the processed image. Of at least one image processing algorithm corresponding to the inspection condition designated by the operator, and among the at least one image processing algorithm presented by the algorithm presenting unit, the image processing algorithm selected by the operator is set. An algorithm setting unit is provided, and the inspection unit performs image processing on the light transmission image based on the image processing algorithm set by the algorithm setting unit to generate a processed image.

In this optical inspection system, when the operator specifies the inspection condition, at least one image processing algorithm corresponding to the inspection condition is presented. Thereby, the operator can easily select the image processing algorithm suitable for the inspection of the article. Then, when the image processing algorithm is selected by the operator, the image processing algorithm is set, and the light transmission image is subjected to image processing based on the image processing algorithm. Thereby, the inspection of the article can be appropriately performed. Therefore, according to this optical inspection system, it is possible to easily set the image processing algorithm suitable for the inspection of the article.

In the optical inspection system according to the aspect of the present disclosure, the inspection condition may include at least one of the type of the article, the type of foreign matter that may be included in the article, the light and shade in the light transmission image, and the light irradiation output of the light irradiation unit. Good. Further, the article type may include at least one type of material, shape and size of the article. Further, the type of foreign matter may include at least one type of the material, shape and size of the foreign matter. By classifying a plurality of image processing algorithms using these as indexes, it is easy to present an image processing algorithm suitable for inspecting an article.

The optical inspection system according to an aspect of the present disclosure may further include a display unit that displays a processed image. This allows the operator to confirm in advance the effect of performing image processing on the light transmission image based on the presented image processing algorithm, and as a result, it is possible to accurately determine the image processing algorithm suitable for the inspection of the article. You can choose.

An image processing algorithm setting method according to an aspect of the present disclosure is an image processing algorithm setting method implemented in an optical inspection system, and is specified by an operator from among a plurality of image processing algorithms classified using an inspection condition as an index. Presenting at least one image processing algorithm corresponding to the inspection condition, and setting an image processing algorithm selected by the operator among the presented at least one image processing algorithm.

According to this image processing algorithm setting method, the image processing algorithm suitable for the inspection of the article can be easily set for the same reason as the above-described optical inspection system.

According to an aspect of the present disclosure, it is possible to provide an optical inspection system and an image processing algorithm setting method capable of easily setting an image processing algorithm suitable for inspection of an article.

FIG. 1 is a perspective view showing an appearance of an X-ray inspection apparatus according to an embodiment of the present disclosure. FIG. 2 is a perspective view showing a configuration inside a shield box of the X-ray inspection apparatus of FIG. FIG. 3 is a block diagram showing a functional configuration of the X-ray inspection apparatus of FIG. FIG. 4 is a diagram showing an example of an image processing algorithm used in the X-ray inspection apparatus of FIG. FIG. 5 is a flowchart showing an image processing algorithm setting method implemented in the X-ray inspection apparatus of FIG. 6A and 6B are diagrams showing processed images generated based on the presented image processing algorithm.

Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts will be denoted by the same reference symbols and redundant description will be omitted.

As shown in FIGS. 1 and 2, an X-ray inspection apparatus (optical inspection system) 1 includes a shield box 3, a conveyor 5, an X-ray irradiator (light irradiation unit) 7, an X-ray line sensor (optical). A detection unit 9 and a monitor (display unit) 11 are provided. The X-ray inspection apparatus 1 is installed in a production line of an article G such as food, and inspects the article G for the presence of foreign matter.

The shield box 3 houses the conveyor 5, the X-ray irradiator 7, and the X-ray line sensor 9. A pair of openings 3a is provided on both side surfaces of the shield box 3. Each opening 3a is closed by a shielding curtain (not shown) made of rubber containing lead, for example. This prevents the X-rays from leaking to the outside of the shield box 3 through the openings 3a.

The conveyor 5 is arranged in the shield box 3 so as to be bridged between the pair of openings 3a. The conveyor 5 conveys the article G placed on the belt 5a by rotating the endless belt 5a by a conveyor motor (not shown). As a result, the article G is carried into the shield box 3 through the one opening 3a and carried out of the shield box 3 through the other opening 3a.

The X-ray irradiator 7 is arranged in the shield box 3 so as to be located above the belt 5a. The X-ray irradiator 7 irradiates X-rays so as to cross the belt 5a along the width direction of the belt 5a. As a result, the X-ray irradiator 7 irradiates the article G conveyed by the conveyor 5 with X-rays.

The X-ray line sensor 9 is arranged in the shield box 3 so as to be located below the belt 5a. The X-ray line sensor 9 has a plurality of pixel sensors 9a arranged in a line along the width direction of the belt 5a. As a result, the X-ray line sensor 9 detects the X-ray transmitted through the article G conveyed by the conveyor 5.

The monitor 11 is, for example, a liquid crystal display, and displays various information such as processed images. The monitor 11 has a touch panel function, and functions as an interface that receives input of various conditions by an operator.

As shown in FIG. 3, the X-ray inspection apparatus 1 further includes a control unit 20. The control unit 20 has an inspection unit 21, an algorithm presenting unit 23, and an algorithm setting unit 25. The control unit 20 is configured of a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. The inspection unit 21, the algorithm presenting unit 23, and the algorithm setting unit 25 include the control unit 20. In, it is configured as a functional block.

The inspection unit 21 generates an X-ray transmission image (light transmission image) of the article G based on the signal output from the X-ray line sensor 9, performs image processing on the X-ray transmission image, and generates a processed image. .. The inspection unit 21 inspects the presence or absence of foreign matter contained in the article G based on the generated processed image. When generating the processed image, the inspection unit 21 can perform image processing on the X-ray transmission image based on at least one image processing algorithm set in advance.

Here, the image processing algorithm will be described. The image processing algorithm is a type indicating a processing procedure of image processing performed on an X-ray transmission image, and is configured by, for example, one image processing filter or a combination of a plurality of image processing filters. In the example of the image processing algorithm shown in FIG. 4, the filters C1 and C2 reduce the X-ray transmission image of the article G containing the foreign matter to generate the image 1. Subsequently, the filters F1 to F5 remove the foreign substance image from the image 1 to generate the image 2. On the other hand, the foreign matter image in the image 1 is emphasized by the filters F6 and F7 to generate the image 3. Subsequently, in the subtraction, the difference between the image 2 and the image 3 is obtained, and the processed image in which the foreign substance image is extracted is generated.

The algorithm presenting unit 23 can acquire a plurality of image processing algorithms classified by using the inspection condition as an index via a communication network such as the Internet. The algorithm presenting section 23 presents at least one image processing algorithm corresponding to the inspection condition designated by the operator among the plurality of image processing algorithms classified by using the inspection condition as an index. Note that the operator specifies the inspection conditions via the monitor 11 that functions as an interface.

The algorithm setting unit 25 sets the image processing algorithm selected by the operator among the at least one image processing algorithm presented by the algorithm presenting unit 23. That is, the algorithm setting unit 25 checks the image processing algorithm selected by the operator in addition to the at least one image processing algorithm set in advance (or instead of the at least one image processing algorithm set in advance). Set to use. The operator selects the image processing algorithm through the monitor 11 that functions as an interface.

Here, the inspection conditions will be described. The inspection conditions are various conditions for performing an inspection of the article G (inspection of the presence or absence of foreign matter contained in the article G), the type of the article G, the foreign matter that can be included in the article G (that is, the foreign matter to be detected). ), the light and shade in the X-ray transmission image, and the X-ray irradiation output (light irradiation output) of the X-ray irradiator 7. The type of the article G includes at least one type of material, shape and size of the article G. The type of foreign matter that can be included in the article G includes at least one type of material, shape, and size of the foreign matter. The light and shade in the light transmission image includes at least one of a difference in gray value between the article image and the foreign substance image, a difference in gray value between the background and the foreign substance image, and both of them.

The plurality of image processing algorithms acquired by the algorithm presenting unit 23 are classified using the inspection conditions as described above as an index. For example, the inspection condition “the type of the article G is meat” is associated with an image processing algorithm suitable for the inspection when the type of the article G is meat. An image processing algorithm suitable for the inspection when the type of foreign matter is metal is associated with the inspection condition “the type of foreign matter is metal”. The inspection condition "the difference between the grayscale values of the article image and the foreign matter image is a predetermined value (for example, 20 of the grayscale divided into 255 gradations) or more" is the grayscale of the article image and the foreign matter image. An image processing algorithm suitable for the inspection is associated when the difference between the values is equal to or larger than a predetermined value (for example, 20 out of 255 divided gradations). The inspection condition "the X-ray irradiation output of the X-ray irradiator 7 is a predetermined value (for example, 75 kV) or more", the X-ray irradiation output of the X-ray irradiator 7 is a predetermined value (for example, 75 kV) or more. The image processing algorithm suitable for the inspection when the value is

Next, an image processing algorithm setting method implemented in the X-ray inspection apparatus 1 will be described with reference to the flowchart shown in FIG. Here, a case where the article G is “block meat” and the foreign matter to be detected is “SUS (stainless steel) wire having a diameter of 0.5 mm and a length of about 2 mm” will be described.

First, when the operator specifies the inspection condition that “the type of the article G is block meat” (step S01), the algorithm presenting unit 23 selects one of the plurality of image processing algorithms classified using the inspection condition as an index. , At least one image processing algorithm corresponding to the inspection condition designated by the operator is presented (step S02). For example, 10 image processing algorithms are presented and displayed on the monitor 11.

Subsequently, when the inspection condition is further specified (step S03) and the operator specifies the inspection condition "the type of the foreign matter is the SUS line" (step S01), the algorithm presenting unit 23 first At least one image processing algorithm corresponding to the inspection condition designated by the operator is presented from the presented plurality of image processing algorithms (step S02). For example, the presented 10 image processing algorithms are narrowed down, and 5 image processing algorithms are presented and displayed on the monitor 11.

Subsequently, the inspection condition is further specified (step S03), and the operator specifies the inspection condition "the size of the foreign matter is 0.5 mm in diameter and 2 mm in length" ( In step S01), the algorithm presenting section 23 presents at least one image processing algorithm corresponding to the inspection condition designated by the operator among the plurality of image processing algorithms presented previously (step S02). For example, the presented five image processing algorithms are narrowed down, two image processing algorithms A1 and A2 are presented, and displayed on the monitor 11.

Subsequently, when the inspection condition is not further specified (step S03), the operator requests the trial use of the two image processing algorithms A1 and A2 presented by the algorithm presenting unit 23 (step S04). The operator's trial request is made via the monitor 11 functioning as an interface.

In the trial use of the two image processing algorithms A1 and A2, a plurality of foreign matter test pieces P1 to P5 (P1: “SUS wire having a diameter of 1.0 mm and a length of 2 mm”), P2: “diameter of 0.8 mm and a length of 2 mm” SUS line", P3: "0.6 mm diameter, 2 mm long SUS line", P4: "0.5 mm diameter, 2 mm long SUS line", P5: "0.4 mm diameter, 2 mm long SUS line" The block meat to which the line ") is attached is prepared as a test sample, and the X-ray inspection apparatus 1 performs the inspection based on the image processing algorithms A1 and A2.

Specifically, the inspection unit 21 performs image processing on the X-ray transmission image of the test sample based on the image processing algorithm A1 to generate a processed image, and based on the processed image, the foreign matter contained in the article G. Inspect for the presence of The inspection result including the processed image is displayed on the monitor 11 as shown in FIG. FIG. 6A shows that, as the inspection result, all the foreign matter test pieces P1 to P5 are detected.

Similarly, the inspection unit 21 performs image processing on the X-ray transmission image of the test sample based on the image processing algorithm A2 to generate a processed image, and based on the processed image, presence/absence of foreign matter contained in the article G. To inspect. The inspection result including the processed image is displayed on the monitor 11 as shown in FIG. FIG. 6B shows that, as the inspection result, the foreign matter test pieces P1 to P3 were detected, but the foreign matter test pieces P4 to P5 were not detected.

Note that the inspection unit 21 evaluates the evaluation value E (for example, E=k1דat the position of the foreign object image” for each of the processed images generated based on each of the plurality of image processing algorithms presented by the algorithm presenting unit 23. It is also possible to calculate “reaction strength”+k2דreaction weakness at a position where there is no foreign object image”, and display the plurality of image processing algorithms on the monitor 11 in the descending order of the evaluation value E. In addition, an X-ray transmission image of the article G to which the foreign matter test piece is not attached is generated, and an image corresponding to the foreign matter image is attached to the X-ray transmission image to be used as the X-ray transmission image of the test sample. May be. The evaluation value E may be calculated by averaging the evaluation values E calculated by flowing the article a plurality of times (for example, five times) in order to eliminate the influence of variations due to the deviation of the posture and the contents.

As a result of the above trial, when the image processing algorithm A1 is selected by the operator as the image processing algorithm suitable for the inspection (step S05), the algorithm setting unit 25 causes the two image processing algorithms presented by the algorithm presenting unit 23. The image processing algorithm A1 selected by the operator from among A1 and A2 is set (step S05). That is, the algorithm setting unit 25 checks the image processing algorithm A1 selected by the operator in addition to the at least one image processing algorithm set in advance (or instead of the at least one image processing algorithm set in advance). 21 to be used.

Accordingly, in the actual inspection, the inspection unit 21 performs image processing on the X-ray transmission image based on the image processing algorithm A1 set by the algorithm setting unit 25 to generate a processed image, and based on the generated processed image. Thus, it is possible to inspect the presence or absence of foreign matter contained in the article G. At this time, the monitor 11 can display the inspection result including the processed image.

As described above, in the X-ray inspection apparatus 1, when the inspection condition is designated by the operator, at least one image processing algorithm corresponding to the inspection condition is presented. Thereby, the operator can easily select the image processing algorithm suitable for the inspection of the article G. Then, when the image processing algorithm is selected by the operator, the image processing algorithm is set, and image processing is performed on the X-ray transmission image based on the image processing algorithm. Accordingly, the inspection of the article G can be appropriately performed without presetting many types of image processing algorithms. Therefore, according to the X-ray inspection apparatus 1 (and the image processing algorithm setting method implemented in the X-ray inspection apparatus 1), the image processing algorithm suitable for the inspection of the article G can be easily set.

Further, in the X-ray inspection apparatus 1, the inspection condition is at least one of the type of the article G, the type of foreign matter that can be contained in the article G, the density in the X-ray transmission image, and the X-ray irradiation output of the X-ray irradiator 7. Is included. Further, the type of the article G includes at least one type of material, shape and size of the article G. Further, the type of foreign matter includes at least one type of material, shape, and size of the foreign matter. By classifying a plurality of image processing algorithms using these as indexes, it is easy to present an image processing algorithm suitable for the inspection of the article G.

Further, in the X-ray inspection apparatus 1, the monitor 11 displays the inspection result including the processed image. This allows the operator to confirm in advance the effect when the image processing is performed on the X-ray transmission image based on the presented image processing algorithm, and as a result, the image processing algorithm suitable for the inspection of the article G is selected. You can select with high accuracy.

Although the embodiments of the present disclosure have been described above, one form of the present disclosure is not limited to the above embodiments.

For example, one embodiment of the present disclosure is not limited to the X-ray inspection device, and may be any optical inspection device that inspects an article using electromagnetic waves. That is, in one embodiment of the present disclosure, light is X-rays, near infrared rays, or other electromagnetic waves. Further, one embodiment of the present disclosure is not limited to inspecting for the presence or absence of foreign matter contained in an article, and in an article in which contents such as food are stored in a package such as a film packaging material and shipped, the package The contents may be inspected for biting into the sealed portion, damage of the contents in the package, inclusion of foreign matter in the package, or the like. In addition, the type of article is not limited to meat, and various articles can be inspected. Similarly, the type of foreign matter is not limited to metal, and various foreign matter can be inspected.

The inspection unit, the algorithm presenting unit, and the algorithm setting unit are not limited to those configured as functional blocks, and may be configured as a hardware configuration. Further, the plurality of image processing algorithms classified by using the inspection condition as an index may be stored in an internal memory provided inside the optical inspection apparatus or may be stored in an external memory provided outside the optical inspection apparatus. Good. In addition, the plurality of image processing algorithms classified by using the inspection condition as an index are not limited to the mode in which they are provided to the optical inspection device via a communication network such as the Internet, and the optical inspection device via a storage medium such as a memory card. May be provided to That is, one form of the present disclosure is not limited to the case where the optical inspection system is configured by only the optical inspection device as described above, and the optical inspection system may be connected to the optical inspection device and a telecommunication line (for example, the Internet). And an external device (for example, an external memory provided outside the optical inspection device) connected to the optical inspection device via a communication network such as.

DESCRIPTION OF SYMBOLS 1... X-ray inspection apparatus (light inspection system), 7... X-ray irradiator (light irradiation unit), 9... X-ray line sensor (light detection unit), 11... Monitor (display unit), 21... Inspection unit, 23 ... algorithm presenting section, 25 ... algorithm setting section, G ... article.

Claims (6)

A light irradiation unit for irradiating the article with light,
A light detection unit for detecting light transmitted through the article,
An inspection unit that generates a light transmission image based on a signal output from the light detection unit, generates a processed image by performing image processing on the light transmission image, and inspects the article based on the processed image. ,
Gets the sorted plurality of image processing algorithms which the inspection conditions as an index, if the first test condition as the test condition is designated by an operator, from the plurality of image processing algorithms, corresponding to the first inspection condition A plurality of first image processing algorithms to be presented, and when a second inspection condition is specified as the inspection condition by the operator, at least the second inspection condition corresponding to the second inspection condition is selected from the plurality of first image processing algorithms. An algorithm presenting unit that presents one second image processing algorithm,
Wherein among the presented at least one of the second image processing algorithms by an algorithm presentation unit, and a algorithm setting unit that sets the second image processing algorithm selected by the operator,
The optical inspection system, wherein the inspection unit performs the image processing on the light transmission image based on the second image processing algorithm set by the algorithm setting unit to generate the processed image. The test conditions, the type of the article, the type of foreign matter that may be included in the article, shading in the light transmission image, and at least one including the light irradiation power of the light irradiation portion, light according to claim 1, wherein Inspection system. The optical inspection system according to claim 2, wherein the type of the article includes at least one type of material, shape, and size of the article. The optical inspection system according to claim 2, wherein the type of the foreign matter includes at least one type of material, shape and size of the foreign matter. The optical inspection system according to claim 1, further comprising a display unit that displays the processed image. An image processing algorithm setting method executed in an optical inspection system, comprising:
Gets the sorted plurality of image processing algorithms which the inspection conditions as an index, if the first test condition as the test condition is designated by an operator, from the plurality of image processing algorithms, corresponding to the first inspection condition A plurality of first image processing algorithms to be presented, and when a second inspection condition is specified as the inspection condition by the operator, at least the second inspection condition corresponding to the second inspection condition is selected from the plurality of first image processing algorithms. Presenting a second image processing algorithm,
Of the presented at least one of the second image processing algorithms, including the steps of setting a second image processing algorithm selected by the operator, the image processing algorithm setting method.

Images