JPH04216444A - Device for inspecting bottle - Google Patents

Abstract

PURPOSE:To improve the detecting accuracy of a defective foreign substance by removing noise signals corresponding to a scratch occurring in the outer circumference part of a bottle among the image signals for one picture obtained as the result of image pickup to the bottom of the bottle. CONSTITUTION:An inspected bottle 1 is held by a rotating wheel 6 and a bottle- supporting plate 7 and carried, and the bottom of the bottle is emitted at an inspecting position by an illuminator 2. At this time, it is prevented by a shading plate 3 that the light from the illuminator 2 makes directly incidence to an image pickup camera 4. The picture signals taken by the camera 4 are input to a picture processing apparatus 5. An address value of measure along a circumferential direction is previously stored within a memory in the apparatus 5. The brightness value of the picture element aimed at is corrected by the brightness value of each picture element of the circumferential direction following this address, and a scratch noise is removed. Thus, the judgment of the defective part and scratch noise part can be made.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a bottle inspection device that detects foreign matter mixed into the bottom of a bottle based on image information regarding the bottom of the bottle.

0002

[Prior Art] In general, bottles that contain almost transparent liquids such as juice and beer may have deposits left on the inside of the bottle or large scratches due to cleaning errors, etc. Defective bottles naturally not only reduce commercial value but also pose a major problem in terms of food hygiene and safety.

Conventionally, inspection for the presence of such defects has been carried out visually, but visually inspecting the inside of the bottle to determine the presence or absence of defects has a negative impact on the physical condition and ability of the inspector. This can sometimes lead to incredibly large defects being overlooked. Since such visual inspection relies largely on human vision, it is inevitable that many defects will be overlooked. These proposals mainly concern methods and devices for inspecting bottle bodies and bottle bottoms. For example, the bottle body (
In the proposal to inspect the bottle (including the side of the mouth), light is irradiated from one side onto the bottle being rotated at high speed, and a CCD camera installed on the other side captures the transmitted image, converts it into an electrical signal, and sends it to an image processing device. shows a technique for determining the presence or absence of defects. In addition, a proposal to inspect the bottom of a bottle suggests a technology that illuminates the bottom of the bottle from below, captures the transmitted image with a CCD camera installed above the mouth of the bottle, and digitizes this signal for image processing. .

0004

[Problem to be Solved by the Invention] However, the above-mentioned conventional bottle inspection apparatus is mainly intended for empty bottles.
Visual inspection has become the mainstream for inspecting bottles after filling them with liquid. In addition, a particularly serious defect in bottles after filling with liquid is when foreign matter gets mixed into the liquid or adheres to the bottle, and if it is present on the bottom of the bottle, it can be detected even by visual inspection. It is difficult to confirm. When carrying out automatic inspection of the bottom of the bottle after filling with liquid using photographed images, the image obtained from a television (TV) camera installed above the bottle cannot capture the entire bottom of the bottle due to the crown and stopper of the bottle. . In addition, in order to image the bottom of the bottle using a TV camera installed on the side of the bottle body and inspect it for defects, image processing using several cameras is required, which increases cost and inspection time. become. For this reason, illumination is performed from above or from the side of the bottle, and image input is performed by a TV camera installed below the bottle.

[0005] Generally, bottles for juice, beer, etc.
There are embossments and scratches on the sides (recycled bottles are used repeatedly, so the bottles rub against each other on the conveyor during the manufacturing process, causing scratches). For this reason, images captured by a TV camera below the bottle with illumination from the top or side of the bottle include noise images of the scratches mentioned above caused by refraction, total internal reflection, and diffused reflection of light, and foreign objects inside the bottle. There is a problem that it is difficult to distinguish them from images, and processing is required to remove their influence.

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to solve the above-mentioned conventional problems, and to provide a bottle that can remove noise caused by scratches on the bottom of the bottle from a photographed image of the bottom of the bottle. The purpose is to propose noise removal for inspection equipment.

[0007]

[Means for Solving the Problems] In order to achieve such an object, the present object includes a light source that projects onto the lower half of the bottle body from above the bottle bottom, and a light source that projects light information from the bottle bottom. A reference that is calculated using an imaging means that converts into an image signal, and image signals that are continuous from the image of the bottle to a certain number of pixels or more around the pixel of interest among the image signals for one screen obtained as a result of imaging. and image signal processing means that compares the difference between the luminance level of the pixel of interest and the luminance level of the pixel of interest with a set threshold value, detects and removes the pixel of interest that is smaller than this, and finally recognizes the image signal for one screen that remains as a defect. It is characterized by

[0008]

[Operation] In the present invention, the foreign objects that enter the bottle are glass fragments, hairpins, crowns, etc., and as long as the camera is focused on the bottom of the bottle, the area of the image is small and the brightness change is very large. Focusing on the fact that the signal increases rapidly, image signals that continuously exceed a certain number of pixels (area) and have a level above a certain value are removed as nozzle signals corresponding to scratches on the periphery of the bottle. Furthermore, if there is an embossment on the side of the bottle, the noise signal caused by this embossment is also removed.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be explained in detail with reference to the drawings.

FIGS. 1, 2, and 3 show the basic configuration of an embodiment of the present invention.

The bottle inspection device of this embodiment removes noise symbols corresponding to scratches occurring on the outer periphery of the bottle from one screen worth of image signals obtained as a result of imaging the bottom of the bottle. It is an inspection device.

The basic configuration of an embodiment of the present invention will be described below with reference to FIG. In FIG. 1, 100 is means for calculating a reference value from the luminance level of pixels around the pixel of interest, and the reference value is calculated from the input image signal. Next, at 200,
The reference value is subtracted from the luminance value of the pixel of interest in the input image to calculate a difference value.

Further, at 300, the difference value is compared with a set threshold value, and if the difference value is larger than the set threshold value, it is determined that there is a defect.

Next, a bottle inspection device to which the present invention is applied will be explained with reference to FIGS. 2 and 3.

As shown in FIG. 2, the bottle 1 to be inspected is conveyed while being held by a rotating wheel 6 and a bottle support plate 7, and when the bottle 1 to be inspected is positioned above the imaging camera 4, an image of the bottom of the bottle is captured by the inspection camera. 4, and then in the image processing device 5,
Based on the imaging results, the bottle is inspected for foreign matter. As shown in FIG. 3, a light shielding plate 3 and a light 2 are installed above the inspection camera 4, and when the bottle 1 to be inspected comes to the inspection position, the bottom of the bottle is illuminated by the light 2. The light shielding plate 3 is for preventing the light from the illumination 2 from directly entering the imaging camera 4.

[0016] Here, the positions of the illumination 2 and the imaging camera 4 are set as follows. The light emitted from the illumination 2 enters the bottle 1 to be inspected, is refracted and transmitted at the bottle surface, the interface between the bottle and the liquid inside, etc., but there is a position where this refracted and transmitted light does not enter the lens of the imaging camera 4. will be installed in Therefore, the image captured by the imaging camera 4 basically consists of diffusely reflected light due to embossing, scratches on the bottle surface, foreign objects in the liquid, etc.

[0017] This test attempts to detect foreign matter in the liquid content from images resulting from such diffused reflection. An image of the bottom of the juice bottle obtained by the above procedure is shown in FIG. Defects 8 and scratch noises 9 in the liquid content are captured. Here, there are scratches caused by contact between the bottles on the side of the body of the juice bottle, and when this area is irradiated with light from illumination 2, the light reflected from the bottle surface is totally reflected inside the bottle. 4, and appears as scratch noise 9 as shown on the left side of FIG. These scratches occur almost all around the circumference of the bottle, resulting in an image that is long in the circumferential direction.

When recognizing the defect 8 from such an image, it is necessary to distinguish it from a foreign object image as scratch noise. Generally, in such cases, judgment is often made based on the magnitude of the brightness value of the output image, but in the case of bottles that have been used repeatedly, the scratch noise 9 is often the same or higher in brightness level than the defect signal 8. It is not practical to simply compare the magnitude of brightness values. Therefore, in the present invention, the following process is executed in the image processing device 5 by taking advantage of the fact that the continuous change in brightness in the circumferential direction of images of scratch noise is gentler than images of defects, and Remove noise.

An example of an inspection image is shown in FIG. 5 to explain the method of inputting the luminance values of pixels in the circumferential direction. The squares in the figure indicate pixels, and the pixel positions are indicated in an orthogonal coordinate system. In the case of this process, address values of squares along the circumferential direction are stored in advance in the memory of the image processing device 5 in order to perform filter processing to be described later in the circumferential direction of the bottle. The brightness value of each pixel in the circumferential direction according to this address is set from al to a.
Suppose it is k. Assuming that the brightness value of the current pixel of interest is ai, the scratch noise is removed by correcting the brightness value of the pixel of interest using the following filter process.

[0020]

[Math 1]

[0021] This filter processing calculates the average of the luminance levels of 2N+1 fixed lengths centered on the pixel of interest, and subtracts the value (reference value) obtained by multiplying the average value by X times from the luminance level of the pixel of interest. That's true. Here, X is a numerical value of about 0.3 to 5, and when it is set to a large value, the erasing effect becomes stronger in areas where high-brightness pixels are continuously present, and scratch noise can be easily removed. If it overlaps with noise or is a large defect, it will be erased in the same way as scratch noise, so a value of about 0.5 to 2 is appropriate.

This will be explained in more detail with reference to FIG.

FIG. 8 shows the luminance distribution in the circumferential direction of the bottle in the image signal captured by the imaging camera 4, and the luminance distribution subjected to the filter processing shown in equation (1). Furthermore, the distribution of the image signal is shown in which pixels smaller than the set threshold are detected and removed by comparison with the set threshold. Here, the filtering process of equation (1) is performed with X=1. The upper two diagrams in Figure 8 show the luminance distribution before and after filter processing.As shown in the distribution before filter processing, the signal of the defective part changes rapidly, whereas the scratch noise has a lower luminance. I can see that it is changing slowly. Therefore, in the scratched portion, there is no large difference between the brightness level of the pixel of interest and the average value, and the brightness level ai′ after correction becomes a value close to zero.

On the other hand, in the defect image, the brightness changes rapidly at the outer edge of the defect, and the range of a certain length for filtering (2N+1 in this example) is larger than the size of the defect, so the brightness level of the pixel of interest changes. is larger than the average value.

Through the above processing, the brightness distribution shown in the center of FIG. 8 is obtained, and by setting the threshold value to an intermediate value between N2 and S2, it is possible to distinguish between defective parts and scratch noise parts, as shown in the lower part of FIG. It becomes possible.

[0026] In this example, we have shown an example in which the range of a certain length for filter processing is larger than the defect size, but even if the defect size is larger, the brightness at the outer edge changes rapidly. Therefore, the brightness value of the outer edge portion becomes a value sufficiently larger than the average value, making it possible to distinguish it from scratch noise.

FIG. 6 shows an example of the circuit configuration of the image processing device 5 for executing such processing.

In FIG. 6, the central processing unit (CPU
) 100, read-only memory 110, random access memory (RAM) 120, keyboard input device 130
, a display device 140, and an analog-to-digital (A/D) converter 150 are connected to the common bus. The CPU 100 executes the control procedure shown in FIG. 7 stored in the ROM 110 in response to an execution command input from the keyboard input device 130.

That is, the image signal (analog form) of one screen outputted from the imaging camera 4 as the imaging result is A/
It is converted into a signal indicating the brightness level of each pixel in digital form in the D converter 150, and is stored in the RAM by the CPU 100.
120 (step 10 of U7).

The CPU 100 reads the luminance data of pixels near the circumference from the RAM 120, performs the above-described filter processing, and stores the filter-corrected luminance data in the RAM 120.
After finishing the filter processing (loop processing of steps S20 to S50 in FIG. 7), the CPU 100
performs a threshold comparison with the image data of RAM120,
A defective image having luminance data above a threshold is detected. The presence or absence of this defective image is displayed on the display device 140 according to an instruction from the CPU 100 (step S60 in FIG. 7).

The luminance level distribution in the circumferential direction of the image before filter correction as shown in FIG. 4 is as shown in FIG. The lower part of FIG. 8 shows the result of filtering this signal level distribution. As shown in this figure, it can be seen that the ratio S/N ratio between the luminance signal level and the noise level is significantly improved for scratch noise of a certain length or more. In this example, the average range of the average value to be subtracted is 8 degrees in the circumferential direction.

Here, when the filter processing of this embodiment is performed, the signal level becomes small as shown in FIG. 8, and the margin between the defect level and the noise level may become small. Therefore, in this embodiment, the corrected brightness level was amplified by multiplying the filtered signal by a constant of 1 to 3, and defect determination was performed using a threshold value.

The present invention is not limited to this embodiment, and the present invention can be implemented in various ways as described below.

1) In this embodiment, the range for averaging is 8 degrees in the circumferential direction, but it is effective if it is 2 degrees or more. As the range of this averaging process becomes larger, defect signals can be detected with larger values, but the effect of erasing scratch noise becomes smaller. On the other hand, if the range of the averaging process is made smaller, the scratch noise becomes smaller, but the defect signal also becomes smaller. The range of the averaging process should be set to an optimal value depending on the type of bottle, and is generally desirably about 2 to 90 degrees in the circumferential direction.

2) In this embodiment, when extracting pixels in the circumferential direction, the brightness value of each pixel was read out according to the address stored in the memory. may be obtained by calculation. In addition, although the brightness value of a certain address was used as is, in order to obtain a more accurate brightness value in the circumferential direction, it is also possible to calculate the brightness value along the circumferential direction from the brightness values of neighboring pixels using supplementary questions. It is.

3) In this embodiment, an example was shown in which only scratch noise on the bottom of the bottle is removed, but when there is an emboss on the bottom of the bottle, it is also possible to remove the noise image caused by the emboss. In this case, filter processing is performed on the image signal of one screen sentence.

[0037]

[Effects of the Invention] As explained above, according to the present invention, it is possible to remove images of scratches on the bottom of the bottle, which are not subject to bottle inspection. Therefore, it is possible to detect defective foreign substances present at the bottom of the bottle, and the detection accuracy can be improved.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the basic configuration of an embodiment of the present invention.

FIG. 2 is a top view showing the arrangement of bottles in an embodiment of the present invention.

FIG. 3 is a structural diagram showing a side configuration of an embodiment of the present invention.

FIG. 4 is an explanatory diagram schematically showing images before and after filter processing according to the embodiment of the present invention.

FIG. 5 is an explanatory diagram showing a procedure for capturing pixel data in a circumferential direction in an inspection image.

6 is a block diagram showing a circuit configuration of the image processing device 5 of FIG. 3. FIG.

7 is a flowchart showing a processing procedure executed by the CPU 100 in FIG. 6. FIG.

FIG. 8 is a waveform diagram showing waveforms of a luminance signal before and after filter processing according to an embodiment of the present invention.

[Explanation of symbols]

4 Imaging camera 5 Image processing device 100 CPU 110 ROM 120 RAM

Claims (1)

[Claims] 1. A light source that projects onto the lower half of the bottle body from above the bottle bottom, an imaging means that converts light information from the bottle bottom into an image signal, and one screen obtained as a result of imaging. The difference between the brightness level of the pixel of interest and the reference value calculated using image signals that are consecutive for a certain number of pixels or more around the pixel of interest from the image of the bottle within the image signals of the number of minutes is compared with a set threshold value. 1. A bottle inspection device comprising: image signal processing means for detecting and removing smaller pixels of interest and finally recognizing one screen's worth of image signals remaining as a defect.