JPH01206240A - Evaluating method and apparatus of checking capacity for external appearance checking apparatus - Google Patents

Abstract

PURPOSE:To obtain exactly an evaluation value for evaluating a checking capacity, by determining a detection probability of an external appearance checking apparatus and an emergence probability of a defect of a surface of a substance to be checked up, and by computing thereafter the total sum of the detection probability and the emergence probability. CONSTITUTION:A reference image having pixels of all density variation gradations is picked up by a video camera 11 and image data thus obtained are stored in RAM 3. Next, CPU 1 stores the mean value of gradation data of the reference image in each density variation gradation as a detection probability F(i) of an image pickup device 100 in the RAM 3. Then, a substance to be checked which has a stain defect is picked up and the image data on a stained image are stored in the RAM 3. The CPU 1 stores stain emergence data on all density variation gradations in the RAM 3. Then, an emergence probability G(i) of the stain defect is determined and stored in the RAM 3. Subsequently, the CPU 1 calculates a checking power K1 from the probabilities F(i) and G(i) and then displays same.

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Application Field] The present invention relates to an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object to be inspected based on the data of the grayscale image. This invention relates to a method and device for evaluating testing ability.

[Prior Art] Conventionally, a two-dimensional black-and-white camera is used to image an object to be inspected, or a one-dimensional black-and-white camera is used to move the object to be inspected in a direction perpendicular to the scanning direction of the one-dimensional black-and-white camera. Various measurement methods, dirt detection algorithms, inspection devices, etc. have been devised in order to detect dirt defects on the surface of an object to be inspected from a two-dimensional grayscale image obtained by imaging the object.

[Problem to be solved by the invention] What is the appropriate inspection method and device for the object to be inspected that actually requires inspection for dirt defects?
There was no evaluation method or device that could appropriately and objectively quantify and display the results.

Therefore, when selecting a method and device for detecting dirt defects from their gradation images as a powerful means for visual inspection, it is important to accurately express, evaluate, and confirm the inspection ability of the inspection device. I couldn't do it. For this reason, there is a discrepancy in the expected performance of the system between the user and the designer, or between the designer and the manufacturer of the inspection equipment, and after the inspection equipment is installed, it may result in performance that is contrary to expectations. Problems were occurring extremely frequently.

SUMMARY OF THE INVENTION An object of the present invention is to solve the above-mentioned problems and provide an evaluation method and apparatus for a visual inspection device that can automatically quantify and evaluate the inspection ability of the visual inspection device.

[Means for Solving the Problems] The evaluation method of the first invention is for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object to be inspected based on data of the grayscale image. In the inspection ability evaluation method of The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the grayscale image of the object to be inspected having a defect on the surface for each grayscale, and the difference between the detection probability and the appearance probability is calculated. The first sum, which is the sum of the products for each of the above gray scales, is calculated over all the gray scales, and the second sum, which is the sum of the appearance probabilities for each gray scale, is calculated over all the gray scales. The method is characterized in that the calculation is performed over the gray scale, the first sum is divided by the second sum, and the divided value is used as an evaluation value of the inspection ability of the visual inspection apparatus.

The evaluation device of the second invention is an inspection ability evaluation device for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image. a first calculation means that calculates a detection probability that is a probability that the appearance inspection device can detect an image of each density gradation based on image data including all of the density gradations for each density gradation; a second calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected having a defect on the surface for each grayscale; a third calculation means for calculating a first sum, which is the sum of the products of the probability and each of the gray scales, over all the gray scales;
a fourth calculation means for calculating a second sum, which is the sum of the appearance probabilities of each of the gray scales, over all the gray scales; and dividing the first sum by the second sum. and a fifth arithmetic means, and the divided value obtained by the fifth arithmetic means is used as an evaluation value of the inspection ability of the appearance inspection apparatus.

The evaluation method of the third invention is an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image. The detection probability, which is the probability that the visual inspection device can detect an image of each density gradation, is calculated based on the image data including all of the above density gradations for each density gradation, and the detection probability is calculated for each density gradation. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the grayscale image of the object to be inspected that has a defect on its surface, and the detection probability, the appearance probability, and each density gradation for the object to be inspected are calculated. The first sum, which is the sum of the products for each density gradation with the predetermined importance for each, is calculated over all the density gradations, and A second sum, which is the sum of the products for each of the gray scales, is calculated over all the gray scales, the first sum is divided by the second sum, and the divided value is calculated for the appearance. It is characterized in that it is an evaluation value of the inspection ability of the inspection device.

An evaluation device according to a fourth aspect of the invention is an inspection ability evaluation device for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object to be inspected based on the data of the grayscale image. a first calculation means that calculates a detection probability that is a probability that the appearance inspection device can detect an image of each density gradation based on image data including all of the density gradations for each density gradation; a second calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected having a defect on the surface for each grayscale; A first sum, which is the sum of the products of the probability and the predetermined importance of each gray scale for the object to be inspected, for each gray scale is calculated over all the gray scales. a third calculation means; and a fourth calculation means for calculating a second sum, which is the sum of the products of the appearance probability and the importance level, for each of the gray scales, over all the gray scales. , and a fifth calculation means for dividing the first sum by the second sum, and the division value obtained by the fifth calculation means is used as an evaluation value of the inspection ability of the appearance inspection apparatus. It is characterized by

The evaluation method of the fifth invention is an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the grayscale image of the object to be inspected that has a defect on its surface for each grayscale; The sum of the products of the detection probability and the appearance probability, which are predetermined based on image data including gray scale, and which is the probability that the appearance inspection device can detect an image of each gray scale, for each gray scale. A first sum that is the sum of the appearance probabilities of each of the gray scales is calculated over all the gray scales, and a second sum that is the sum of the appearance probabilities of each gray scale is 1 is divided by the second sum, and the divided value is used as an evaluation value of the inspection ability of the visual inspection apparatus.

An evaluation device according to a sixth aspect of the invention is an inspection ability evaluation device for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object to be inspected based on the data of the grayscale image. a first calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of a gray scale image of the object to be inspected having a defect on the surface for each gray level; The detection probability, which is the probability that the appearance inspection device can detect an image of each density gradation, is predetermined based on image data including all of the density gradations for each density gradation, and the appearance probability. a second calculation means for calculating a first sum, which is a sum of products for each tone, over all the above-mentioned gradation levels, and a second sum, which is a sum of the above-mentioned appearance probabilities for each of the above-mentioned gradation levels. and a fourth calculation means that divides the first sum by the second sum.
The present invention is characterized in that the division value obtained by the fourth calculation means is used as an evaluation value of the inspection ability of the visual inspection device.

An evaluation method according to a seventh aspect of the present invention is an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the gradation image of the object to be inspected, which has a defect on the surface, for each gradation level, and the appearance probability, which is the probability that the defect will appear, is Detection probability, which is predetermined based on image data including gradations, and is the probability that the appearance inspection device can detect an image of each gradation, the appearance probability, and a predetermined value for each gradation of gradation for the object A first sum, which is the sum of the products of the above-mentioned importance levels for each of the above-mentioned gray scales, is calculated over all the above-mentioned gray scales, and the above-mentioned respective gray-scale scales of the above-mentioned appearance probability and the above-mentioned importance levels are calculated. A second sum, which is the sum of the products for each, is calculated over all the gray scales, the first sum is divided by the second sum, and the divided value is calculated as the inspection capacity of the visual inspection device. It is characterized by being an evaluation value.

An evaluation device according to an eighth aspect of the invention is an inspection ability evaluation device for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image. a first calculating means for calculating an occurrence probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected having a defect on the surface for each grayscale level; Detection probability, which is the probability that the appearance inspection device can detect an image of each density gradation, which is predetermined based on image data including all of the above-mentioned gradations, the above-mentioned appearance probability, and each gradation for the object to be inspected. a second calculation means for calculating a first summation, which is a sum of the products of each gray scale with a predetermined importance level for each gray scale, over all the gray scales; a third calculating means for calculating a second sum, which is the sum of the products of the probability and the importance level for each of the gray scales, over all the gray scales; 2, and the divided value obtained by the fourth calculation means is used as an evaluation value of the inspection ability of the visual inspection apparatus.

[Operation] According to the first and second inventions, after the detection probability of the visual inspection device and the probability of appearance of surface defects on the inspected object are calculated for each predetermined gray scale, , a first sum, which is the sum of the products of the detection probability and the appearance probability for each of the gray scales, is calculated over all the gray scales, and the "1 occurrence" of each of the gray scales is calculated. A second summation, which is a summation of probabilities, is calculated over all the gray levels, the first summation is divided by the second summation, and the divided value is calculated as the inspection capacity of the visual inspection device. Used as evaluation value. This makes it possible to accurately and quickly obtain an evaluation value for evaluating the inspection ability of the visual inspection device.

Further, according to the third and fourth inventions, after calculating the detection probability of the appearance inspection apparatus and the appearance probability of surface defects on the object to be inspected for each predetermined gray scale, the detection probability is calculated. The first sum, which is the sum of the products of the above occurrence probability and the predetermined importance level for each of the gray scales, is calculated over all -1-l gray scales, and the above is calculated. The second sum, which is the sum of the product of the probability of appearance of each density level and the above importance level, is calculated over all the density levels, and the first sum is 2, and the divided value is used as an evaluation value of the inspection ability of the visual inspection device. This makes it possible to accurately and quickly obtain an evaluation value for evaluating the inspection ability of the visual inspection device.

Furthermore, according to the fifth and sixth inventions, after calculating and determining the appearance probability of a surface defect on the object to be inspected for each predetermined iR lightness gradation, the predetermined detection probability and A first sum, which is the sum of the products of the above-mentioned appearance probability and each of the above-mentioned lightness and lightness gradations, is calculated over all the above-mentioned lightness and lightness gradations, and The second summation is calculated over all the gray scales, and the second summation
The total sum is divided by the second sum, and the divided value is used as an evaluation value of the inspection ability of the visual inspection apparatus. This makes it possible to accurately and quickly obtain an evaluation value for evaluating the inspection ability of the visual inspection device.

Furthermore, according to the seventh and eighth inventions, after calculating and determining the appearance probability of a surface defect on the object to be inspected for each predetermined scale, the predetermined detection probability is determined. A first sum, which is the sum of the products of the above-mentioned appearance probability and the predetermined importance level for each of the above-mentioned gradation levels, is calculated over all the 1st gradation levels, and A second sum, which is the sum of the products of the ``1 appearance probability'' and the ``1 importance, of the key, is calculated over all the gray levels, and the first sum is the second sum. The divided value is used as an evaluation value of the inspection ability of the visual inspection device. As a result, the evaluation value for evaluating the inspection ability of the above-mentioned appearance inspection device is
can be obtained accurately and quickly.

[Example] Fig. 1 shows a visual inspection function and an evaluation device (hereinafter referred to as
It is called appearance inspection and evaluation equipment. ) is a block diagram of.

In FIG. 1, this visual inspection and evaluation apparatus includes a light projecting device 20 that irradiates an object to be inspected with illumination light, a video camera 11, and an analog-to-digital converter (hereinafter referred to as A/D converter).
It's called conversion. ) An imaging device 100 having a circuit 12, a central processing unit l, and a read-only memory (hereinafter referred to as RO
It's called M. ) 2. Random access memory (hereinafter referred to as R
It's called AM. ) 3, an image processing device 200 having a keyboard 4 and a display device 5;
The first step is to evaluate the dirt defect inspection ability of other imaging devices.
It is characterized by having a second evaluation mode.

In FIG. 1, a video camera 11 photographs an object to be inspected 10 irradiated with light from a light projector 20, and then includes information on a two-dimensional grayscale image of one field (one screen) of the photographed object. A black and white television signal is output to the A/D conversion circuit 12. The A/D conversion circuit 12 A/D converts the image of the input television signal in 16 gradations and sends the image data to the image processing device 2.
CPU that outputs to CPUI via connector 30 of 00
I is a control circuit that controls operations within the image processing device 200, and the CPU includes a ROM 2 that stores a system program for controlling the image processing device 200, and is used as a work area for the CPUI. RAM3 temporarily stores image data input to the CPUI, and image data input manually to the CPUI and RA.
A display device 5 is connected that displays each image of the image data temporarily stored in the M3 and also displays the test result and evaluation result data calculated by the CPU 1.

The operation of the visual inspection and evaluation apparatus configured as described above will be explained separately in the inspection mode, the first evaluation mode, and the second evaluation mode.

(1) Inspection mode First, the object to be inspected, which has no dirt or defects on its surface, is
1, and the image data of the photographed image (hereinafter referred to as image data of a normal image) is transferred to the A/D conversion circuit 1.
2 and CPUI, and is stored in the RAM 3 and displayed on the display device 5. Then c'pu
t is each gradation (hereinafter referred to as gradation gradation) in which the image data of the normal image stored in the RAM 3 indicates the gradation of each pixel in 16 steps, from 1 indicating the lightest white to It is indicated by a natural number up to 16, which indicates the darkest black color.

) is detected, and a total of 1 detected pixels are detected.
6 pieces of data (hereinafter referred to as normal image gradation data)
After storing the image data in the RAM 3, the image data of the normal image stored in the RAM 3 is deleted.

When inspecting for dirt defects, a video camera is used to inspect the object to be inspected.
The image data of the photographed image (hereinafter referred to as
This is called the image data of the inspection image. ) is the A/D conversion circuit 12
and stored in RAM3 via cpul,
displayed on the display device 5. Next, after detecting whether the image data of the inspection image stored in the RAM 3 includes pixels of each gray level, the CPU ) is compared with the gradation data of the normal image stored in the RAM 3, and it is determined whether the gradation data of the inspection image includes gradations that are not present in the gradation data of the normal image. do. Here, if the gradation data of the inspection image includes a gradation that is not included in the gradation data of the normal image, the CPU 1 sends the data of the gradation gradation that is not included in the gradation data of the normal image to the display device 5. On the other hand, if the gradation data of the inspection image does not include gradation levels that are not present in the gradation data of the normal image, the CPU
It is determined that there is no stain defect, and the message "°°No stain defect" is outputted to the display device 5 to be displayed.

Using the above-mentioned visual inspection and evaluation device using images with 16 gradations of gradation, dirt adhering to the surface of the object to be detected, which has a red company emblem printed on a flat plate with a light yellow background, is inspected. An experimental example in which a visual inspection device was evaluated will be described below. Here, it is assumed that the above-mentioned stains include stains ranging from pale gray to black.

In a normal image taken using the video camera 11 of an object to be inspected with no dirt on its surface, the light yellow ground color is the brightest, resulting in a light gray image, and the company emblem is a slightly darker gray color. For example, the gradation of the ground color is 4.
~6, the gray level of the mark is lO~12.

In contrast, images of objects to be inspected with dirty surfaces (hereinafter referred to as
It is called a dirty image. ), and for example, if ink is attached to the surface, the gradation level of the nearly pure black image will be, for example, 15. Conversely, when white powder adheres to the surface of the object to be inspected, the gray scale of the image becomes 2. In these cases, it is relatively easy to detect dirt using the above-mentioned inspection device. That is, in normal images, 4-6 and 10-1
However, in addition to the gradation of the normal image, the soiled image has a gradation of 15, which is an image of silver dirt, and the gradation of 2, which is an image of white powder. Also included. Therefore, as mentioned above, whether it is a normal image or a dirty image,
It is checked whether the image has only gray scales of 4 to 6 and lO to 12, or whether it contains other gray scales, and if it does, it can be detected as a dirty image. can.

In this case, Table 1 shows data on the detection probability of the apparatus and the appearance probability of dirt defects with respect to gradations of color and lightness, and FIG. 2 shows a graph showing the relationship between the above-mentioned probabilities.

Here, the detection probability is a characteristic unique to the inspection device, and the detection probability at each gray level included in a normal image is 0, while the detection probability at each gray level when a dirty image can be reliably detected. The detection probability at each gradation is 1. if,
If the inspection device is not perfect and does not detect an image of one gray scale with a certain probability, the detection probability is less than one. In the above visual inspection and evaluation device, the detection probability depends on the performance of the imaging device 100.

Furthermore, the appearance probability of a stain defect is the probability that a stain defect will occur in each density gradation among all the stain defects that occur in a large number of inspected objects, for example, 100 or more manufactured by the same process. Note that the sum of the above-mentioned appearance probabilities for each gray level is 1.

As mentioned above, the normal image includes images with gradations of 4 to 6 and 10 to 12, so as shown in FIG. The above-mentioned inspection apparatus cannot detect dirt defects in grayscale images.

In addition, as long as the device works normally, if the image of the stain defect is only in 2 to 15 gray scales as shown in FIG. Can detect 100% of the test object (hereinafter referred to as 100% detection capability of the test device)
It is said that it is 0%. ) can be expected.

Now suppose that a smudge defect is caused by the red printing ink used for the mark spilling onto the surface of the board. In this case, as shown in Table 2 and Figure 3 (B), the stain image is an image with the same 11 gradations as the mark, so the stain defect cannot be detected by the above-mentioned discrimination based on the gray scale. . That is, the above-mentioned inspection device cannot detect the above-mentioned dirt defect.

Therefore, the inspection ability of the inspection device is 0%.

Furthermore, as a numerical case, as shown in Table 3 and FIG. 4(B), a case will be described in which the dirt defect includes gradations other than the above two examples. In this case, the image of the dirt defect is 1
Which gradation of 16 to 16 stain defects will appear is a statistical probability phenomenon. Here, as long as we use the above-mentioned inspection device that distinguishes gradations of gradation, we can use the same background color and mark as the company emblem.
Images with gray scales of ~6 and 10~12 cannot be detected as stain defects.

Therefore, in this embodiment, (i) is expressed by the following equation for the first inspection ability of the inspection system including the inspection apparatus and the object to be inspected.

Here, F(i) is the detection probability of the inspection device at the gray scale of i, and G(i) is the probability of appearance of the stain defect in the inspection device at the gray scale of i. Also, F
r(i) is the above-mentioned detection probability of the ideal inspection device at the gray level of i, and is ■.

That is, as shown in equation (1a), the first inspection capability of the inspection system including the inspection device and the object to be inspected is the detection probability of the inspection device at each gray scale and its gray scale. , and the probability of the appearance of a stain defect in , and the value obtained by summing the product value at each gray scale over all gray scales, and the detection probability is 1 at all gray scales. The value obtained by calculating the above sum and the value of the ratio are used in an ideal inspection device. Here, if the number of gray scales to be investigated is infinitely increased, the detection probability of the inspection device at each gray scale is Take the product of the appearance probability of a dirt defect at that density gradation,
A value obtained by integrating the product value at each gray scale over all gray scales, and a value obtained by calculating the integral value using the ideal inspection apparatus are used as a ratio value.

If we use the index for the above inspection performance, for example, if the performance of the inspection device is good and the gradation of dirt on the object to be inspected does not overlap with the background color of the company emblem or the gradation of gradation of the mark, then it will be 1. The values will be close to each other, but if the detection probability of the inspection device itself at each gradation level is smaller than 1, or if the probability that the gradation level of a dirt defect overlaps with the gradation level of the background color or mark increases, then The value of 1 for testability becomes small and approaches 0. That is, by using the index of this inspection ability as a guide, it is possible to display how much inspection ability the inspection system essentially has for the object to be inspected. The first evaluation mode of the above-mentioned visual inspection and evaluation apparatus, which will be described in detail later, is a mode in which the first inspection ability is set to 1.

Next, in the above-mentioned first inspection performance index of 1, it is assumed that the influence of a stain defect on a product to be inspected is a constant value of 1, regardless of the concentration of the stain defect.

However, in real cases, for example, the degree of deterioration of the image of the product when there is whitish dirt is often evaluated as being smaller than the degree of deterioration of the image of the product when there is black dirt. Therefore, an evaluation that also takes this factor into account is more appropriate.

Therefore, in this embodiment, the second inspection ability K2(i) of the inspection system including the inspection apparatus and the object to be inspected is expressed by the following equation.

Kt = IF (i) G (i) 1 (i) - (2
・)IF r(i)G (i)・H(i) = J F(i)□G(iゝ“”0 ・・・(2b)
f F r(i)G (i)・H(i)diwhere, H
(i) is a value that quantifies the degree of deterioration of the product image caused by the dirt defect of the gray scale of i on the inspected object (hereinafter referred to as
It is called importance. ), and the larger the value of the importance, the more
Contamination defects have a large negative impact on the image of the inspected object,
The importance of the gradation is high.

In other words, as shown in equations (2a) and (2b), 2 in the second inspection capacity of the inspection system including the inspection device and the test object is calculated by each numerator and denominator in equations (1a) and (1b). is multiplied by the above importance level. Here, the degree of importance H(i) is determined in advance based on the value and performance of each object to be inspected, the sense of value of the group handling the object, the manufacturing process, and the like.

Therefore, by using the index as a guideline for this inspection ability, it is possible to determine how much inspection capability the inspection system essentially has for the objects to be inspected. It is possible to display the image in consideration of the degree of importance indicating the degree of deterioration of the image. The second evaluation mode of the above-mentioned visual inspection and evaluation device, which will be described in detail later, is
This is the mode for determining the inspection ability of

Therefore, the closer the first or second inspection ability is to 1, the more complete the inspection system is, but in a normal inspection system, the inspection ability is, for example, 0. If it is 4 or more, the inspection system is considered to have valuable inspection ability. In addition, for example, the test ability is 0
．． If it is 6 or more, it becomes an even more valuable inspection system,
For example, if it is 0.8 or higher, it becomes an extremely valuable inspection system.

(2) First evaluation mode First, in order to find the detection probability of the imaging device 100,
An image having pixels of all 16 gray scales (hereinafter referred to as a reference image) is photographed using the video camera 11, and the image data of the reference image, which is the image data of the photographed image, is transferred to the A/D. RA via the conversion circuit 12 and cput
Store in M3. Next, the CPU 1 detects whether or not the image data of the reference image stored in the RAM 3 includes pixels of each density gradation, and determines whether or not the image data of the reference image stored in the RAM 3 includes pixels of each density gradation. After storing the data in the RAM 3, the image data of the reference image stored in the RAM 3 is erased.

Next, the procedure for obtaining the gradation data of the reference image described above is repeated, for example, 10 times or more, and the average value of the gradation data of the reference image at each of the gradation levels is determined by the imaging device 10.
It is stored in the RAM 3 as a detection probability F(i) of 0.

Further, an object to be inspected with no dirt or defects on its surface is photographed in advance using the video camera 11, and gradation data of a normal image is determined in the same manner as in the inspection mode described above and stored in RA~13.

Next, the object to be inspected with the stain defect is photographed using the video camera 11, and the image data of the photographed image (hereinafter referred to as image data of the stain image) is sent via the A/D conversion circuit 12 and the CPUI. Stored in RAM3. Next, the CPU 1 detects whether or not the image data of the dirty image stored in the RAX 13 includes pixels of each gray scale, and then processes the detected data (hereinafter referred to as 16 in total).
This is called gradation data of a dirty image. ) and the gradation data of the normal image stored in R1 to M3, and it is determined whether the gradation data of the dirty image includes gradations that are not included in the gradation data of the normal image. Here, if the gradation data of the dirty image includes a gradation level that is not included in the gradation data of the normal image, the CPU
On the other hand, if the gradation data of the dirty image does not include a gradation level that does not exist in the gradation data of the normal image, the CPU
A total of 16 pieces of dirt appearance data for all gray levels are stored in RAM 3, with the dirt appearance data set to 0.

Next, the procedure for obtaining the stain appearance data described above is repeated on, for example, 100 or more test objects that are manufactured in the same manufacturing process and have scratch defects on the surface, and then the stain appearance data at each of the above-mentioned gray scales is determined. The average value of the appearance data is determined, and the average value is stored in the RAM 3 as the appearance probability G(i) of a dirt defect at each gray level for the object to be inspected.

Further, the CPU reads out the detection probability F(i) of the imaging device 100 and the appearance probability G(i) of dirt defects stored in the RAM 3, and calculates the first
After calculating 1 for the testability, the data for the testability is output to the display device 5 and displayed. With the above, the first
The evaluation mode operation ends.

In addition, for example, 1 or 0 for the inspection ability. If the test is 4 or higher, it is considered that the testing capacity of the inspection system is above the specified level, and the test is passed.
On the other hand, the test ability is 0. If it is less than 4, the inspection ability of the inspection system is considered to be less than a predetermined value and the inspection system is rejected.Before calculating the above inspection ability, enter the evaluation criteria of the inspection system in advance from the keyboard 4 and then write it to the RAM 3 via the CPU 1.
and after calculating 1 for the above test performance, the above evaluation base ij
It is also possible to determine whether the CPU 1 passes or fails according to J, and output the evaluation result to the display device 5 for display. Here, the evaluation standard for inspection ability is 0°4.
However, it is not limited to this, and may be changed based on consideration of the inspection process, manufacturing process, degree of combined use with visual inspection, cost and reliability of inspection, equipment cost of automatic external fall inspection equipment, etc. .

In the operation of the first evaluation filli mode described above, the inspection ability of the imaging device 100 is not limited to this, but the detection probability changes by changing the imaging device, and the detection probability of the object to be inspected changes. Since the appearance probability changes by changing the number of objects to be inspected, it is possible to connect another imaging device equipped with a video camera and an A/D conversion circuit to the connector 30 of the image processing device 200, and perform inspection on the same or another object to be inspected. Alternatively, 1 may be calculated.

(3) Second evaluation mode At this time, as in the first evaluation mode, the CPUI calculates the detection probability F(i) of the imaging device 100 and the inspection target that is manufactured in the same manufacturing process and has a dirt defect. The appearance probability G(i) of a stain defect is calculated and stored in the RAM 3.

Next, the operator uses the keyboard 4 to input the degree of importance H(i) at each gray level indicating the degree of deterioration of the product, which has been predetermined for the object to be inspected based on the criteria mentioned above. However, the data with the above-mentioned importance level H(1) is stored in the RAM 3 via the CPU 1.

Furthermore, cput is the detection probability F(i) of the imaging device 100 stored in the RAM 3 and the appearance probability G(
i) and the importance level H(i), calculate 2 for the second inspection ability using the above formula (2a), and then output the data for the second inspection ability to the display device 5 and display it. . This completes the operation of the second evaluation mode.

In addition, when the first and second inspection abilities of the inspection apparatus of each of the experimental examples in Tables 1 to 3 are calculated using the above inspection apparatus and evaluation apparatus, they are 1.0 and 1.0, respectively. 0,
It is 0.43. Therefore, the inspection equipment in Table 1 has an inspection capacity of 1, so it can be used completely as an inspection apparatus, and the inspection equipment in Table 2 has an inspection capacity of 2, which is 0.
Therefore, it cannot be used as an inspection device. Further, although the inspection devices shown in Table 3 have lower inspection capabilities than the devices shown in Table 1, they have a predetermined or higher ability and can be used as inspection devices.

Tables 4 to 7 are graphs showing detection probabilities, appearance probabilities, and degrees of importance in experimental examples in which the above-mentioned company emblems were evaluated using this inspection and evaluation device. The detection probability, appearance probability, and importance of Table 7 are shown in FIGS. 5 to 8, respectively.

When the second inspection performance of the inspection apparatus of each experimental example in Tables 4 to 7 is calculated using the above inspection apparatus and evaluation apparatus, they are 0.34.0, 85.0.93, O, It is St. Therefore, the inspection equipment shown in Table 4 has an inspection ability of 0.
34, so its ability as an inspection device is low. In addition, even though the inspection equipment in Table 5 is set to have higher importance for dark stains than near the marks, the inspection performance is 0°85, so it can be said that the inspection equipment has high performance. I can say that. Furthermore, the inspection devices in Tables 6 and 7 similarly have a relatively high inspection ability of 2, and can be said to have high capabilities as inspection devices.

As described above, in the visual inspection and evaluation apparatus for inspecting dirt defects on an object to be inspected and evaluating its inspection ability, the above-mentioned first or second inspection ability KI.

Since K can be automatically calculated, it is possible to quickly and accurately evaluate the performance of the above-mentioned visual inspection device. Therefore, when introducing this type of inspection device, it becomes easy to judge which inspection ability is best to introduce.

Furthermore, as a result, it can be expected that the above-mentioned transactional troubles will be reduced, which is extremely meaningful from an industrial perspective.

In the above embodiments, an apparatus is described that uses a grayscale image of the object to be inspected to determine whether or not there is a dirt defect on the surface. The grayscale image of the object to be inspected may be used to inspect whether there is a defect that can be seen in the grayscale image.

In the above embodiment, the video camera 11 is used, but the present invention is not limited to this, and other types of cameras capable of capturing a single screen of grayscale images may be used.

In the above embodiments, the detection probability of the imaging device 100 is calculated in the first and second evaluation modes of the visual inspection and evaluation device, but the detection probability is not limited to this, and the detection probability calculated by another device or 2 may be calculated for the testability using a predetermined detection probability.

In the above embodiment, the A/D conversion circuit 12 A/D converts the image of the television signal inputted from the video camera 11 in 16 gradations, but the A/D conversion circuit 12 is not limited to this.
A/D conversion may be performed at a plurality of gradations such as 64, 128, 256, etc. At this time, the data processed by the image processing device 200 is processed at each of a plurality of gray levels.

Table 1 Table 2 Table 3 Table 4 Table 5 Table 6 Table 7 "Effects of the Invention" As described in detail below, according to the present invention, the detection probability of the appearance inspection device and the limb inspection After calculating and determining the appearance probability of a surface defect on the object for each predetermined gray level, an evaluation value of the inspection ability of the inspection device is calculated based on the detection probability and the appearance probability described in 1. Therefore, the evaluation value f+Ili for evaluating the inspection ability of the above-mentioned visual inspection apparatus can be accurately and quickly calculated as 15.

In addition, in addition to the detection probability and the appearance probability, the evaluation 11III value of the inspection ability of the inspection device is calculated based on the predetermined importance of each gray scale.
By taking into account the importance of each gray scale, it is possible to accurately and quickly obtain an evaluation value for evaluating the inspection ability of the visual inspection apparatus.

Furthermore, the evaluation value of the inspection ability of the inspection device is calculated using a predetermined value of the detection probability (1+4
The same effect can be obtained even if

[Brief explanation of the drawing]

FIG. 1 is a block diagram of a visual inspection and evaluation device that is an embodiment of the present invention, and FIGS. 2 to 8 are graphs showing evaluation results in experimental examples evaluated using the above evaluation device, respectively. ■... Central processing unit (CPU), 2... Read only memory (ROM), 3... Random access memory (RAM), 4... Keyboard, 5... Display device, 10... Target Inspection object, 11... Video camera, 12... Analog-digital conversion circuit (A/D conversion circuit), 100... Imaging device, 200... Image processing device. Patent applicant: Bell; Agent for IBM Chemical Industry Co., Ltd. Patent attorney: Seihaku Ao, and 1 other person Fig. 1 Fig. 2 Dark ■ 1 tone 1 12 +516 ; Le [Additional key 1 Fig. 4 1 Music scale haze 1 Tontan degree tone 1 Fig. 5 3L light 1 key i ''a missing and Yang 3131 Fig. 6 5! Immersion degree training 1 7th LA Mit5 Enakubo pi8 Tears 1 Geo [5 Flame RPi tone i

Claims (8)

[Claims] (1) In an inspection capability evaluation method for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. Calculate the detection probability, which is the probability that the appearance inspection device can detect an image of each density gradation, based on image data including all of the above-mentioned density gradations, and determine whether there is a defect on the surface for each of the above-mentioned density gradations. An appearance probability, which is the probability that the defect will appear, is calculated based on the data of the grayscale image of the inspected object, and a first A second sum, which is the sum of the appearance probabilities of each of the gray scales, is calculated over all the gray scales, and the first sum is calculated over all the gray scales. An inspection capability evaluation method for a visual inspection device, characterized in that the division is performed by the second sum, and the divided value is used as an evaluation value of the inspection capability of the visual inspection device. (2) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. a first calculating means for calculating a detection probability that is a probability that the visual inspection device can detect an image of each gray level based on image data including all of the gray levels; a second calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected having a defect on its surface; and each grayscale of the detection probability and the appearance probability. a third calculation means for calculating a first sum, which is a sum of products for each density gradation, over all the density gradations; and a second sum, which is a sum of the appearance probabilities of each density gradation. and a fifth calculation means for dividing the first sum by the second sum. An inspection ability evaluation device for a visual inspection device, characterized in that the divided value is used as an evaluation value of the inspection ability of the visual inspection device. (3) In an inspection capability evaluation method for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. Calculate the detection probability, which is the probability that the appearance inspection device can detect an image of each density gradation, based on image data including all of the above-mentioned density gradations, and determine whether there is a defect on the surface for each of the above-mentioned density gradations. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the gray scale image of the inspected object, and the above detection probability, the appearance probability, and the predetermined values for each gray level for the inspected object are calculated. A first sum, which is the sum of the products of the above-mentioned importance level and the above-mentioned gray level gradation, is calculated over all the above-mentioned gray scale gradations, and the above-mentioned appearance probability and the above-mentioned importance are calculated for each gray level gradation. A second sum, which is the sum of the products, is calculated over all the gray scales, the first sum is divided by the second sum, and the divided value is an evaluation value of the inspection ability of the visual inspection device. An inspection ability evaluation method for an appearance inspection device, characterized in that: (4) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. a first calculating means for calculating a detection probability that is a probability that the visual inspection device can detect an image of each gray level based on image data including all of the gray levels; a second calculation means for calculating an appearance probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected that has a defect on its surface; the detection probability, the appearance probability, and the object to be inspected; a third calculating means for calculating a first summation, which is the sum of the products of each of the gray scales with a predetermined importance level for each gray scale, over all of the gray scales; , a fourth calculation means for calculating a second sum, which is the sum of the products of the appearance probability and the importance level for each of the gray scales, over all the gray scales; and the first total sum. and a fifth calculation means for dividing by the second summation, and the division value obtained by the fifth calculation means is used as an evaluation value of the inspection ability of the appearance inspection apparatus. Inspection ability evaluation device for equipment. (5) In an inspection capability evaluation method for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object to be inspected based on the data of the grayscale image, for each predetermined grayscale gradation. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the grayscale image of the object to be inspected that has a defect on the surface, and the appearance probability, which is the probability that the defect will appear, is calculated, and the image data including all the grayscales is calculated for each grayscale. a first value which is the sum of the products of the appearance probability and the detection probability, which is the probability that the appearance inspection device can detect an image of each density gradation, and which is predetermined based on the
A second sum, which is the sum of the appearance probabilities of each of the gray scales, is calculated over all the gray scales, and the first sum is calculated over all the gray scales. An inspection capability evaluation method for a visual inspection device, characterized in that the division is performed by the second sum, and the divided value is used as an evaluation value of the inspection capability of the visual inspection device. (6) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. a first calculation means for calculating an appearance probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected having a defect on its surface; It is the sum of the products of the detection probability and the appearance probability, which are predetermined based on image data including gradations, and which is the probability that the appearance inspection device can detect images of each gradation level, for each gradation level. 1st
a second calculation means for calculating the sum of the appearance probabilities for each of the gray levels over all the gray levels; 3 calculation means, and a fourth calculation means for dividing the first sum by the second sum, and the division value obtained by the fourth calculation means is used to calculate the inspection capacity of the visual inspection apparatus. An inspection ability evaluation device for an appearance inspection device, characterized in that an evaluation value is used. (7) In an inspection ability evaluation method for an appearance inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the grayscale image of the object to be inspected that has a defect on the surface, and the appearance probability, which is the probability that the defect will appear, is calculated, and the image data including all the grayscales is calculated for each grayscale. a detection probability that is predetermined based on the probability that the appearance inspection device can detect an image of each density gradation, the above-mentioned appearance probability, and a predetermined importance of each density gradation for the inspected object. The first sum, which is the sum of the products for each of the above gray scales, is calculated over all the gray scales, and the sum of the products of the above probability of appearance and the above importance level for each gray scale is calculated. Calculating a certain second sum over all the gray scales, dividing the first sum by the second sum, and using the divided value as an evaluation value of the inspection ability of the visual inspection device. Inspection ability evaluation method for featured appearance inspection equipment. (8) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected as a grayscale image and inspects defects on the surface of the object based on the data of the grayscale image, for each predetermined grayscale gradation. a first calculation means for calculating an appearance probability that is a probability that the defect will appear based on data of a grayscale image of the object to be inspected having a defect on its surface; Detection probability, which is predetermined based on image data including gradations, and is the probability that the appearance inspection device can detect an image of each gradation, the appearance probability, and a predetermined value for each gradation of gradation for the object a second calculation means for calculating a first sum, which is the sum of the products of the above-mentioned importance levels, for each of the above-mentioned grayscale levels, over all the above-mentioned grayscale levels; a third calculating means for calculating a second sum, which is a sum of products for each of the gray scales, over all the gray scales; and a third calculation means for dividing the first sum by the second sum. 4 arithmetic means, wherein the division value obtained by the fourth arithmetic means is used as an evaluation value of the inspection ability of the visual inspection apparatus.