JPH01231181A - Method and device for evaluating inspection capacity for visual inspecting device - Google Patents

Abstract

PURPOSE:To exactly and quickly obtain an evaluation value by calculating and deriving the detection probability and the appearance probability of a defect of the surface in an object to be inspected, at every degree of the feature quantity of an image for showing a feature of an image of the object to be inspected, respectively and thereafter, calculating an evaluation value of the inspection capacity. CONSTITUTION:With respect to all objects to be inspected having a contamination defect on the surface, probability of appearance data of the contamination defect in each contamination area (j) is derived, and the probability is stored in a RAM 3 as appearance probability G(j) of the contamination defect in each contamination area (j) to the object to be inspected. After the first inspection capacity has been calculated, this data is outputted to a display device 5 and displayed. Also, a CPU 1 reads out detection probability F(j) of an image pickup device 100 stored in the RAM 3, the appearance probability G(j) of the contamination defect and a degree of importance H(j), and calculates the second inspection capacity, and thereafter, outputs this data to the display device 4 and displays it. In such a way, since the first or the second inspection capacity can be calculated automatically, with respect to a visual inspecting device, the performance can be evaluated quickly and exactly.

Description

Detailed Description of the Invention [Industrial Field of Application] The present invention is directed to a visual inspection device for photographing an object to be inspected and inspecting defects on the surface of the object based on the data of the photographed image. This invention relates to a testing ability evaluation method and device.

[Prior Art] Conventionally, a two-dimensional camera is used to image an object to be inspected, or a one-dimensional camera is used to image the object while the object is moved in a direction perpendicular to the scanning direction of the one-dimensional camera. Various measurement methods, defect detection algorithms, inspection devices, etc. are used to detect defects such as dirt, scratches, damage, and missing parts on the surface of the inspected object from the two-dimensional grayscale or colored images obtained by has been devised.

[Problems to be Solved by the Invention] However, it is difficult to properly and objectively quantify which inspection methods and devices are appropriate for the objects to be inspected that actually require inspection for the above-mentioned defects in appearance. There was no evaluation method or device to display the results.

Therefore, when selecting a method or device for detecting the above-mentioned defects from the photographed gray scale image or colored image as a powerful means for performing visual inspection, it is necessary to accurately express and evaluate the inspection ability of the inspection device. or could not be confirmed. 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 and inspects defects on the surface of the object based on the data of the photographed image. In the inspection ability evaluation method, the visual inspection device evaluates each degree of the feature amount based on image data including all the degrees of the feature amount of the image representing the characteristics of the image of the inspected object. The detection probability, which is the probability that the image can be detected, is calculated, and the appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected, which has a defect on the surface, for each degree of the feature amount. , a first sum, which is the sum of the products of the detection probability and the appearance probability for each degree of the feature amount, is calculated over all degrees of the feature amount, and the probability of appearance for each degree of the feature amount is calculated. A second summation, which is a summation, is calculated over all degrees of the feature amount, and the first summation is divided by the second summation, and the divided value is used as an evaluation value of the inspection ability of the visual inspection device. It is characterized by

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 and inspects defects on the surface of the object based on the data of the photographed image. Detection probability that is the probability that the visual inspection device can detect an image with each degree of the feature amount based on image data including all the degrees of the feature amount for each degree of the feature amount of the image representing the feature of the image. The first step to calculate
a second calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on the surface for each degree of the feature amount; a third calculating means for calculating a first sum, which is the sum of the products of the detection probability and the appearance probability for each degree of the feature amount, over all degrees of the feature amount; a fourth calculation means for calculating a second sum, which is the sum of the appearance probabilities, over all degrees of the feature quantity; and a fifth calculation means for dividing the first sum by the second sum. The method is characterized in that the divided value obtained by the fifth calculation means is used as an evaluation value of the inspection ability of the visual inspection device.

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 and inspects defects on the surface of the object based on the data of the photographed image. Detection probability, which is the probability that the visual inspection device can detect an image with the above feature quantity based on image data including all the above feature quantities for each feature quantity capacity of the image representing the feature of the image. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected that has a defect on its surface for each volume of the feature quantity, and the detection probability and the appearance probability are calculated. Calculating a first sum, which is the sum of the products of the predetermined importance for each capacity level of the feature quantity for the object to be inspected, for each capacity level of the feature quantity, over all degrees of the feature quantity; A second sum, which is the sum of the products of the appearance probability and the importance for each degree of feature quantity, is calculated over all degrees of the feature quantity, and the first sum is calculated as the second sum. and the divided value is used as an evaluation value of the inspection ability of the visual inspection device.

The evaluation device of the fourth invention is an inspection ability evaluation device for an appearance inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image. Detection probability, which is the probability that the visual inspection device can detect an image with the above feature quantity based on image data including all the above feature quantities for each feature quantity capacity of the image representing the feature of the image. The first step to calculate
a second calculating means that calculates an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on the surface for each capacity of the feature quantity; The first sum, which is the sum of the products of the detection probability, the appearance probability, and the predetermined importance level for each capacity level of the feature quantity for the object to be inspected, for each capacity level of the feature quantity is calculated. a third calculation means that calculates over all degrees; and a second sum, which is the sum of the products of the appearance probability and the importance level, for each capacity level of the feature amount, over all degrees of the feature amount. a fourth calculation means; and a fifth calculation means for dividing the first sum by the second sum; It is characterized in that the evaluation value is

The evaluation method of the fifth invention is an inspection capability evaluation method for an appearance inspection apparatus that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected that has a defect on its surface for each capacity of the feature quantity of the image representing the feature of the image, and the capacity of the feature quantity is calculated. The feature amount is predetermined based on image data including all the degrees of the feature amount for each degree, and is the probability that the appearance inspection device can detect an image with the capacity degree of the feature amount and the detection probability and the appearance probability. The first sum, which is the sum of the products for each capacity degree, is calculated over all the degrees of the feature quantity, and the second sum, which is the sum of the appearance probabilities of the capacity degree of the feature quantity, is calculated for the feature quantity. The method is characterized in that the calculation is performed over all degrees, 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.

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 and inspects defects on the surface of the object based on data of the photographed image. a first calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on its surface for each degree of feature amount representing the feature of the image; The detection probability and the appearance probability are predetermined based on image data including all the degrees of the feature amount for each degree of feature amount, and are the probability that the appearance inspection device can detect an image having the degree of the feature m. a second calculation means for calculating a first sum, which is the sum of products for each degree of capacity of the feature amount, over all degrees of the feature amount; and a sum of the appearance probabilities of the six degrees of the feature amount. a third calculation means for calculating a second sum over all degrees of the feature amount; and a fourth calculation means for dividing the first sum by the second sum; The method is characterized in that the divided value obtained by the means is used as an evaluation value of the inspection ability of the visual inspection device.

The evaluation method of the seventh invention is an inspection ability evaluation method for an appearance inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on data of the photographed image. 6 of the image feature quantity representing the image feature of
Calculate the appearance probability, which is the probability that the defect will appear, based on the data of the image of the object to be inspected that has a defect on the surface for each degree, and include all degrees of the feature amount for every 6 degrees of the feature amount. a detection probability that is predetermined based on image data and is a probability that the appearance inspection device can detect an image with six degrees of the feature amount; The first total #U, which is the sum of the products of the above feature amount for every six degrees with the importance level
is calculated over all degrees of the feature amount, and a second sum, which is the sum of the products of the appearance probability and the importance level for every six degrees of the feature amount, is calculated over all degrees of the feature amount, The method is characterized in that 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.

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 and inspects defects on the surface of the object based on data of the photographed image. 6 of the image feature quantity representing the image feature of
a first calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a surface defect for each degree; Detection probability, which is predetermined based on image data including all degrees of the feature amount, and is the probability that the appearance inspection device can detect an image with six degrees of the feature amount, the appearance probability, and the six degree of feature amount for the object to be inspected. a second calculation means for calculating a first sum, which is the sum of the products of each of the six degrees of the feature amount and the predetermined importance of each of the features, over all the degrees of the feature amount; The second, which is the sum of the products of the above feature quantities for each six degrees, with the importance level.
and a fourth calculation means for dividing the first sum by the second sum. The method is characterized in that the obtained division value is used as an evaluation value of the inspection ability of the visual inspection device.

Furthermore, in each of the above inventions, the feature amount of the image is
It is characterized by the area of dirt defects on the surface of the object to be inspected.

[Operations] According to the first and second inventions, there is an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image. In the above, the visual inspection device can detect images of six degrees of the feature amount based on image data including all degrees of the feature amount for every six degrees of the feature amount of the image representing the feature of the image of the inspected object. The detection probability, which is the probability, is calculated, and the appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected, which has a defect on the surface, for every six degrees of the feature amount, and the detection probability is calculated. A first sum, which is the sum of the products of six degrees of the feature amount, and the appearance probability, is calculated over all degrees of the feature amount, and a first sum, which is the sum of the products of the six degrees of the feature amount, is calculated. 2 is calculated over all degrees of the feature quantity, 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.

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, an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected and inspects defects on the surface of the object based on data of the photographed image, Based on the image data including all the degrees of the upper gripping amount for each of the six degrees of the feature amount of the image representing the characteristics of the image of the object to be inspected, A certain detection probability is calculated, and an appearance probability, which is the probability that the defect appears, is calculated based on the data of the image of the object to be inspected that has a defect on the surface for each degree of the feature amount, and the above detection probability and the above are calculated. A first sum, which is the sum of the products of the appearance probability and the predetermined importance level for each degree of the feature amount for the object to be inspected, for each degree of the feature amount is calculated over all degrees of the feature amount. Then, a second sum, which is the sum of the products of the appearance probability and the importance for each degree of the feature, is calculated over all degrees of the feature, and the first sum is calculated as the second sum. The result is divided by the total sum, and the divided value is used as the evaluation value of the inspection ability of the appearance 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, in an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected and inspects defects on the surface of the object based on data of the photographed image. , calculate the appearance probability, which is the probability that the defect will appear, based on the data of the image of the object to be inspected, which has a defect on the surface, for each degree of the feature amount of the image representing the feature of the image of the object to be inspected; The detection probability and the appearance probability are predetermined for each degree of the feature amount based on image data including all the degrees of the feature amount and are the probability that the appearance inspection device can detect an image with each degree of the feature amount. A first sum, which is the sum of the products for each degree of the feature amount, is calculated over all the degrees of the feature amount, and a second sum, which is the sum of the appearance probabilities of each degree of the feature amount, is calculated as the sum of the products of each degree of the feature amount. The calculation is performed over all degrees of the feature amount, 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. 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, an inspection ability evaluation method for an appearance inspection apparatus that photographs an object to be inspected and inspects defects on the surface of the object based on data of the photographed image. Calculating the appearance probability, which is the probability that the defect will appear, based on the data of the image of the object to be inspected, which has a defect on the surface, for each degree of the feature amount of the image representing the feature of the image of the object to be inspected; Detection probabilities that are predetermined based on image data including all degrees of the feature amounts for each degree of the feature amounts, and are probabilities that the appearance inspection device can detect images of each degree of the feature amounts; and the appearance probability. and a predetermined degree of importance for each degree of the feature amount for the object to be inspected, and a first sum total for each degree of the feature amount is calculated over all degrees of the feature amount, A second sum, which is the sum of the products of the appearance probability and the importance for each degree of the feature, is calculated over all degrees of the feature, and the first sum is calculated by the second sum. The divided value is used as the 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.

Note that the feature amount of the image is, for example, the area of a dirt defect on the surface of the object to be inspected, or the circumferential length of the object to be inspected.

[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 ROM).
That's what it means. ) 2. Random access memory (hereinafter referred to as RAM)
That's what it means. ) 3, an image processing device 200 having a keyboard 4 and a display device 5;
00 is an inspection mode in which dirt defects on the surface of an object to be inspected are inspected using the imaging device 100, and the above VLT imaging device 100.
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, the video camera 11 photographs the inspected object 10 irradiated with light from the light projector 20, and then includes information on a two-dimensional grayscale image of one field (one screen). A black and white television signal is output to the A/D conversion circuit 12. The A/D conversion circuit 12 performs A/D conversion on the input television signal image in 16 gradations, and outputs the converted image data to the CPU 1 via the connector 30 of the image processing device 200. Here, the image data output from the A/D conversion circuit 12 has a gradation in which each pixel of one screen is expressed in 16 gradations (hereinafter referred to as gradation, and the gradation is the lightest gradation). The image data of one screen consists of image data of 1OOOO pixels.

The CPUI is a control circuit that controls operations within the image processing device 200, and the ROM 2, RAM 3, and display device 5 are connected to the CPUI.

The ROM 2 stores a system program for controlling the inspection mode and the first and second evaluation modes in the image processing device 200, and the RAM 3 stores a system program for controlling the inspection mode and the first and second evaluation modes in the image processing device 200.
Used as a work area for the PUI and as a CPU
The image data input to I is temporarily stored. The display device 5 displays each image of the image data input to the CPUI and the image data temporarily stored in the RAM 3, and also displays the data of the inspection results and evaluation results calculated by the CPUI.

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. The image data of the above-mentioned normal image is composed of gray scale data for each pixel for one screen.

Next, when inspecting for defects on the surface of the object to be inspected, the object to be inspected is photographed using the video camera 11, and the image data of the photographed image (hereinafter referred to as image data of the inspection image) is A/D converted. R via circuit 12 and CPUI
It is stored in AM3 and displayed on display device 5. Next, the CPU 1 compares the image data of the inspection image stored in the RAM 3 with the image data of the normal image previously stored in the RAM 3 with respect to the gray scale data of each pixel, and determines the gray scale of each pixel. Count the number of different pixels. Here, the counted number of pixels j is proportional to the area of dirt on the surface of the inspected object, so
Hereinafter, the soil area will be referred to as j. Furthermore, the CPUI outputs the data of the dirt area J to the display device 5 for display, and also stores it in the RAM 3.

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. It becomes an image.

On the other hand, if an object to be inspected has a dirty surface and, for example, ink is attached to the surface, the image of the area where the dirt is attached in the image of the object to be inspected (hereinafter referred to as a smeared image) is The image becomes a pitch black image, and the image data of the dirt image has the predetermined dirt area j corresponding to the area of the adhered portion. Further, for example, when white powder adheres to the surface of the object to be inspected, the image data of the part to which the stain is attached in the stain image corresponds to the area of the adhered part and has the predetermined stain area j.

Figures 2 and 3 show the detection probability F for the soil area j.
3 is a graph showing the relationship between (j) and the appearance probability G(j) of a stain defect.

Here, the detection probability F (j) is a characteristic unique to the inspection device, and the detection probability for each dirt area j included in a normal image is 0, whereas the detection probability when a dirt image can be reliably detected is The detection probability for each stain area is 1. If the inspection device is not perfect and does not detect an image of the dirt area j with a certain probability, the detection probability will be less than 1.

In the above visual inspection and evaluation device, the detection probability depends on the performance of the imaging device 100.

In addition, the appearance probability G(j) of a dirt defect is the probability that a dirt defect occurs in each dirt area j among all the dirt defects that occur in a large number of objects to be inspected, for example, 100 or more manufactured in the same process. It is a probability. Note that the sum of the above appearance probabilities for each stain area j is 1. This probability of appearance can be determined statistically if there is no change in the manufacturing process, but cannot be determined statistically if there is a change in the manufacturing process. Therefore, in general, when there is a change in the raw material or manufacturing process of the object to be inspected, the above-mentioned appearance probability changes.

As shown in Figure 2, the detection probability of the inspection device is 0 when the soil area j is 20 or less, and 0 when the soil area j corresponding to the area of the company emblem is 4601 to 5000. and l for other soiled areas j, and on the other hand, if the soiled area j is always larger than the area of the company emblem, the inspection device can always detect the stains.

In other words, in the case where the area of soil that appears is always larger than the area of the company emblem, as long as the inspection device operates normally, it is possible to detect the contaminated object with 100% probability, and the inspection described above The inspection capability of the device will be 100%.

On the other hand, as shown in FIG. 3, when the surface area j of the appearing stain almost matches the area of the company emblem, that is, strictly speaking, when the detection probability is O in the area of the company emblem, the inspection device cannot always detect contaminated objects. Therefore, the inspection ability of the above-mentioned inspection device is 0%.

In this embodiment, the first inspection ability Kl(J) of the inspection system including the inspection apparatus and the object to be inspected is expressed by the following equation.

Here, F(j) is the detection probability of the inspection device in the dirt area j, and G(j) is the appearance probability of the dirt defect in the inspection device in the dirt area j.

Further, Fr(j) is the detection probability of the ideal inspection device for the soil area j, and is 1.

That is, assuming that the first inspection ability of the inspection system including the inspection device and the object to be inspected is 1, the detection probability F(j) of the inspection device for each contamination area j and its contamination area are calculated as shown in equation (la). The appearance probability G of a dirt defect appearing at j
(j), and the value obtained by summing the product value for each soil area j over all soil areas j, and the above value in an ideal inspection device where the detection probability is 1 for all soil areas j. Use the sum value and the ratio value. Here, when the soil area j to be investigated is made infinitely large, the detection probability F(j) of the inspection device for each soil area j is given as the inspection performance of the inspection system, as shown in equation (1b). The product is calculated by the appearance probability G(j) of the appearance of a dirt defect in the dirt area j, and the value obtained by integrating the value of the stain in each dirt area over all the dirt areas j,
The value obtained by calculating the above-mentioned integral value in the above-mentioned ideal inspection apparatus and the ratio value are used.

If we use the index for the above inspection performance, for example, if the performance of the inspection equipment is good and the soil area of the soiled defect on the inspected object does not match the ground color of the company emblem or the area of the mark, the value will be close to l. However, the detection probability of the inspection device itself for each dirt area j is 1
If it is smaller, or if the probability that the soil area j of the soil defect matches the area of the ground color or mark increases, the value of 1 for the inspection ability will become smaller and become closer to 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 above-mentioned first inspection ability is determined.

Next, in the above-mentioned first index of inspection performance of 1, it is assumed that the influence of a dirt defect on the product to be inspected is a constant value of 1, regardless of the dirt area j of the dirt defect. However, in the real case, for example, the degree of deterioration of the image of the product when there is a stain defect with a small stain area j is lower than the degree of deterioration of the image of the product when there is a stain defect with a larger stain area j. It is often evaluated as small. Therefore, an evaluation that also takes this factor into account is more appropriate.

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

Here, H(j) is a numerical value (
Hereinafter, it will be referred to as importance level. ), and the larger the value of the importance, the greater the image deterioration that the stain defect gives to the object to be inspected (the higher the importance of the stain area j is).

In other words, the second inspection capability of the inspection system including the inspection device and the test object is as shown in equations (2a) and (2b), where each numerator and denominator in equations (1a) and (1b) are is multiplied by the above importance level. Here, the degree of importance H(j) 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 of this inspection ability as a guide, we can determine how much inspection ability the inspection system essentially has for the inspection object as a product that gives the inspection object. 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

As shown in Fig. 4, the importance level H(
By setting j), the inspection ability of the inspection apparatus can be displayed in consideration of the degree of importance indicating the degree of deterioration of the image of the product to be inspected. Figure 4 shows a general example, where the probability of appearance of a dirt defect with a relatively small dirt area j is high, but conversely the importance of a relatively small dirt area j is made small; The importance of big dirt is increasing.

For example, 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 above inspection ability is, , or, for example, 0. If it is 4 or more, the inspection system is considered to have valuable inspection ability. In addition, if the test performance is, for example, 6 or more, the test system becomes even more valuable, and if it is, for example, 0.8 or more, the test system becomes extremely valuable.

(2) First evaluation mode First, in order to find the detection probability of the imaging device 100,
10,000 images (hereinafter referred to as reference images) having all the dirt areas j are photographed using the video camera 11, and the image data of the reference image, which is the image data of the photographed images, is transferred to the A/D conversion circuit. 12 and R via CPUUI
Store in AM3. Then, cput reads the above RAM3
It is detected whether each of the 10,000 image data of the reference image stored in Store.

Next, the procedure for obtaining the image data of the 10,000 reference images described above is repeated, for example, 10 times or more, and the average value of the image data of the reference images for each of the dirt areas j is calculated as the detection probability F(j ) is stored in RAM3.

Further, an object to be inspected with no dirt or defects on its surface is photographed in advance using the video camera 11, image data of a normal image is obtained in the same manner as in the above inspection mode, and is stored in the RAM 3.

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, that is, the image data of the stain image is sent to the A/D conversion circuit 12 and the CPU.
It is stored in RAM3 via I. Next, the CPU 1 compares the image data of the inspection image stored in the RAM 3 with the image data of the normal image previously stored in the RAM 3 with respect to the gray scale data of each pixel, and determines the gray scale of each pixel. Count the number of different pixels. Here, the counted number of pixels j is the dirt area j, as described above, and the CP
U1 displays the data of the dirt area j on the display device 5 and stores it in the RAM 3.

Next, after repeating the above procedure for determining the soil area j for 100 or more test objects manufactured in the same manufacturing process and having dirt defects on the surface, , find the probability of appearance data of dirt defects in each dirt area j, and convert this probability into appearance probability G of dirt defects in each dirt area J for the above-mentioned object to be inspected.
(j) and stored in the RAM 3.

Further, the CPU l calculates the detection probability F(j) of the imaging device 100 and the appearance probability G of dirt defects stored in the RAM 3.
After reading (j) and calculating the first testability using the above equation (1a), the data of the testability is output to the display device 5 and displayed. This completes the operation of the first evaluation mode.

For example, when the inspection ability is 0.4 or more, it is assumed that the inspection ability of the inspection system is at least a predetermined value and is passed, whereas an inspection ability of 1 is 0.4. 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 store it in the RAM 3 via the CPUI. Then, after calculating the above test performance, C according to the above evaluation criteria.
It is also possible to determine whether the PU1 passes or fails, and output the evaluation result to the display device 5 for display. Here, the evaluation standard for inspection performance is 0°4, but it is not limited to this, but it is also applicable to the inspection process, manufacturing process, degree of combined use with visual inspection, inspection cost and reliability, and equipment cost of automatic visual inspection equipment. It may be changed taking into consideration the following.

In the above-described operation in the first evaluation mode, the imaging device l
Although the inspection performance of OO is calculated, it is not limited to this, but the above detection probability changes by changing the imaging device, and the above appearance probability changes by changing the inspected object, so image processing Another imaging device equipped with a video camera and an A/D conversion circuit may be connected to the connector 30 of the device 200, and the inspection capability may be calculated as 1 for the same or another object to be inspected.

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

Next, the operator uses the keyboard 4 to input the degree of importance H(j) for each stain area j that indicates the degree of deterioration of the product, which has been predetermined based on the above-mentioned criteria for the object to be inspected. Data with importance level H(j) is sent to R via CPUI.
Stored in AM3.

Furthermore, cpul is the detection probability F(j) of the imaging device ■00 stored in the RAM 3 and the appearance probability G(
j) and the importance degree H(j), and after calculating the second testability using the above equation (2a), output the data of the testability to the display device 5 and display it. . This completes the operation of the second evaluation mode.

Table 1 is a graph showing the detection probability, appearance probability, and importance level in an experimental example in which the above-mentioned company emblem was evaluated using this inspection and evaluation device. The probability and importance are shown in Figure 5.

When the second inspection performance of the inspection apparatus of the experimental example shown in Table 1 and FIG. 5 is calculated using the above inspection apparatus and evaluation apparatus, it becomes 0.94, respectively. Therefore, the inspection equipment in Table 1 is
Since it has a very large inspection capacity, it can be said that its ability as an inspection device is very high.

As explained above, in a visual inspection and evaluation device that inspects dirt defects on an object to be inspected and evaluates its inspection ability, it is possible to automatically calculate the above-mentioned first or second inspection ability K I+. Therefore, 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 evaluation examples shown in Figures 2 to 5 above, it is assumed that the stain area j is undetectable when the stain area j matches the area of the company emblem, but this is not limited to this. Normal images with different gradations may exist other than company emblems. In this case, it is necessary to determine the detection probability by also considering these images.

In the above embodiments, an apparatus is described that uses a grayscale image of the object to be inspected to check whether there is a dirt defect on the surface of the object. It may be possible to inspect flaws, the normality of the shape of the component, the normality of the position, direction, and orientation of the component, the size of the object to be inspected, the length of the object to be inspected, and the like. Therefore, instead of the dirt area j, continuous or discrete parameters (hereinafter referred to as image feature quantities) that can be easily calculated and obtained from an image of the appearance of the object to be inspected and represent the shape characteristics of the image are used. may also be used. The feature values of this image include the circumference of the object to be inspected, the ratio of the circumference to the area of the object to be inspected, the number of pixels in each gray scale, the number of holes in the object to be inspected, the circumference of the holes, The area of the hole, the circularity count of the object to be inspected, the shape count of the object to be inspected, the Feret diameter of the object to be inspected, the first moment of the object to be inspected, the second moment of the object to be inspected,
Moment relative to the area of the object to be inspected, coordinates of the center of gravity of the object to be inspected, basic statistical values of the object to be inspected, occupancy of the object to the entire image, angle between the maximum diameter of the object to be inspected and a specific axis, the object to be inspected Maximum brightness of the object, minimum brightness of the object to be inspected, diameter of the object to be inspected, volume of the object to be inspected, axial length of the elliptical object to be inspected, axial length ratio of the elliptical object to be inspected, average diameter of two axes of the object to be inspected , distance between two points on the object to be inspected, distance between two points on the object to be inspected, three-point angle on the object to be inspected, four-point angle on the object to be inspected, number of multiple objects to be inspected, plural The distance between the objects to be inspected may also be used.

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. This camera uses an IT camera that uses a storage type or non-storage type image pickup tube.
A V camera, MOS type, CCD type or intermediate type solid state camera can be used. Alternatively, a color video camera may be used as the video camera 11, and a colored image containing color information may be used instead of a grayscale image for evaluation.

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 The testability may be calculated 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, 4.8, 32, 4.8, 32,
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.

In the above embodiment, one screen of image data is 100
Although the image data has 00 pixels, it is not limited to this.
It may be image data having a plurality of pixels.

Table 1 [Effects of the Invention] As detailed above, according to the present invention, the detection probability of the appearance inspection device and the appearance probability of surface defects on the inspected object are respectively calculated from the image representing the characteristics of the image of the inspected object. After calculating and finding each degree of feature quantity, the evaluation value of the inspection ability of the inspection device is calculated based on the detection probability and the probability of appearance, so that the inspection ability of the appearance inspection device can be evaluated. evaluation values can be obtained accurately and quickly.

Further, in addition to the detection probability and the appearance probability, the evaluation value of the inspection ability of the inspection device is calculated based on the predetermined importance of each degree of the feature quantity.
Taking into consideration the degree of importance of each of the feature amounts, it is possible to accurately and quickly obtain an evaluation value for evaluating the inspection ability of the visual inspection device.

Furthermore, a similar effect can be obtained when the evaluation value of the inspection ability of the inspection apparatus is calculated using a predetermined value of the detection probability.

[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 5 are graphs showing evaluation results in experimental examples evaluated using the above evaluation device, respectively. l...Central processing unit (CPU), 2...Read only memory (ROM), 3...Random access memory (RAM), 4...Keyboard, 5...Display device, 10... Object to be inspected, 11... Video camera, 12... Analog-to-digital conversion circuit (A/D conversion circuit), 100... Imaging device, 200... Image processing device. Patent Applicant Kanekabuchi Chemical Industry Co., Ltd. Agent Patent Attorney Haka Maeda 1 person Figure 1 Figure 2 120 46015000 10000 Male;
nimen species j torture ω woman j Figure 3 120 46015000 1OoO05 ← 1 O t 1 Origineshi 11 Figure 4 Dirt [Phase] Rust 1

Claims (10)

[Claims] (1) In an inspection ability evaluation method for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. Calculate the detection probability, which is the probability that the visual inspection device can detect an image with each degree of the feature amount, based on the image data including all the degrees of the feature amount for each degree of the feature amount of the image, The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected that has a defect on its surface for each degree of quantity, and each of the feature quantities of the detection probability and the appearance probability are calculated. A first sum, which is the sum of products for each degree, is calculated over all the degrees of the feature quantity, and a second sum, which is the sum of the appearance probabilities of each degree of the feature quantity, is calculated over all the degrees of the feature quantity.
The method is characterized in that the sum total is calculated over all degrees of the feature quantity, the first sum sum is divided by the second sum sum, and the divided value is used as an evaluation value of the inspection ability of the visual inspection device. Inspection ability evaluation method for visual inspection equipment. (2) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. A first step of calculating a detection probability that is a probability that the appearance inspection device can detect an image with each degree of the feature amount based on image data including all the degrees of the feature amount for each degree of the feature amount of the image. a calculation means; a second calculation means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on the surface for each degree of the feature amount; a third calculating means for calculating a first sum, which is the sum of the products of the probability and the appearance probability for each degree of the feature amount, over all degrees of the feature amount; The second, which is the sum of the appearance probabilities,
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 obtained division value is used as an evaluation value of the inspection ability of the visual inspection device. (3) In an inspection capability evaluation method for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. Calculate the detection probability, which is the probability that the visual inspection device can detect an image with each degree of the feature amount, based on the image data including all the degrees of the feature amount for each degree of the feature amount of the image, The appearance probability, which is the probability that the defect will appear, is calculated based on the image data of the object to be inspected that has a defect on its surface for each degree of quantity, and the detection probability, the appearance probability, and the above for the object to be inspected are calculated. A first sum, which is the sum of the products of each degree of the feature amount with a predetermined importance level for each degree of the feature amount, is calculated over all the degrees of the feature amount, and the probability of appearance and the importance value are A second sum, which is the sum of the products of each degree of the feature amount with the degree, is calculated over all degrees of the feature amount, and the first sum is divided by the second sum, and the divided value is An inspection ability evaluation method for an appearance inspection device, characterized in that: is used as an evaluation value of the inspection ability of the appearance inspection device. (4) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. A first step of calculating a detection probability that is a probability that the appearance inspection device can detect an image with each degree of the feature amount based on image data including all the degrees of the feature amount for each degree of the feature amount of the image. a calculation means; a second calculation means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on the surface for each degree of the feature amount; The first sum, which is the sum of the products of the probability, the appearance probability, and the predetermined importance for each degree of the feature for the object to be inspected, for each degree of the feature is calculated as a third calculating means for calculating a second sum total for each degree of the feature amount of the appearance probability and the importance degree for each degree of the feature amount; 4 arithmetic means; and a fifth arithmetic means for dividing the first sum by the second sum. An inspection ability evaluation device for an appearance inspection device, characterized in that an evaluation value is used. (5) In an inspection ability evaluation method for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the image taken, the characteristics of the image of the object to be inspected are expressed. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected that has a defect on its surface for each degree of the feature amount of the image, and The product of the detection probability and the appearance probability, which is predetermined based on image data including all degrees of the feature amount and is the probability that the appearance inspection device can detect an image with each degree of the feature amount, for each degree of the feature amount. A first sum, which is the sum, is calculated over all the degrees of the above-mentioned feature quantity, and a second sum, which is the sum of the above-mentioned appearance probabilities of each degree of the above-mentioned feature quantity, is calculated.
The method is characterized in that the sum total is calculated over all degrees of the feature quantity, the first sum sum is divided by the second sum sum, and the divided value is used as an evaluation value of the inspection ability of the visual inspection device. Inspection ability evaluation method for visual inspection equipment. (6) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. a first calculation means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on the surface for each degree of the feature amount; and for each degree of the feature amount. Each of the feature amounts has a detection probability that is predetermined based on image data including all degrees of the feature amount and is a probability that the appearance inspection device can detect an image with each degree of the feature amount, and a probability of appearance. a second calculation means that calculates a first sum that is the sum of products for each degree over all degrees of the feature amount; and a second calculation means that is the sum of the appearance probabilities of each degree of the feature amount.
a third calculation means for calculating the sum of the sum of the features over all degrees of the feature amount, and a fourth calculation means for dividing the first sum by the second sum, the fourth calculation means An inspection ability evaluation device for a visual inspection device, characterized in that the obtained division value is used as an evaluation value of the inspection ability of the visual inspection device. (7) In an inspection ability evaluation method for an appearance inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. The appearance probability, which is the probability that the defect will appear, is calculated based on the data of the image of the object to be inspected that has a defect on its surface for each degree of the feature amount of the image, and Detection probability that is predetermined based on image data including all degrees of feature quantity and is the probability that the visual inspection device can detect an image with each degree of feature quantity, the above appearance probability, and each degree of feature quantity for the object to be inspected. A first sum, which is the sum of the products for each degree of the feature quantity with a predetermined importance level for each, is calculated over all degrees of the feature quantity, and A second sum, which is the sum of products for each degree of quantity, is calculated over all the degrees of the feature quantity, the first sum is divided by the second sum, and the divided value is calculated by the visual inspection device. An inspection ability evaluation method for an appearance inspection device, characterized in that the inspection ability is evaluated as an evaluation value of the inspection ability. (8) In an inspection ability evaluation device for a visual inspection device that photographs an object to be inspected and inspects defects on the surface of the object based on the data of the photographed image, the characteristics of the image of the object to be inspected are expressed. a first calculating means for calculating an appearance probability that is a probability that the defect will appear based on data of an image of the object to be inspected having a defect on its surface for each degree of the feature amount of the image; and each of the feature amounts of the image. A detection probability that is predetermined based on image data including all degrees of the feature amount for each degree and is a probability that the appearance inspection device can detect an image of each degree of the feature amount, the appearance probability, and the object to be inspected. a second calculation means for calculating a first sum, which is the sum of the products of each degree of the feature amount and a predetermined degree of importance for each degree of the feature amount, over all degrees of the feature amount; and a third calculation means for calculating a second sum, which is the sum of the products of the appearance probability and the importance level for each degree of the feature amount, over all degrees of the feature amount; and a fourth arithmetic means for dividing the sum by the second sum, and the divided value obtained by the fourth arithmetic means is used as an evaluation value of the inspection ability of the appearance inspection apparatus. Inspection ability evaluation device for inspection equipment. (9) Claim 1, 3, or 5, wherein the feature amount of the image is an area of a dirt defect on the surface of the object to be inspected or a circumferential length of the object to be inspected, or An inspection ability evaluation method for the appearance inspection device according to item 7. (10) Claims 2, 4, and 6, wherein the feature amount of the image is an area of a dirt defect on the surface of the object to be inspected or a circumferential length of the object to be inspected, or An inspection ability evaluation device for the appearance inspection device according to item 8.