JPH0763686A - Mounted component inspection apparatus - Google Patents

Abstract

PURPOSE:To provide a mounted component inspection apparatus which can realize an efficient teaching operation and a stable inspection by automatically computing an optimum binary-coded threshold value which is used to extract a hue pattern from a color image obtained by imaging a mounted component on a board. CONSTITUTION:When a mounted component 11S on a reference board 10S is imaged by an imaging part 15 in a teaching operation, an image processing part 25 generates information about brightness on the basis of its color image and generates information about an adaptation degree to a prescribed pattern. In addition, it generates information, by hues, giving the evaluation criterion or an image quality on the basis of the pieces of information. In addition, it automatically computes brightness giving a best image quality as a binary-coded threshold value on the basis of the information. It performs a binary-coding processing operation by using the binary-coded threshold value, and it extracts a pattern for every hue.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a component mounted on a printed circuit board (hereinafter simply referred to as "circuit board"),
Before and after soldering, it relates to the mounting component inspection device used to inspect the presence or absence of components, the attitude, etc. after soldering (hereinafter simply referred to as "mounting quality"). The present invention is a technique for extracting a hue pattern for inspecting the mounting quality of a component by binarizing a color image obtained by picking up an image of a mounted component on a board by a binarization threshold value. Regarding

[0002]

2. Description of the Related Art Conventionally, FIG.
As shown in FIG. 1, a color television camera 4 is provided above the substrate 1 to be inspected, and an annular light source 5R for emitting different hue light (for example, red light, green light, and blue light) at different elevation angles with respect to the inspection position. , 5G, 5B are proposed.

This mounting component inspection apparatus irradiates the substrate 1 to be inspected with red light, green light and blue light from the respective light sources 5R, 5G and 5B at the same time, and reflects them on the surface of the soldering portion 3 of the component 2, for example. Each hue light is observed by the color television camera 4. The color image obtained by the color television camera 4 is taken into the image processing device 6, and the image pickup pattern corresponding to the curved surface property of the soldering part 3 is binarized for each hue to obtain a hue pattern of three primary colors. After the determination, each hue pattern is collated with the reference pattern to determine a good soldering product of the soldering site 3.

By the way, when using this mounted component inspection apparatus, prior to the inspection, the mounted component inspection is performed for each type of the substrate to determine what position and what component are mounted on the substrate to be inspected. The device needs to be taught. This teaching work is called “teaching”. The inspection data of the mounted component includes not only the position and type of the component mounted on the substrate to be inspected, but also information about the image necessary for the automatic inspection and its determination standard. This image and information about the judgment criteria include information about the land on the board to which each component is soldered (shape, length, width, etc.), information about the window set as the inspection area (shape, size, etc.), There are information (characteristics such as chromaticity and lightness) relating to the characteristic parameters indicating the soldering state on the land, and judgment criteria for judging the quality of the characteristic parameters.

[0005]

In this teaching and inspection, in order to obtain the feature amount of the component, a color image obtained by imaging the mounted component on the board is binarized by a predetermined binarization threshold value. Each hue pattern will be extracted by performing the rectification process, but in order to realize an appropriate mounted component inspection,
Precise extraction of this pattern is a prerequisite. Conventionally, since the operator adjusts the binarization threshold value for pattern extraction while checking the hue pattern each time, it takes time to determine the binarization threshold value. However, since it depends on the experience of the operator and the like, there is a problem that the determination result of the binarization threshold value varies greatly due to individual differences and stable inspection cannot be performed.

The present invention has been made in view of the above-mentioned problems, and an optimum binarization threshold value for extracting a hue pattern from a color image obtained by picking up an image of a mounted component on a substrate is set. An object of the present invention is to provide a mounted component inspection device that can realize efficient teaching work and stable inspection by automatically calculating.

[0007]

According to the present invention, a color image obtained by picking up an image of a mounted component on a board is binarized by a binarization threshold value to inspect the mounting quality of the component. And a window scanning means for setting and scanning a window in a predetermined range on the color image, and a brightness of the color image in the window scanned by the window scanning means. Second information for each hue relating to the degree of conformity between the first information generating means for generating the first information regarding the color information and the predetermined pattern preset for the color image within the window scanned by the window scanning means. Second
Information generating means and third information generating means for generating, for each hue, third information for giving an image quality evaluation criterion from the first and second information generated by the first and second information generating means. Means and threshold value calculating means for calculating the brightness that gives the best image quality based on the third information generated by the third information generating means, as a binarization threshold value for extracting each hue pattern. It is equipped with.

[0008]

When the color image obtained by picking up the image of the mounted component on the board is captured, the third information giving the image quality evaluation standard is obtained from the first information on the brightness and the second information on the compatibility. After being generated for each hue, a binarization threshold value for extracting each hue pattern is automatically calculated based on the third information. Therefore, it takes no time to determine the binarization threshold value, the efficiency of teaching work is improved, and the determination result of the binarization threshold value does not change due to individual differences of operators, and stable inspection can be performed. Furthermore, the binarization threshold value is obtained from the brightness that gives the best image quality, and the image quality evaluation criterion is generated from the degree of conformity with a predetermined pattern that contains intermediate information, so it is possible to finely calculate the binarization threshold value. Becomes

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 shows the overall construction of a mounted component inspection apparatus which is an embodiment of the present invention. This mounted component inspection device
The reference substrate 10S obtained by imaging the reference substrate 10S
Characteristic parameters of the inspection area of each upper part 11S,
The inspected substrate 1 obtained by imaging the inspected substrate 10T
This is for inspecting the mounting quality of each component 11T by comparing with the characteristic parameters of the inspection region of each component 11T on 0T.
The light projecting unit 14, the image pickup unit 15, the control processing unit 16 and the like are included as its components.

The X-axis table unit 12 and the Y-axis table unit 13 each include a motor (not shown) that operates based on a control signal from the control processing unit 16. The X-axis table unit is driven by these motors. The unit 12 is the imaging unit 1
5 is moved in the X direction, and the Y axis table 13 moves the conveyor 17 supporting the substrates 10S and 10T in the Y direction.

The light projecting section 14 has different diameters, and based on a control signal from the control processing section 16, red light, green light,
Three annular light sources 18, 19 that simultaneously emit blue light
Each of the light sources 18, 19 and 20 is centered directly above the observation position and positioned in different elevation angles when viewed from the observation position.

Each of the light sources 18, 19 and 20 is constituted by a light source which emits light of a red light spectrum, a green light spectrum and a blue light spectrum having a light emission energy distribution with respect to wavelength so as to become white by mixing colors, and each light source 18 ，
It is possible to adjust the light amount of each hue light by the imaging controller 28 described later so that the red light, the green light, and the blue light emitted from 19 and 20 are mixed to become white light.

Next, as the image pickup section 15, a color television camera is used, and the image pickup section 15 is positioned right above the observation position so as to face downward. As a result, the substrate 10S, 1 that is the object of observation
The reflected light on the surface of 0T is picked up by the image pickup unit 15, converted into color image signals of three primary colors, and supplied to the control processing unit 16.

The control processor 16 includes an A / D converter 21, an image memory 22, a memory 23, and a teaching table 2.
4, image processing unit 25, determination unit 26, XY table controller 27, image pickup controller 28, display unit 29, printer 30, keyboard 31, floppy disk device 3
2, the control unit 33, etc., in the teaching mode, select the component type corresponding to each component 11S on the reference substrate 10S from the floppy disk set in the floppy disk device, call it, and observe position A determination data file is created by applying characteristic parameters such as chromaticity and lightness to the inspection area of each component of the reference board 10S that has been carried in.

When the control processing unit 16 is in the inspection mode,
Color image signals R, G, B for the inspected substrate 10S
Is processed to extract each hue pattern of red, green, and blue for the inspection region of each component 11T on the inspected substrate 10T, generate characteristic parameters, and create an inspected data file.
Then, the inspection data file is compared with the determination data file, and the inspection substrate 10T is obtained from the comparison result.
The mounting quality such as the quality of soldering is automatically determined for each of the above components 11T.

FIG. 2 shows the cross-sectional shape of the solder 7 when soldering is good, when parts are missing, when there is insufficient solder, and the imaging pattern by the imaging unit 15 in each case, red, This is an example of the relationship with each hue pattern of green and blue, and since there is a clear difference between any of the hue patterns, it is possible to judge the presence or absence of parts and the quality of soldering. .

Returning to FIG. 1, the A / D converter 21 A / D-converts the color image signals of the three primary colors from the image pickup section 15 to generate image data R, G, B of the three primary colors. R, G and B are stored in the image memory 22 in pixel units. The memory 23 is provided with a threshold value table TB which will be described later and is used as a work area of the control unit 33.

The image processor 25 calculates the lightness L and the hues r, g and b of the three primary colors pixel by pixel from the red, green and blue image data R, G and B supplied via the controller 33. , By comparing with the binarization threshold value described later,
After performing the value conversion process, the inspection data file and the determination data file are created and supplied to the control unit 33 and the determination unit 26.

The teaching table 24 stores the judgment data file when it is supplied from the control unit 33 at the time of teaching, and when the control unit 33 outputs a transfer request at the time of inspection, the judgment data file is stored according to this request. It is supplied to the control unit 33, the determination unit 26, and the like.

The determination unit 26 compares the determination data file supplied from the control unit 33 at the time of inspection with the inspection data file transferred from the image processing unit 25, and determines each component 11T of the inspection substrate 10T. The quality of the soldering state is determined, and the determination result is output to the control unit 33.

The image pickup controller 28 includes an interface for connecting the control unit 33 to the light projecting unit 14 and the image pickup unit 15, and adjusts the light amount of each of the light sources 18 to 20 of the light projecting unit 14 based on the output of the control unit 33. Control is performed or the mutual balance of the respective hue light outputs of the imaging unit 15 is maintained.

The XY table controller 27 is a controller 3
3, the X-axis table unit 12 and the Y-axis table unit 13
The control unit 33 is provided with an interface for connecting with
The X-axis table unit 12 and the Y-axis table unit 13 are controlled based on the output of.

The display unit 29 receives image data, inspection results, key input data, etc. from the control unit 33,
This is displayed on the display screen, and when the inspection result or the like is supplied from the control unit 33, the printer 30 prints it out in a predetermined format.

The keyboard 31 includes operation information and reference board 1.
Various keys necessary for inputting data, commands, threshold value information and the like regarding 0S and the substrate 10T to be inspected are provided, and the key input data is supplied to the control unit 33.
The control unit 33 includes a microprocessor and the like,
According to the procedure shown in FIGS. 3 and 4, the operation of the mounted component inspection device in teaching and inspection is controlled.

FIG. 3 shows a step 1 of the teaching procedure.
(Indicated by "ST1" in the figure) to step 16. First, in step 1 of the figure, the operator uses the keyboard 3
1 is operated to register the board name to be taught, and the board size is keyed in. Then, in the next step 2, the reference board 10S is set on the Y-axis table 13 and the start key is pressed. To do. Next, at step 3, the origin of the reference substrate 10S and the upper right and lower left corners are set to the image pickup unit 15.
The actual reference board 10S is picked up by
After the size is input, the control unit 33 controls the X-axis table unit 12 and the Y-axis table unit 13 based on the input data to position the reference substrate 10S at the initial position.

The reference board 10S has a good mounting quality in which a predetermined component 11S is properly soldered at a component mounting position. When the reference board 10S is positioned at the initial position, In step 4, the imaging unit 15
Captures an area on the reference board 10S and teaches the mounting position of the component and the component type.

The following steps 5 to 9 are procedures for setting the inspection area for each component on the board. First, in step 5, the operator operates the key to start the setting of the inspection area. As a result, in the next step 6, the counter j in the control unit 33 is initialized to "1", and in step 7, the first inspection area is set. After that, it is judged in the next step 8 whether or not all the inspection areas have been set. If the judgment is "NO", the value of the counter j is incremented in step 9 and the process returns to step 7.

When the inspection areas are set for all the components on the board, the determination in step 8 is "YES",
In step 10, the reference substrate 10S is unloaded, and in step 11, another counter n in the control unit 33 is initialized to "1".

Next, in step 12, when the operator gives an instruction to extract the characteristic parameters for the first inspection region set in the procedure of steps 5 to 9, the color input image is taken in from the image pickup unit 15 and A / Image data R, G, B of three primary colors which have been D-converted and are stored in the image memory 22.
Are stored in pixel units.

Now, assuming that the image data of the three primary colors of a pixel in the inspection area are R, G and B, respectively, the image processing unit 25
Is the lightness L of this pixel by executing the following equation:
The red hue r, the green hue g, and the blue hue b are calculated.

[0031]

[Equation 1]

[0032]

[Equation 2]

[0033]

[Equation 3]

[0034]

[Equation 4]

The lightness L and the hues r, g, and b are calculated for all the pixels in the target area, so that the image processing unit 25 uses the optimum binary value for extracting each hue pattern. After automatically calculating the threshold
Binarization processing is performed using the threshold value to extract each hue pattern, and the characteristic parameter is extracted from the hue pattern (step 13).

In the next step 14, it is judged whether or not the extraction of the characteristic parameters for all the inspection areas is completed depending on whether or not the value of the counter n matches the total number j of the inspection areas. If "NO", the value of the counter n is incremented in step 15, and then the process returns to step 13 again to extract the characteristic parameter in the next inspection region.

As a result of repeated execution of the same procedure, if the judgment in step 14 is "YES", step 16
Then, the image processing unit 25 creates a judgment data file using the position of the part, the kind of the part, the inspection area of each part, the characteristic parameter in each inspection area, etc. and stores it in the teaching table 24, and the teaching procedure is completed. To do.

FIG. 4 shows steps 1 to 9 of the procedure for automatic inspection of mounted components. First, steps 1 and 2 in the figure
Then, a board name to be inspected is selected and a board inspection start operation is performed. In the next step 3, the supply of the inspected substrate 10T to the mounted component inspection device is checked. If the determination is “YES”, the conveyor 17 operates and the Y-axis table portion 13 is inspected by the inspected substrate 10T. Are loaded and the automatic inspection is started (steps 4 and 5).

In step 5, the control section 33 controls the X-axis table section 12 and the Y-axis table section 13 so that the image pickup section 1 for the first component 11T on the inspected substrate 10T.
The field of view 5 is positioned and imaged, each land area in the inspection area is automatically extracted, and the image processing unit 25
The inspected data file is created by calculating the characteristic parameters of each land area in the same manner as during teaching.
Then, the control unit 33 transfers this inspection data file to the determination unit 26, compares this inspection data file with the determination data file, and determines the first part 11T.
Therefore, the mounting quality such as the quality of soldering is judged.

Such an inspection is repeatedly executed for all the components 11T on the inspected substrate 10T. As a result, if there is a soldering defect, the defective component and the contents of the defect are displayed on the display unit 29 or the printer. After being printed on 30, the substrate 10T to be inspected is carried out from the observation position (steps 7 and 8). Thus, when the same inspection procedure is executed for all the inspected substrates 10T, the determination in step 9 becomes "YES", and the inspection is completed.

FIG. 5 shows an example of the configuration of the binarization processing unit 40 included in the image processing unit 25. The hue degree calculating unit 41, the hue degree threshold value calculating unit 42, the lightness calculating unit 43, the lightness. It includes a threshold value calculation unit 44 and a binary image generation unit 45.

The hue degree calculator 41 scans a color image within a designated target area, and obtains image data (red, green, and blue luminance data R, G, B) of each pixel captured in accordance with the scanning. (2) to (4) described above using
By executing the calculation of the formula, each hue degree r,
Calculate g and b. These hue degrees r, g, and b are given to the hue degree threshold value calculation unit 42.

The hue degree threshold value calculating section 42 receives the hue degrees r, g, for each pixel input from the hue degree calculating section 41.
From b, the optimum binarization threshold value TH _R , TH _G , for each hue,
This is for calculating TH _B, which will be described in detail later, but a method of obtaining an optimum binarization threshold value by obtaining an image quality evaluation value is used.

The lightness calculation section 43 scans the color image in the designated target area, and uses the image data R, G, B of each pixel captured in accordance with the scanning.
The brightness L is calculated for each pixel by executing the calculation of the equation (1). This lightness L is given to the lightness threshold value calculation unit 44.

The lightness threshold value calculator 44 converts the hue values r, g, and b into the binarization threshold value TH of each hue value.
_R TH _G , TH _B, and for calculating only the binarized threshold values TH _LR , TH _LG , TH _LB for each hue from the lightness L of each target pixel only for the pixels satisfying the conditions described later. However, the method of obtaining the optimum binarization threshold value by obtaining the image quality evaluation value is the same as above.

The target area is designated by operating the keyboard 31, whereby the target area to be binarized in the color image is designated, and the hue to be binarized or excluded, that is, red. , Green or blue is specified.

The binary image generator 45 performs a binarization process using any of the binarization thresholds calculated by the brightness threshold calculator 44 to generate a binary image.

FIG. 6 shows the above-mentioned 2 for generating a binary image.
The control procedure of the digitization processing unit 40 is shown in steps 1 to 7. First, when the color image is taken into the control processing unit 16 at the start point, the color image is stored in the image memory 22. Then, in accordance with the procedure shown in FIGS. 8 to 10 described later, the keyboard 31 is used to specify the target area to be binarized and the hue to be binarized or not.

Next, in step 1, the image processing unit 2
After calculating the hue degrees r, g, and b for each pixel by scanning the color image in the target area by the hue degree calculating unit 41 of No. 5, the hue degree threshold calculating unit 42 calculates the hue degree calculating unit 41. By inputting the hue degrees r, g, b for each pixel, an image quality histogram is generated for each hue, and the optimum binarization threshold values TH _R , TH _G , TH _B are calculated for each hue from each image quality histogram. (Steps 2 and 3).

Next, in step 4, the brightness calculation unit 4
3 calculates the lightness L for each pixel by scanning the color image in the target area, and then the lightness threshold value calculation unit 44 converts the hue values r, g and b into the binarization threshold value of each hue value. T
Compared with H _R , TH _G , and TH _B , the lightness L of each target pixel is input from the lightness calculation unit 43 only for the pixels satisfying the conditions described later, and an image quality histogram is generated for each hue.
Further, optimum binarization thresholds TH _LR , TH _LG , and TH _LB are calculated for each hue from each image quality histogram (step 5,
6).

Next, in step 7, the binary image generation unit 45
Is a binarization threshold value corresponding to a designated color among the binarization threshold values TH _LR , TH _LG , and TH _LB calculated by the brightness threshold value calculation unit 74. Processing to generate a binary image.

FIG. 7 shows a threshold value table TB which is created based on a key input from the keyboard 31 and is referred to in the binarization process. In the figure, TH _LR , TH _LG ,
TH _LB is a binarization threshold of lightness for each hue, and TH _R
TH _G and TH _B are binarization threshold values of the hue degree for each hue. FF _L , FF _r , FF _g , and FF _b are upper limit flags that indicate whether or not each of the binarization thresholds is the upper limit for binarization processing. If these flags are “1”, If it is present, it means that it is the upper limit value, and if it is "0", it means that it is the lower limit value. Further, S _r , S _g , and S _b are color designation identification data indicating whether each hue is a target of binarization processing or not, and if the value is “1”, the hue is It indicates that it is a target of the binarization process, and if it is “0”, it indicates that the hue is not a target.

Thus, the binary data q by the binarization process
(Q = 1 or 0) is blue if the specified hue is red, and if it is green, and if it is green, then it is blue by if there is,
Each is determined by the logical formula shown in formula (7).

[0054]

[Equation 5]

[0055]

[Equation 6]

[0056]

[Equation 7]

8 to 10 show the keyboard 31 described above.
The procedure of the designation operation by is shown in steps 1-27. First, in step 1 of the figure, a guide character (message) is displayed on the display unit 29 to specify the target area,
In the subsequent step 2, a guide character is displayed so as to input the coordinates of the end points (start point and end point) that define the target area.

FIG. 11 shows the color image 8, in which the coordinates (x1, y1) of the starting point P and the coordinates (x2, y) of the ending point Q are shown.
By inputting 2) and 2 on the keyboard 31, the rectangular target area 9 is designated.

Steps 3 to 7 in FIG. 8 show the procedure for designating the target area. When this procedure is completed, a confirmation display for designating the target area is displayed on the display unit 29, and then red and green are displayed. , A guide character is displayed so as to specify one of the hues of blue (steps 8 and 9).

When a desired color is designated by the key operation in the next step 10, the determination becomes "YES", and in the following steps 11 to 15, red and green are selected as the hues to be binarized or not to be binarized. , Determine which color is blue.

If red is designated as the hue to be binarized, the determination in step 11 is "YES".
Therefore, "1" is set as the identification data S _r for designating red and "0" is set as the upper limit value flag FF _{r in the} threshold value table TB (steps 16 and 1).
7).

If green is specified as the hue to be binarized, the determination in step 12 is "YES", and if blue is specified, the determination in step 13 is "YES". Color designation identification data S _g , S _b
And the upper limit value flags FF _g and FF _b are set respectively (steps 18 and 19 and steps 20 and 2).
1).

If red is designated as the hue to be excluded from the binarization processing, the determination in step 14 is "Y".
“ES”, and “0” as the identification data S _r for red designation.
And the upper limit value flag FF _r is set to "1" in the threshold value table TB (step 2).
2, 23).

If green is designated as the hue to be excluded from the binarization processing, the determination in step 15 is "YE".
S ”, and when blue is designated, the determination in step 15 is“ NO ”, and the same color designation identification data S _g ,
S _b and upper limit value flags FF _g and FF _b are set (steps 24 and 25 and steps 26 and 26, respectively).
27).

In the next step 28, a guide character is displayed on the display unit 29 so as to specify whether the image part to be binarized is the lighter or the darker one of the specified hues.

When the brightness is specified by the key operation in the next step 29, the judgment is "YES", and it is judged in the next step 30 whether or not the brighter one is specified. If the determination is “YES”, the upper limit value flag FF _L is “0”, and if the step 3
If the determination of 0 is "NO", "1" is set in the threshold value table TB as the upper limit value flag FF _L.

The threshold value table TB is set in this way, and the binarization threshold value T of the hue degree for each hue is further set.
H _R , TH _G , and TH _B are calculated and the threshold table T
After being set to B, the lightness calculation unit 43 calculates the lightness L for each pixel in the target area. If the red color is currently designated as the hue to be binarized, the lightness is calculated. The threshold value calculation unit 44 generates an image quality histogram from the brightness of each target pixel only for pixels whose hue r of each pixel is equal to or greater than the binarization threshold TH _{R, and} performs optimal binarization from the image quality histogram. Find the threshold value TH _LR .

When the brighter red color is designated, the binary image generation unit 45 extracts the pixels whose brightness L of each pixel is equal to or higher than the binarization threshold TH _LR, and when the darker red color is selected. If specified, the brightness L of each pixel is 2
Pixels smaller than the threshold value TH _LR are extracted and binary images are generated. The same applies when green or blue is designated, and a description thereof will be omitted here.

FIG. 12 shows an example of a circuit configuration used in the hue threshold calculating section 42 and the lightness threshold calculating section 44 described above. In the figure, a CPU 51 controls an address generator 53 via a CPU bus 52 to generate necessary addresses, control signals, timing signals, etc.
Output to each component. The image memory 22 is controlled in writing and reading in response to a control signal input via the image control bus 55, and the image address bus 54
The image data supplied from the image data bus 56 is written to or read from the address input via the. An image bus 57 including an image address bus 54, an image control bus 55 and an image data bus 56.
Are also connected to other circuits not shown.

The image memory 22 stores, for example, color image data for one field (or one frame) (see FIG. 14).
Data of the screen 120 shown in FIG. Of the image data written in the image memory 22, the image data in a predetermined range (the range designated by the window 121 in FIG. 14) is read out, and the latch circuits 59, 60, the 1H delay circuit 65, the latch circuit 61, 62, 1H delay circuit 66,
It is sequentially supplied to the latch circuits 63 and 64. The 1H delay circuits 65 and 66 delay the input data by 1H and output it, and the latch circuits 59 to 64 latch the input data. As a result, as shown in FIG. 14, N (nine in the case of the embodiment) pixels p ₀ designated by the window 121 in the screen 120.
The image data up to p ₈ is extracted and supplied to the illegal pattern determination unit 68. In the case of this embodiment, the pixel p ₀ is arranged at the center, and the pixels p _{0 to} p ₈ are arranged sequentially in the counterclockwise rotation direction. The image data of the pixel p ₀ latched by the latch circuit 61 is the illegal pattern histogram generation unit 69 and the brightness histogram generation unit 7.
It is also supplied to 0.

The illegal pattern determination section 68 is, for example, as shown in FIG.
It is configured as shown in FIG. The subtraction circuits 81 to 88 are supplied with the image data of the pixels p _{1 to} p _{8 and} the image data of the pixel p ₀ . The subtraction circuits 81 to 88 calculate differences in brightness q _{1 to} q ₈ between the pixels p _{1 to} p ₈ and the pixel p _0, and the edge matching calculation circuit 10
Output to 1 to 108. That is, the subtraction circuits 81 to 88
As shown in FIG. 15, with the pixel p ₀ at the center in the window 121 as a reference, eight pixels p _{1 to} p ₁ around it are
To create a brightness pattern of the difference between q ₁ ~q ₈ of _8.

The edge conformance calculation circuit 101 uses the MFC
(Membership Function Circuit) 91 to 98 and a minimum value circuit 99 that selects the minimum value of its output, and the outputs q _{1 to} q ₈ of the subtraction circuits 81 to 88 are MF.
Input to C91 to 98, respectively. MFC 91-98
Stores the membership function corresponding to each pixel position based on the fuzzy model in the edge direction in the window 121, and executes the process corresponding to this membership function.

That is, the MFCs 91 to 98, as shown in FIG. 16, correspond to the fuzzy model of the edge in the direction 1 pointing upward 45 degrees to the right, and the membership functions Z, N
Or P is stored. More specifically, the pixel p ₁
To p ₅ (brightness difference q _{1 to} q ₅ ) corresponding to MFC91
˜95 sets the membership function Z to pixels p ₂ ˜p
₄ MFC92～9 corresponding to (difference q ₂ to q ₄ brightness)
4 stores membership function N, and MFCs 96 to 98 corresponding to pixels p _{6 to} p ₈ (brightness difference q _{6 to} q ₈ ) store membership function P, respectively.

The membership functions N, Z and P are shown in FIG.
It has the input / output characteristics shown in. That is, the membership function N has a brightness difference q
When (q _{1 to} q ₈ ) is smaller than −q _b , the goodness of fit μ
(Μ _{11 to} μ ₁₈ ) has a maximum value of 1, and a minimum value of 0 when it is greater than 0. When the value is between −q _b and 0, it is set to an intermediate value of 1 to 0 corresponding to the value. Set. The membership function P has a fitness μ of minimum value 0 when the brightness q is less than 0, and a maximum value 1 when greater than q _b ,
When an intermediate value of 0~q _b, an intermediate value between 0 and 1 in response to the value. The membership function Z sets the fitness μ to the minimum value 0 when the absolute value of the brightness q is larger than q _a ,
The maximum value is 1 when the absolute value is smaller than q _b . And
When the absolute value of the brightness q is larger than q _{b and} smaller than q _a , the goodness of fit μ is set to an intermediate value from 1 to 0 corresponding to the value.

As described above, the MFCs 91 to 98 use the membership function N, Z or P to be stored as a reference, and the brightness difference q input from the corresponding subtraction circuits 81 to 88.
Goodness of fit μ _{11 to} μ ₁₈ is calculated from the size of _{1 to} q ₈ . The larger the value of the fitness μ ₁₁ (closer to 1), the more appropriate the binarized image can be obtained by binarizing the data of the pixel p ₁ with the brightness of the pixel p ₀ as a reference. become. This also applies to the pixels p _{2 to} p ₃ .

The minimum value circuit 99 selects the minimum one of the matching degrees μ _{11 to} μ ₁₈ output from the MFCs 91 to 98,
It is output as the fitness μ ₁ of the edge fitness calculation circuit 101. That is, each pixel p _{1 to} p ₈ in the window 121
Is to find the minimum value of the goodness of fit μ _{11 to} μ ₁₈ when binarized with respect to the brightness of the pixel p ₀ .
It is nothing but the finding of the minimum adaptability obtained by binarizing the brightness of the pixel p ₀ .

The edge conformance calculation circuits 102 to 108 are also
The fuzzy model of the membership function, which is configured similarly to the edge conformance calculation circuit 101, is stored in the MFC, and the direction of the edge is defined as the direction 2 to the direction 8 as shown in FIGS. ing. The edge directions of the direction 2 to the direction 8 are the upward direction, the leftward 45 degree upward direction,
The left horizontal direction, the left 45 ° downward direction, the downward direction, the right 45 ° downward direction, or the right horizontal direction.

The maximum value circuit 100 is _{one of} the fitness levels μ _{1 to} μ ₈ output from the edge fitness level calculation circuits 101 to 108.
Select the maximum one and output it as the goodness of fit μ. That is, of the minimum conformity that is obtained when the edge conformance calculation circuits 101 to 108 associate the directions (image patterns) of the edges in the window 121 with the directions 1 to 8 (preset patterns). Since the largest one is selected, the matching degree μ means that the matching degree in the most appropriate direction is selected from the directions 1 to 8.

The fitness μ output from the maximum value circuit 100 is
It is input to the subtraction circuit 112 of the fuzzy negation operation circuit 110. The value “1” in the fuzzy logic output from the “1” generation circuit 111 is applied to the other input of the subtraction circuit 112, and the subtraction circuit 112 subtracts the fitness μ from the value “1” to obtain a value μ ′. (= 1-μ) is output. That is, μ ′ represents an inappropriate degree (invalidity) of the most appropriate pattern.

The above processing is performed by the address generator 5
3, the image memory 22, the latch circuits 59 to 64, and the window scanning unit 67 having the 1H delay circuits 65 and 66 repeatedly scan the window 121 over the entire screen 120 as shown in FIG.

Illegal pattern histogram generator 69
Creates a histogram of the degree of illegality by cumulatively adding the degree of illegality μ ′ at each scanning position of the window 121 for each brightness of the reference pixel p ₀ at that time. In addition, the brightness histogram generation unit 70 cumulatively adds the number of reference pixels p ₀ for each brightness to generate a brightness histogram of all pixels on the screen.

The image quality histogram generation unit 71 divides the cumulative value for each brightness output by the illegal pattern histogram generation unit 69 by the corresponding cumulative value for each brightness output by the brightness histogram generation unit 70 to obtain a normal value. Turn into. As a result, an image quality histogram as shown in FIG. 18 is obtained.
In FIG. 18, the horizontal axis represents brightness, and the vertical axis represents poor image quality (illegalness) as an image quality evaluation standard. Therefore, when the binarization is performed with the brightness k _opt that provides the bottom value (negative peak value) in FIG. 18 as the reference (binarization threshold), the poor image quality is minimized. That is, the best binary image can be obtained.

The optimum threshold value search section 72 searches the brightness (binarization threshold value) at which the bottom value of the image quality histogram generated by the image quality histogram generation section 71 is obtained, and outputs it to the CPU 51. The CPU 51 binarizes the brightness of all the pixels of the screen 120 based on the input binarization threshold value and generates a binarized image.

The above processing will be further described by using a fuzzy logic arithmetic expression as follows. That is,
The process in the illegal pattern determination unit 68 shown in FIG. 12 can be expressed by the following equation (8).

[0085]

[Equation 8]

Here, q _i represents the difference in brightness (q _{1 to} q ₈ ), and μji (q _i ) is the membership function of the fuzzy label corresponding to the pixel position i in the direction j in the fuzzy model of FIG. (N, Z, P) is represented (that is, processing of MFCs 91 to 98 is represented). MINi
Is an operation for obtaining the minimum value obtained by changing i (processing of the minimum value circuit 99), MAXj is an operation for obtaining the maximum value obtained by changing j (processing of the maximum value circuit 100),
Each represents. Even if the minimum value operation or the maximum value operation in the equation (8) is an operation that satisfies the conditions of t norm (t norm) or t conorm (t conorm), a similar effect can be obtained.

The processing of the illegal pattern histogram generating section 69 can be expressed by the following equation (9).

[0088]

[Equation 9]

Here, f _hist (p ₀ ) represents the possibility of generating an illegal pattern in the brightness (binarization threshold value) of the pixel p ₀ . Also, the terms f _{hist that} are the same on the left and right of the equation
The insertion of (p ₀ ) means that the illegality μ ′ is added to this and a new value is obtained.

Furthermore, if the brightness histogram generated by the brightness histogram generating section 70 is hist (k), the processing in the pixel histogram generating section 71 is hist.
When (k) = 0, it can be expressed by the following expression (10), and when hist (k) ≠ 0, it can be expressed by the following expression (11).

[0091]

[Equation 10]

[0092]

[Equation 11]

Here, q _hist (k) represents the image quality histogram generated by the image quality histogram generation unit 71, and Q ₀ is the maximum value (constant).

[0094]

As described above, according to the present invention, a binarization threshold value for extracting an arbitrary hue pattern from a color image obtained by picking up an image of a mounted component on a substrate is automatically calculated. Therefore, it takes less time to determine the binarization threshold value, the efficiency of the teaching work is improved, and the determination result of the binarization threshold value does not change due to individual differences of operators, and stable inspection can be performed. Further, the binarization threshold value is obtained from the brightness that gives the best image quality, and the image quality evaluation standard is generated from the degree of conformity with a predetermined pattern containing intermediate information, so it is possible to finely calculate the binary threshold value. Becomes

[Brief description of drawings]

FIG. 1 is a block diagram showing the overall configuration of a mounted component inspection device that is an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing the relationship between the quality of soldering and a pattern.

FIG. 3 is a flowchart showing a procedure of teaching.

FIG. 4 is a flowchart showing a procedure of automatic inspection.

FIG. 5 is a block diagram showing a configuration example of a binarization processing unit of the image processing unit.

FIG. 6 is a flowchart showing a control procedure of a binarization processing unit.

FIG. 7 is an explanatory diagram showing a threshold table.

FIG. 8 is a flowchart showing a procedure of a designation operation using a keyboard.

FIG. 9 is a flowchart showing a procedure of a designation operation using a keyboard.

FIG. 10 is a flowchart showing a procedure of a designation operation using a keyboard.

FIG. 11 is an explanatory diagram showing a method of specifying a target area.

FIG. 12 is a block diagram showing an example of a circuit configuration used in a hue threshold calculator and a lightness threshold calculator.

FIG. 13 is a block diagram illustrating an example of an illegal pattern determination unit.

FIG. 14 is an explanatory diagram for explaining the operation of the embodiment in FIG.

FIG. 15 is an explanatory diagram for explaining the operation of the subtraction circuit in FIG.

16 is an explanatory diagram showing an edge pattern of a fuzzy model of MFC in FIG. 13. FIG.

17 is an explanatory diagram showing the input / output characteristics of the membership function of the MFC in FIG.

18 is an explanatory diagram showing an image quality histogram generated by an image quality histogram generation unit in FIG.

FIG. 19 is an explanatory diagram showing a configuration of a mounted component inspection device.

[Explanation of symbols]

 10S, 10T Substrate 11S, 11T Component 15 Imaging unit 16 Control processing unit 25 Image processing unit 42 Hue intensity threshold calculation unit 44 Brightness threshold calculation unit 45 Binary image generation unit 67 Window scanning unit 68 Illegal pattern determination unit 69 Illegal pattern histogram generation unit 70 Brightness histogram generation unit 71 Image quality histogram generation unit 72 Optimal threshold value search unit

Claims (1)

[Claims] 1. A mounting component for binarizing a color image obtained by imaging a mounting component on a substrate by a binarization threshold value to extract a hue pattern for inspecting the mounting quality of the component. An inspection apparatus, wherein window scanning means for setting and scanning a window in a predetermined range on the color image, and first information relating to brightness is generated from the color image in the window scanned by the window scanning means. First information generating means, and second information generating means for generating, for each hue, second information relating to the degree of conformity with a predetermined pattern preset for the color image in the window scanned by the window scanning means. A third information for generating, for each hue, third information for giving an image quality evaluation standard from the first and second information generated by the first and second information generating means. Generating means, and threshold calculating means for calculating, based on the third information generated by the third information generating means, the brightness that gives the best image quality as a binarizing threshold for extracting each hue pattern. A mounting component inspection device comprising: