JPH03202707A - Board-mounting inspecting apparatus - Google Patents

Abstract

PURPOSE:To improve the accuracy in inspection for the mounting state of a board by providing a constitution wherein a plurality of feature quantities extracted from input image data are used, and the mounted state of the board is inspected by a plurality of methods having the different principles. CONSTITUTION:Analog image signals in R (red), G (green) and B (blue) colors which are picked up through a CCD camera 101 are stored in frame memories 105 - 107 through A/D converters 102 - 104. The image data pass through an interface 108, an averaging circuit 109 and a noise removing part 110, and a region is extracted with a region extracting part 111. Feature quantities such as position data, shape data and the like are extracted from the extracted region in a feature-quantity extracting parts 112. Pattern matching between the feature quantity of the position data and the reference pattern from a reference-pattern generating part 115 is performed by a reverse-truth-value limiting method in a reverse-truth-value-limiting-method operating part 113. The feature quantity of the shape data and the like are matched with a reference pattern by fuzzy clustering in a fuzzy-clustering operation part 114. The results of two operations are synthesized in a Dempster combining part 116. The result of judgement is outputted from a judged-result outputting part 117.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a board mounting inspection apparatus for inspecting board mounting.

[Conventional technology]

In recent years, there has been an increasing demand for electronic devices to be smaller, lighter, and more multifunctional, and surface mounting technology is also being developed to meet these demands.

[Problem to be solved by the invention]

However, surface mount technology is still in its infancy;
The miniaturization of parts has taken the lead, and it is difficult to say that this has been established as a well-balanced production process, leaving much to be desired for future technological development. Among these, there is a particularly strong demand for automation of visual inspection.

Inspection items that are considered to be inspected by automatic visual inspection equipment include ■Presence of parts, installation position of parts, installation status of parts, ■ incorrect parts, ■ soldering conditions, etc., which are currently inspected visually. All of these are expected from automatic visual inspection.

Among these, various image inspection devices are commercially available for ■ to ■ because image processing is easy, but it is difficult to quantitatively evaluate the soldering condition of ■. Various methods have been proposed and studied up until now, but no reliable method has yet been developed, and the reality is that most people rely on visual inspection. It is an object of the present invention to provide a board mounting inspection device that can perform inspection.

[Means and effects for solving the problems] In order to solve the above problems, the board mounting inspection apparatus of the present invention includes means for extracting a plurality of feature quantities using input image data, and a plurality of features extracted by the extraction means. The present invention is characterized by having means for inspecting the mounting state of the board by a plurality of methods with different principles using the feature quantities.

In the above configuration, the extraction means extracts a plurality of feature quantities using the input image data, and the inspection means uses the feature quantities to inspect the mounting state of the board by a plurality of mutually different methods.

〔Example〕

Preferred embodiments of the present invention will be described with reference to the drawings.

Actual JL example” 2 A soldering tester according to a first embodiment of the present invention will be described.

FIG. 1 is a block diagram showing the overall configuration of a soldering tester according to this embodiment.

In Fig. 1, 101 is a CCD camera that reads image data as R, G, and B analog signals;
03.104 is an analog/digital converter, 105°1
06.107 is a frame memory that stores R, G, and B digital data, 108 is an interface,
109 is an averaging circuit that calculates the average value of R, G, and H for each pixel; 110 is a noise removal unit; 111 is a region extraction unit;
Reference numeral 12 denotes a feature amount extraction unit, 113 an inverse truth value limited rask ring operation unit, 115 a reference pattern generation unit that generates a reference pattern, and 116 a D e that combines the operation results of the inverse truth method and the fuzzy clustering operation. m
117 is a determination result output unit that outputs the final determination result; 118 is a motor for rotating or moving the CCD camera within a two-dimensional plane; 119 is a motor for driving the motor 118; This is a control unit that performs memory address control and other controls.

R (red) and G captured from the CCD camera 101
(green) and B (blue) analog image signals are A
/D converter 102. 103. 104, each is converted into multivalued digital data, and the frame memo Ij 10
5. 106. 107. This image data passes through the interface 10g, and an averaging circuit 109 calculates average value data. Next, in the noise removal section 110,
Noise removal is performed, and a region extraction unit 111 extracts a region from which a feature quantity is to be extracted. The feature amount extraction unit 112 extracts feature amounts related to position information, brightness information, shape information, etc. from the extracted region. There are 11 features related to location information.
3, the reference pattern generator 1 is
Matching with the reference pattern sent from 15 is performed. On the other hand, the amount of features related to brightness information and shape information is 114.
At , matching with the reference pattern from 115 is performed by fuzzy clustering. The results of these two operations are transferred to the D e m p st e r coupling unit 116
, the judgment results are synthesized according to the Dempster-Shafer combination rule and the confidence level is increased.
Output from 7.

FIG. 2 shows the overall processing flow of soldering and adhesion state inspection according to the present invention.

(Step 1) An image near the first lead of the IC is captured from the CCD camera 101, which is an image input unit, in 8 bits for each color component of R, G, and B for each pixel.

(Step 2) The average value (R+G+B)/3 of the R, G, and B data input in step 1 is taken and converted into a black and white image. In this embodiment, reading was performed using the three primary color components R, G, and H, but for example, any one of R, G, and B may be used as a single color component, or a combination of luminance and chromaticity such as Y, r,
Since the Q or especially the G (green) signal is close to the ND image, the device can be simplified by using the G monochromatic component. Pi.

It is also possible to input color components such as am and b* and use a luminance component. Here, the reason why a monochromatic image is generated is because the purpose of soldering in this embodiment is inspection, and color is not a very important parameter in that inspection, but the chromaticity parameter is taken into account. Judgments can also be made.

(Step 3) The image from which the monochromatic component was extracted in Step 2 is then subjected to noise removal (isolated point removal) in the noise removal unit 110 in FIG.
will be held. In this embodiment, 9×9 like the sixth
A pixel median filter is used.

The algorithm of the median filter is shown in FIG. In other words, the output of the median filter for one point of interest is first divided into a window (9 x 9
The data in the window is arranged in order of size, and the one in the middle is taken as the value at this point. This process is performed for the entire screen.

Note that it is also possible to use a method other than the median filter (for example, a smoothing filter).

Furthermore, the filter size is not limited to 9×9.

(Step 4) Next, region extraction is performed in the region extraction unit 111 in FIG. 1. FIG. 10 shows the region extraction algorithm.

The image data from which noise has been removed is binarized using 5tool for region extraction. A discriminant analysis method is used to determine the binarization threshold (S1001). The algorithm of the discriminant analysis method is shown in FIG. First, as shown in FIG. 8, a histogram of the density of the image is created, and based on this histogram, a threshold value k that maximizes the variance σB' (k) is repeatedly calculated. Then, the image data is binarized using this threshold value. Binarized image data is examined for connection points and regions are extracted (S1003
). Next, the area of each region is calculated by counting the number of dots (51004), and small regions smaller than a predetermined area are considered to be noise and removed (S100).
6). Then, the remaining areas are numbered (S1007). The image after numbering is shown in FIG.

(Step 5) The feature amount extraction unit 112 performs feature amount extraction for each numbered area. The feature values used this time are the 10th
As shown in the figure.

As shown in Figure 12, from the binary image of each area, F+-F
The feature amount of +a is extracted from the multivalued image as shown in Fig.
Calculate the feature amounts of 9 to F24. The calculation method for each feature is shown below.

■This information is required when calculating the feature amount of the circumscribed rectangle or less. A rectangle surrounded by vertical and parallel lines passing through the left, upper, right, and lower ends of the area is called a circumscribed rectangle (see FIG. 14).

■Location of center of gravity This is information that is not directly involved in size and shape recognition. (X G+ ¥c) in Figure 14 corresponds to the center of gravity.

(2) Aspect ratio A feature quantity that has been used in the past and is effective in shape recognition, also called aspect ratio, and is determined by the following equation using the circumscribed rectangle of a.

Aspect ratio = I Yu-YD I/I XRX
L■X average length: X maximum, Y average length; Find the projection of the Y maximum length region onto the coordinate axis, and calculate the average length X in the x (y) direction of its intensity distribution (referred to as marginal distribution) mean(Y
mean ) and the maximum length in the x (y) direction Xmax
(Ymax) Feature amount expressed as a ratio.

■Area The number of all pixels in the area is counted to determine the area.

This feature is related to size and not shape.

■Area density A feature expressed as the ratio of the area determined by ■ to the area of the circumscribed rectangle determined by ■.

@X-direction bias, Y-direction bias b Feature quantity that indicates how much the center of gravity is biased in the x (y) direction within the circumscribed rectangle a. Each, Xc-XL l /
I XR-XL l, l Yc-YU I/
It is calculated as I Yo-Yu 1.

■Perimeter This information is indicated by the length of the outline of the area.

Based on the information of ■Size■Area and ■Perimeter, it is a feature amount expressed as 2×Area/Perimeter.

This is a conventionally used feature amount expressed as (perimeter) 2/area based on the information of 0 circumferential surface ratio ■area and ■perimeter.

■X-axis marginal distribution dispersion, Y-axis marginal distribution dispersion Feature quantity shown by the dispersion for each axis of XSYS in the marginal distribution.

The feature quantity found from a multi-valued image is: (1) Average and variance The feature quantity is represented by the average and variance of the gray values of pixels in the area.

■Bounded variation (BVQ) Bounded variation is a feature quantity that reflects the local characteristics of a pattern and requires a small amount of calculation, and is defined by applying the concept of total variation of a bounded variation function in mathematics. . The amount of bounded variation in the digital grayscale image array P can be calculated as follows. When θ=00, search the region number array PN horizontally one by one, and only when two adjacent regions have the same region number,
The absolute value of the grayscale difference between two corresponding adjacent pixels is SDI Iθ=
In addition to 00, the absolute difference sum SD, lθ=00, is calculated.

At the same time, the number of difference calculations D+lθ=00
After processing the entire screen, θ=
Calculate the bounded variation amount BVQjlθ=0° in the o′ direction.

5Djlθ=0° =Σ(IP(1,J-1)-P(1
, J): PN (I, J-1) = PN (I, J)
) BVQil e = 0° =SDilθ=0'/D
Similar calculations are performed when +lθ=o'θ=45° 90° 135°, only that the PN search direction changes to the θ direction.

The above-described processing from image input (Sl) to feature amount extraction (s5) is repeated for all IC leads.

FIG. 4(a) is a diagram showing the IC, and FIG. 4(b) is an enlarged view of the hatched portion. In FIG. 4(b), 305 is a space that is not soldered, 306 is a board portion, and 307 is an IC lead portion. The image input of Sl is performed with respect to FIG. 4(b), and the above-mentioned processing is performed with respect to FIG.
Repeatedly extract feature amounts for all IC leads in a) and store them in memory.

In order to extract the characteristics of all IC leads in this way, the inspection apparatus of this embodiment has a configuration as shown in FIG. 3(a). That is, 301 places the inspection object. A plate 302 is a substrate to be inspected, 303 is a CCD camera, 304 is a CCD camera moving section, and 305 is a belt conveyor.

The CCD camera moving unit 304 moves the CCD camera 303 to
It is possible to input images of all IC leads by moving in the Y direction and rotating in the θ direction.

Next, the feature amounts obtained above are matched with the reference pattern to determine which pattern the input cover pattern belongs to. The reference patterns used in this example are: ■ Normal (lead part) ■ Normal (solder part) ■ Floating ■ Somewhat floating ■ Bridge ■ Solder ball ■ Insufficient solder (lead part)
■There are 8 types of solder shortages (solder parts).

FIGS. 15 to 20 show examples of binarized images of normal, floating, slightly floating, bridge, solder pole, and insufficient solder, respectively.

(Step 7) Among the above feature values, those related to shape (F7 to F)8
) and those related to brightness (F19 to F24), the fuzzy clustering calculation unit 114 applies the additional data fuzzy clustering method to calculate 'first evidence' regarding which state and how much the input image belongs to. do.

In this example, the reference pattern data is: ■ Normal (lead part) ■ Normal (solder part) ■ Floating ■ Somewhat floating ■
Bridge ■Solder ball ■Solder shortage (lead part)
■ Eight types of solder shortages (solder parts) were used. For each of these reference pattern data, typical samples obtained empirically are selected, and the same image processing as described above (averaging, noise removal, etc.) is performed on them, and the obtained feature quantities (F+ to F24 ) is input as a reference pattern vector from the reference pattern generation unit 115 and stored as internal knowledge.

Here, the reference vector may be, for example, a numerical value statistically obtained from a plurality of samples, or may be a numerical value obtained from a typical sample that is most desired to be matched. The algorithm of the additional data fuzzy clustering method is described below.

In the field of unsupervised pattern recognition, clustering techniques are used to determine which predetermined cluster each data vector of a data set to be handled belongs to. Clustering is the process of dividing a given multidimensional data set into a specified number of clusters by grouping data that are similar based only on the structure of the data set into the same cluster. 1
A cluster is a subset within a given data set, and partitioning is the formation of families of clusters. Each piece of data has the property of belonging to only one cluster in its division.

However, since pattern recognition deals with things that are seen and heard by humans, who are the subjects of recognition, complex elements such as human subjectivity and individuality come into play. That is,
There are ambiguities in the nature of the objects that cannot be explained by only the binary values of truth and effect, and these ambiguities are generally quite complex and diverse. In fields such as this, where human judgment is involved, there are many cases where binary evaluation of (0, 1) alone cannot provide sufficient explanations, so we actively incorporate ambiguous states in the middle (0, 1). The theory of value evaluation has been studied.Fuzzy clustering is the introduction of the concept of [0,1] multi-value evaluation into clustering.

Now, the n classification objects (we will call them individuals) are expressed as E
= (ol, 02 ・−, o I, −・on
1 or [1, 2,...l II..., n)
It is expressed as (1). In addition, the p-variate observation vector of the first individual is expressed as X i ” (X il , X i2
+ ..., X++, ..., XIP), and the entire multivariate data matrix is expressed as X= (XI,
・”, = [ζh ζ2...., ζ3....,
ζ. )(3).

For 0 divisions as in equation (3), the degree to which each individual belongs to each cluster is expressed by the following matrix.

U=(uj+) (j=1.2.... c; i=1.2. ... n) (4) here, Uj+e-(o, 1].

Σu jI = 1.

In other words, u ii is a membership function, which indicates the degree to which individual i belongs to cluster S1. At this time, consider the optimization of the following function.

Jp (U, V) =Σ,Σ(u++)'llx+
−v+112(1≦p<CX))1−I J−1 (5) Here, for l<p<■, uI+: Vi= :E (II XI Vj II ”/ If x+−
vkII ”)”−”k−+ Σ(uji)pX+ (6) (7) Σ(u++)′, and ■ is the average vector of the cluster S.

Now, if we consider that p=L ujig-(o, 11), it becomes the so-called ordinary means method, and Jt is the sum of squares standard itself.For p=l, 2, minimize J in equation (5). The fact that the weighting coefficients for

The algorithm that extends this to general p is summarized as follows.

Country Set the number of clusters C1 exponent p. The initial condition U(0) of U is given appropriately, and the number of iterations L=0.

Figure (7) shows the average vector vI''(J''
+ 2+ times U(L) is multiplied by equation (6).

By giving an appropriate convergence judgment value ε, l U(L+ll
[If J(L)≦ε, the calculation ends. Otherwise, L
=L+1 and return to the figure.

When the fuzzy k-m e a n s method is applied to image data, it has the disadvantage that data sets with similar patterns cannot be classified well, and isolated data (i.e., clusters with a small number of data) are many)
It has the disadvantage of being included in a cluster. In order to improve this point, formula (5) is used as a criterion (l≦p<oo).
(8) gi(-[0,1] However, if gie-(0,1) s+ is given, gi
If you do not give 81, give some vectors (S+) that are representative of the pattern (cluster) you want to classify in advance. This can be considered a type of pattern matching. This method is based on Pedry.
Compared to the cz method, it is only necessary to provide Si with a maximum of C clusters, and the number of data to be provided can be reduced.

Also, gi is a fuzzy −mea regarding cluster Sl.
This is a parameter that represents the ratio between clustering by the ns method and clustering by a type of mumming when 81 is given. If g + = O, fuzzy −me
This is the same as the ans method, and when gl=1, clustering is performed based on si and the distance to each data X1. gj=
In the case of 172, both clusterings are weighted equally.

The degree to which individual i belongs to a cluster can be determined from the finally obtained element uiii of U. normal-means
If the modulus is the cluster set r = (s lT S
21...Sl,...,Sc], a certain individual i
Although it is only necessary to know whether Sj belongs to Sj (u, I=1) or not (+g=O), according to this method, it is possible to know the degree of belonging to each cluster.

In this simulation, p=1 in equation (8)
．． 3 c=8 n=87 gl=0.9 are used.

FIG. 21 schematically shows the principle of the additive fuzzy data clustering method. Although two parameters (two dimensions) are used for illustration, there are actually 18 parameters (18 dimensions).

In additive fuzzy data clustering, features obtained by processing images related to multiple leads are simultaneously processed. As a result, an effect similar to that obtained by simultaneously performing clustering of similar patterns and matching with the reference pattern can be obtained. In addition, in conventional clustering methods (hard clustering), certain input data can only be included in one cluster, but in fuzzy clustering, it is possible to determine the degree to which input data is included in multiple clusters. can be expressed. Therefore, even if it is not possible to make an accurate judgment using clustering alone, it is possible to leave the ambiguity and make a judgment later in conjunction with other information.

In Fig. 21, a, b, and c are the standard patterns of normal (lead part), floating, and solder ball, respectively;
+ is the feature amount obtained from the input image data.

On the other hand, A, B, and C each show cluster results in conventional clustering. That is, feature amount 2
11.212 belongs to cluster B called 'floating', and 2
13 does not belong to any cluster, 214 belongs to cluster C called “solder ball”, and 215 belongs to “normal”
It belongs to cluster A. In this way, in conventional clustering, it is uniquely determined whether a certain feature belongs to any cluster or not to any cluster. On the other hand, according to the fuzzy clustering of the present invention, for example, 211 is A,
Considering the degree to which it belongs to C, leaving ambiguity (
By making a judgment together with other information,
Inspection accuracy can be improved.

Regarding the feature quantities (F+ to Fa) related to the position, the inverse truth limitation method calculation unit 113 applies the inverse truth limitation method to calculate the "second evidence" regarding the above-mentioned items 1 to 2. That is, as shown in FIG. 22(a), position information is expressed as a fuzzy set, and matching with the fuzzy set of the reference pattern is performed.

We used the inverse truth value limitation method using numerical truth values to perform this matching. Here, this inverse truth value restriction method will be briefly described. Now, let A and B be fuzzy sets, and
When the numerical truth value of the proposition "is A" is t, truth value restriction is to find the following.

(“X is A” is t) = (X i
s B) Here, when A and B are given, the inverse truth restriction method estimates t. According to the above proposal, t is expressed by the following equation.

t= (Sup (AnB) 10Inf (AUqB)
l/2 where Sup is the maximum value of the membership function,
Inf means the minimum value. Also, both A and B are n
o r m a l.

Convex. In this method, t has a linguistic meaning as shown in FIG. 22(b).

FIG. 23 shows a specific calculation example.

The result t of the inverse truth value restriction method includes tx (8251 in Fig. 25) in the X direction on the two-dimensional plane and ty in the Y direction.
(5252 in Figure 25), the final result is the product operation, t=min (tx, ty)
(9) is used (S254).

The reason why the inverse truth value restriction method is used for the positional feature is as follows.

In Figure 24, the lead is in the area ■, and the solder is in the area ■
The device is configured to enter the In this case, area I
Anything that gets in there will be defects such as bridges and solder balls.

Since these defects have arbitrary positions, it is difficult to classify them using a clustering method. That is, it is normal that there are no bridges, solder balls, etc., and in most cases they are not detected, but when they occur, it is uncertain where they will occur. Furthermore, since there is some misalignment in the leads and solder, a method that can tolerate misalignment is desirable. Therefore, in this method, the inverse truth limit method is used for position matching instead of the additional data fuzzy clustering.

(Step 9) Finally, use the results of the additional data fuzzy clustering and the results of the inverse truth restriction method as independent basic probabilities.
Combine using the ter combination rule (Fig. 25 5255
).

The calculation formula is Hail to you.

Here, ml(Alt), (i=1.2.-8) is the result of additional data fuzzy clustering regarding the i-th reference pattern, and m2(Az+), (j=1.2.・, 8) is j
Results of the inverse truth restriction method for the th reference pattern.

m (Ait) (k=1.2.-, 8) is the combined result.

Also, the numerator means assigning the product of each basic probability to the intersection set Ak of An and A2i, and the denominator means that in the case of a combination of contradictory inferences, the intersection set of Alt and A2+ may become an empty set. , these are excluded and normalized. Combining two or more basic probabilities, if they are obtained from independent evidence, is achieved by sequentially applying equation (10).

After performing Dempster join for the first region, the inverse truth restriction method and additional data fuzzy clustering are repeated for all regions per bin (S2
56). FIG. 26 shows an example of the processing results for one screen (l bin). There are 32 regions in this, and each region has Dempst
The result of combining er is obtained.

(Step 10) The final evaluation is output from the determination result output unit 117 using the maximum result in all regions per 1 bin. For example, for float, the result for region 1.2.3 is 0.13.
0.634. Since it is 0.001, the maximum value (7)
The result is 0.634=63.4%. This result shows that the probability of floating is 63.4%, and the probability of floating slightly is 30.4%.
Evaluate as %.

The above process is repeated for all pins (525
8) Finally, a judgment is made as to whether the soldering of the board is good or bad.

The final judgment will be made as follows.

First, regarding the evaluation of each pin, the maximum probability of the six defective items of the above evaluation results: floating, slightly floating, bridge, solder pole, shortage (lead part), and shortage (solder part) is 60%. In the above cases, the pin is evaluated as defective.

Next, if at least one pin out of all the pins is determined to be defective, the board is determined to be defective.

If the board is determined to be defective, it may be removed from the line by sorting means, or a warning may be issued by a lamp or buzzer.

The final data handling is not limited to the above cases; for example, basically normal (lead part) and normal (solder part) data are prioritized for evaluation, and even if there is one defective item, 60%
In the above cases, the product may be treated as defective.

[Effects of Example 1] Conventional (binary) clustering (k-means method)
In this case, it is only necessary to know whether something belongs to a certain cluster set or not, and an ambiguous degree of membership is not allowed, so even data in an intermediate state must be forced to belong to one of the cluster sets. As a result, misunderstandings occurred and flexible evaluation was not possible.

On the other hand, in this embodiment, the following effects are obtained by using fuzzy clustering, an inverse truth restriction method, and a combination rule of D e m p st er to integrate them. be able to.

■ False judgments are reduced.

That is, compared to the case of performing hard clustering, the fuzzy clustering according to this embodiment significantly improves the determination accuracy.

Furthermore, the output of the inverse truth restriction method and the output of the additional data fuzzy clustering are combined using Dempster's combination rule to obtain higher confidence than either alone.

■ Flexible evaluation becomes possible.

In hard clustering, because of the evaluation of [0, 1],
For example, I only know if there is a solder shortage or not, but
With fuzzy processing, it is possible to determine the degree of solder shortage, which allows flexibility in subsequent processing.

O Ambiguity can be set freely.

The ambiguity of clustering can be set by changing the value of p in equation (8). The degree of ambiguity can be increased by increasing p. Also,
To perform clustering, initial conditions and 0 must first be provided, but the clustering results will vary depending on how the initial conditions are provided. This tendency is particularly strong in the case of hard clustering. However, in the case of fuzzy clustering, results are obtained that are completely unaffected by differences in initial conditions by first increasing p to perform vague classification, then decreasing p and classifying again.

27 is a block diagram showing the configuration of a second embodiment of the present invention. The basic configuration is the same as that of the first embodiment, but in this embodiment, there is no means for moving and rotating the CCD camera 101, and frame memories 105 to 10 are not provided.
7 stores image data obtained by reading the entire IC, and by controlling read addresses from the frame memories 105 to 107 by the cPUI 19, determination can be made for each pin.

According to this embodiment, a CCD camera or a means for moving and rotating a table on which a substrate is placed is unnecessary, and the configuration of the entire apparatus can be simplified.

In Embodiment 1, by moving and rotating the CCD camera, all ICs on one board can be
I decided to do a long image of the lead, for example, in Figure 3 (
Instead of using the table 301 on which the substrate 302 is placed as an XY table to be moved and rotated by a motor in a), other evaluation means such as fuzzy inference may be used.

In addition, D e m p st e is used to combine the two evaluation methods (fuzzy clustering and inverse truth method) mentioned above.
Instead of the r combination rule, other combination methods may be used, such as weighting the two evaluation means by taking an average, maximum value, or minimum value.

Furthermore, the feature quantities are not limited to position information, shape information, and brightness information; it is of course possible to extract other feature quantities such as color information (color layer, saturation, etc.) and dot arrangement information. .

In addition, the soldering in the above-described embodiments is not limited to inspection, and the algorithm of the present invention can be used, for example, in image pattern matching,
It can also be applied to all other evaluations depending on image features such as image region separation.

〔Effect of the invention〕

As described above, according to the present invention, the accuracy of board mounting inspection can be significantly improved.

[Brief explanation of drawings]

FIG. 1 is an overall block diagram of the board mounting inspection apparatus according to the first embodiment of the present invention. FIG. 2 is a flowchart showing the inspection algorithm of the first embodiment of the present invention. The figures are: Figure 5, Figure 6, Figure 7, Figure 8, Figure 9, Figure 10, Figure 11, Figure 12, Figure 13, Figure 14. The figures are: Figure 15 is a diagram showing, Figure 16 is a diagram, Figure 17 is a diagram showing, Figure 18 is a diagram showing an example, external view of inspection equipment, enlarged view of IC chip, noise Flowchart of removal, Diagram showing windows, Flowchart of discriminant analysis method, Diagram showing binarization method, Diagram showing region extraction examples and numbering, Flowchart of region extraction, Diagram showing features to be extracted, Binary image Diagram showing the flow of data, Diagram showing the flow of multivalued image data, Diagram showing the circumscribed rectangle and center of gravity, Example of a binary image of normal soldering, Example of a binary image in the case of floating. Figure 19 shows an example of a binary image with a bridge. Figure 20 shows an example of a binary image with a solder pole. Figure 20 shows an example of a binary image with a solder pole. FIG. 21 is a diagram showing the principle of fuzzy clustering. FIG. 22 is a diagram explaining the inverse truth limitation method. FIG. 23 is a diagram showing the inverse truth limitation method. A diagram showing a specific example of application, FIG. 24 is a diagram showing extracted regions, and FIG. 25 is a diagram showing a specific example of application.
FIG. 26 is a diagram showing the result of combining empster, FIG. 27 is a block diagram showing the configuration of a board mounting inspection apparatus according to the second embodiment of the present invention. It is. 113... Inverse truth limit method calculation unit 114... Fuzzy clustering calculation unit 115 ・
-De m p st er connection part Fig. 5 Volume 1 To the removal flow - Fig. 73 Shiobond ゐ4 TE” 9 ↓ F + Zinc Clustering file To mushroom part XL Go to XF? Seiden Lae (Ki I included Fig. 78 Bridge ゛One person is missing Fig. 79 1t and Bauj L ×q R Yt, + er D I-word reading of

Claims (4)

[Claims] (1) means for extracting a plurality of feature quantities using input image data; using the plurality of feature quantities extracted by the extraction means;
1. A board mounting inspection apparatus comprising: means for inspecting the mounting state of a board using a plurality of methods based on different principles. (2) The board mounting inspection apparatus according to claim 1, wherein the feature amount includes at least one of position information, shape information, and brightness information. (3) The board mounting inspection apparatus according to claim 1 or 2, wherein the plurality of methods include at least one of an inverse truth limit method and fuzzy clustering. (4) An inverse truth limit method is used for the position information, a fuzzy clustering method is used for the shape information or the brightness information, and the method further comprises means for combining the results of both methods. The board mounting inspection device according to item 1, 2, or 3.