JPH0666528A - Visual inspecting method and apparatus - Google Patents

Abstract

PURPOSE:To make possible the accurate inspection of an external appearance of a soldered state after packaging of a circuit board by a method wherein an image of a reflected light from the surface of an object of inspection is picked up from just above and from obliquely above and the image distribution data on the reflected light are subjected to an arithmetic processing for each pixel. CONSTITUTION:An object (a soldered surface) 3 of inspection is illuminated, with the angle varied, by illuminating devices 11, 13, 15 and 17 switched over and an image of a reflected light being generated from the object 3 and peculiar to each angle is picked up by an image pickup camera 21 located just above and by image pickup cameras 22 and 23 located obliquely above. Image information at each angle of inclination is made data and they are inputted to image memories 5 and 5' sequentially. Image computation parts 6 and 6' select the image of the maximum image illuminance out of the image data corresponding to each illumination, while shape data parts 7 and 7' form number codes of the image meaning angles of reflecting faces of the image, as shape inclination angle data. A recognition determining part 8 computes the magnitude of the shape, height, length, area, etc., of a soldered state on the basis of the coded data and determines exactly whether soldering is formed in a desired state or not.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a soldering appearance inspection apparatus, and more particularly to an apparatus for inspecting the appearance appearance of soldering after mounting an electronic component on a substrate as an object to be inspected.

[0002]

2. Description of the Related Art As a conventional apparatus of this type, as described in, for example, Japanese Patent Laid-Open No. 60-154143, a soldering portion which is an object to be inspected is irradiated with annular lamps having different angles. With respect to the soldering surface, a change in reflected light obtained each time is converted into an electric signal by a light receiving element, a video camera or the like, and image information of a plurality of inclined surfaces of the soldering surface is obtained. Then, a judgment standard is created based on the various image information, and by comparison with the judgment standard value, the solder state is classified into, for example, good, insufficient, excessive, none, lead deviation, etc., and the judgment is made.

[0003]

However, in the above-mentioned prior art, it cannot be said that sufficient consideration is given to the recognition of classification determination of the soldering state.

Further, in recent years, the electronic components mounted on a mounting board have become more dense in density and the lead pitch thereof has become higher with the miniaturization and higher integration. Due to the difference in product type, the solder surface condition has become different.

Therefore, as a matter of course, the reference level for judging whether the soldering is good or bad is slightly changed. In particular, it is extremely important to be able to highly grasp and control the quality of the shape and condition of leads and soldering of electronic components. That is, the shape state of soldering is analyzed more accurately, this is accurately classified and grasped, and then the recognition judgment is made.
In order to improve the recognition rate, that is, the failure indication rate, and improve the false alarm rate for determining non-defective products as defective, it becomes necessary to perform identification optimization.

The present invention has been made in view of the above circumstances, and its purpose is to determine the shape of the object to be inspected in a soldered state, the direction of the object to be inspected in the plane direction. An object of the present invention is to provide a soldering condition inspection device capable of accurately determining the shape, flatness, vertical discontinuity, and the like of these, by an optimum method.

[0007]

SOLUTION: A lighting means arranged above an object to be inspected irradiates light to the object to be inspected at different angles, and the object to be inspected by light irradiation of this illumination. The reflected light from the surface is captured from directly above and diagonally above and converted into an electrical signal, and the image distribution data of the reflected light is arithmetically processed from this electrical signal and organized as shape data. The shape is obtained, the features are extracted together, and the state of the inspection object is recognized and determined.

[0008]

Function: By illuminating a certain position of the object to be inspected at different angles, the reflected light peculiar to the angle is obtained. This reflected light is imaged from above and obliquely above and converted into an electrical signal. The image distribution data of the reflected light, which is obtained in the above manner, from the respective illumination angles to the upper side and the diagonally upper side is arithmetically processed for each pixel to obtain detailed image information. Based on this result, the shape inclination angle data, the shape height data, the volume capacity data, etc. are obtained, and the features are extracted together to recognize and determine the state of the inspection object.

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT An embodiment of a soldering state inspection according to the present invention will be described below with reference to the drawings. First, the outline of the operation of the embodiment will be described. Illumination is performed at different angles with respect to the soldering surface, which is the non-inspection object. Reflected light peculiar to each angle is generated from this soldering surface. The reflected light is imaged from above and obliquely above to obtain image information of each inclination angle of the soldering surface, and then the detailed image information of the soldering state is converted into data. These data are divided into shape inclination angle data of the row direction component of the soldered portion, shape height data, volume capacity data, shape inclination angle data of the column direction component parallel to the lead tip, and further shape height data. Has been. Here, in particular, the image pickup unit (for example, a video camera) located just above the upper surface correctly measures the planar shape and flatness. However, the inclination angle of 45 ° or more cannot theoretically be measured, and it has a drawback that it is difficult to grasp the discontinuous shape in the vertical direction. On the other hand, the image pickup means obliquely above can measure an inclination angle of 45 ° or more. Further, it has a feature that it is easy to grasp a discontinuous shape in the vertical direction. However, it is difficult to measure the planar shape and flatness correctly. Therefore, both of these are used together as needed to determine the shape recognition of the right place. As the identification items, first, for size comparison, comparison is made by calculating solder height, solder cross-sectional area, solder length, solder area, solder amount, solder inclination angle, etc. Angle and steepness, comparison of numerical array shape in row direction component and height direction component of height data, presence / absence of relatively flat part in the center of soldering and its size, shape inclination angle,
Data is created by comparing numerical symmetry, comparison of symmetry deviation amounts, comparison of equiangular line patterns, etc. in the entire row and column direction components of height data. These values correspond to subtle changes in soldering conditions and changes in soldering, and judgment classification items for each solder state, such as (1) good soldering, (2) insufficient soldering, (3) wetting failure, (4)
It is categorized into excess, (5) no solder, (6) lead misalignment, (7) lead floating, (8) lead not attached (9) missing item, etc. to make the optimum determination, especially the soldered part Judgment of the joining state between the solder state and the lead state is performed. According to this method, the determination content can be enhanced, the soldering state inspection and measurement level can be made accurate, and the inspection and measurement efficiency can be greatly improved. Next, details of the embodiment of the present invention will be described.

FIG. 1 is a block diagram showing in detail an embodiment of the appearance inspection apparatus according to the present invention. FIG. 2 is a block diagram showing an embodiment in which the visual inspection devices according to the present invention are arranged in the order of functional blocks. In the figure, 4 is a lighting switching unit, 1
0 is an illumination switching unit, 8 is a recognition determination unit (CPU), 60 is a bus line, 61 is an I / O, 62 is an operation unit, 63 is an image interface, 64 is a monitor, 65 is an external memory interface, 66 is an FDD, Reference numeral 67 is a HDD, 68 is a data display device, 69 is a mechanism control unit, and other symbols will be sequentially described below.

In FIG. 1, above the inspection object 3 of the mounting board 2 mounted on the mechanism section 1 which moves in the XY directions, the illuminating section 11 and the illuminating section are sequentially arranged from above the mounting board 2 side. 13, the illumination unit 15, and the illumination unit 17 are arranged in four stages. Each of the illuminating parts 11, 13, 15, and 17 is composed of a ring arranged concentrically, and its diameter is gradually increased as it is arranged on the mounting board 2 side.

The illuminating units 11, 13, 15, 17
In this embodiment, the mounting substrate 2 is illuminated by being sequentially switched by means of the illumination sequential switching unit 4.

From above the illuminating unit 1, there is one imaging camera 21 of the photographic unit on the central axis of the illuminating unit and directly above the inspection object 3, and the imaging cameras 22 and 2 from diagonally above.
Four of 3, 24 and 25 (24 and 25 are not shown) are symmetrically arranged in four directions. This imaging camera 21, 2
Any one of 2, 23, 24, 25 is the illumination unit 11,
It is possible to capture an image of the reflected light of the inspection object 3 illuminated by sequentially switching 13, 15, and 17.

The image pickup cameras 21, 22, 23, 2
The output signal of either 4 or 25 is output from the imaging camera switching device 10
Is input to the image memory units 5 and 5 '. 31, 33, 35 of the image memory unit 5 of the RAM,
37 stores images corresponding to the illumination units 11, 13, 15 and 17, respectively, and 31 ', 33' of the image memory unit 5 ',
35 'and 37' are illumination units 11, 13, 15, and 1, respectively.
The image is stored corresponding to 7.

In the image memory units 5 and 5 ′, the images of the inspection object 3 illuminated by sequentially switching the illumination units 11, 13, 15, and 17 are picked up, and the captured images are respectively captured by the imaging camera 21. The image signal is sequentially input to the image memory 5, and the image signal of any one of the image pickup cameras 22, 23, 24 and 25 is sequentially input to the image memory 5 '.

Further, the outputs from the image memories 5 and 5'are input to the image calculation processing units 6 and 6'for each pixel.

In the image calculation processing units 6 and 6 ', the image pickup data corresponding to the illumination from the illumination units 11, 13, 15 and 17 are compared with each other in the magnitude of illuminance for each image pickup pixel. Then, from the data obtained from this result, the captured image with the highest image illuminance level is classified and selected.

The selected data is the shape data section 7,
It is input to 7 '. In the shape data sections 7 and 7 ', the image number code indicating the angle of the reflection surface of the selected picked-up image is organized as shape inclination angle data.

The recognition determination section 8 is based on the coded data from the shape data sections 7 and 7 ', and the shape, height, cross-sectional area, length, area and capacity of the soldered state. The size of the tilt angle, the flat part in the center of the solder, etc. is calculated and calculated.

Furthermore, the recognition determining section 8 can accurately determine whether or not the soldering section formed on the surface of the inspection object 3 of the mounting board 2 is formed in a desired state. Has become.

3 and 4 are sectional views showing details of the soldering portion 51 of the mounting board 2. As shown in FIG. FIG. 3 shows reflected light incident on the image pickup camera 21 directly above,
FIG. 4 shows reflected light incident on any of the obliquely upper imaging cameras 22, 23, 24, and 25. The inspection object 3 is also an object of shape state determination. In the figure, a copper foil pattern 52 is formed on the main surface of the mounting substrate 2, and a lead portion 53 is formed so as to be connected to the copper foil pattern 52.
(Lead portion of electronic component) is fixed via the soldering portion 51. In the figure, the data number of the code of the shape inclination angle and the arrow indicate the direction of the reflected light.

In the mounting board 2 having such a structure, after the light from the illuminating section 11 is reflected on the surface of the soldering section 51, the light from the illuminating section 13 is directed in the direction of the data number of the code in the figure. The light from the illumination unit 15 is soldered in the direction of the data number of the code in the figure after being reflected by the surface 51, and the light from the illumination unit 17 is soldered in the direction of the data number of the code in the figure after being reflected by the surface of the soldering unit 51. After being reflected by the surface of the attachment portion 51, the light beam advances in the direction of the data number of the code in the figure and is incident on any of the image pickup cameras 21, 22, 23, 24 and 25.

In FIGS. 3 and 4, the irradiation range to the surface of the soldering portion 51 is 0 ° to 90 ° in the first quadrant and 0 ° to 90 ° in the second quadrant on the opposite side.

As described above, the image data arithmetic processing units 6 and 6'relatively select the target image for each image data corresponding to each illumination, and the shape data units 7 and 7'select the target image. Encode and organize selected data. In the shape data sections 7 and 7 ', data is organized as in a plan view showing a distribution state of data in a portion having high illuminance. That is,
It is a detailed data state diagram showing from the data number of the code of the shape inclination angle from the soldering upper surface. Here, the data of the shape inclination angle code is arranged, stored, recorded, displayed, and output.

Here, the data number of the code,
For how to create ,,,,,,
This will be described below.

First, in order to obtain an accurate angle, analog data distribution of illuminance can be obtained by obtaining data on a known hard sphere similar to the reflectance of the soldering portion 21.
At this time, for example, the illuminance is taken with 256 gradations, and the respective illuminations are spaced at substantially equal angles. This is used as the data of the reflection code on the surface of the soldering portion 51 for illuminating each stage, the data number by the illuminating section 11, the data number by the illuminating section 13, the data number by the illuminating section 15, and the illuminating section 17.
Numbering is done in correspondence with the data number according to.

Further, since the surface of the soldering portion 51 has a continuous curvature, the data number and the illumination portion between the illumination portions 11 and 13 at each stage are interpolated by the interpolation method by the internal search of the intermediate analog value. Data numbers between 13 and the illuminating unit 15, data numbers between the illuminating unit 15 and the illuminating unit 17, data numbers other than the illuminating unit 17 and data numbers less than the illuminating unit 11, and so on. Like

As a concrete method of such interpolation, for example, in the illuminance level of 100 gradations or less, the overlapping portion of the data number illuminance area and the data number illuminance area is defined as the data number, and Further, it is easy to set the data number, the data number, and the direction of the data number and the data number.

Therefore, in this case, the solder surface observable range can be classified into 9 levels of angles by the substrate parts of the solder surface.

FIG. 5 is a plan view of the mounting board 2 on which the soldering portion 51 is formed by the image pickup camera 21 located immediately above, and shows data numbers and equiangular lines described later.
When the illumination units 11, 13, 15, 17 having four steps are sequentially switched, the image calculation processing unit 6 causes the image calculation processing unit 6 to capture a captured image of the reflected light from the soldering unit 51. The area of the portion having a relatively high reflectance from the surface of the attachment portion 51 is defined as the illumination portions 11, 13, 1 described above.
It is explanatory drawing which shows the state made suitable corresponding to 5 and 17. The rectangular frame shows a part of the range to be inspected after being imaged by the imaging camera 21, and in FIG. 5, the area to which the data number is attached is relatively large in the reflected light from the illumination unit 11. A portion having a high illuminance, a region having a data number, is a portion having a relatively high illuminance among the reflected light from the illumination unit 13, and a region having a data number is a portion having a relatively high intensity among the reflected light from the illumination unit 15. The portion with high illuminance and the area with the data number indicate the portion with relatively high illuminance in the reflected light from the illumination unit 17. Also, the data number,
Areas marked with ,,, are calculated and set by the above-described interpolation method.

Further, FIG. 6 shows an obliquely upward image pickup camera 22,
In the plan view of the mounting board 2 on which the soldering portions 51 are formed by 23, 24, and 25, equiangular lines to be described later are written in addition to the data numbers. Each lighting unit 11 with four steps,
The imaging cameras 22 and 2 that capture the reflected light from the soldering portion 51 when 13, 15, and 17 are sequentially switched.
The captured image from any one of 3, 24, and 25 is processed by the image calculation processing unit 6 ′ so that the area of the portion having a relatively high reflectance from the surface of the soldering unit 51 is set to the illumination units 11, 1 respectively.
It is explanatory drawing which shows the state made suitable corresponding to 3,15,17. The rectangular frames are the imaging cameras 22, 23, 24,
FIG. 6 shows a range to be inspected after being photographed in any one of 25, and in FIG. 6, a region to which a data number is attached is a portion of the reflected light from the illumination unit 11 having a relatively high illuminance, The numbered area is a portion of the reflected light from the illumination unit 13 having a relatively high illuminance, and the area numbered is a portion of the reflected light from the illumination unit 15 having a relatively high illuminance. The numbered area indicates a portion of the reflected light from the illumination unit 17 having a relatively high illuminance. The areas to which the data numbers are attached are calculated and set by the above-described interpolation method.

The ends of the lead portion 53 in FIGS.
The position is set in advance by the image pickup of the upper image pickup camera 21.

The results shown in FIGS. 5 and 6 are as follows.
The shape data corresponding to the pixels in the detailed data state diagram of the shape information (after drawing as needed when there is a lot of redundancy) is the row data n × column data m = nm (vertical × horizontal). It is organized and stored in parts 7, 7 '.

With such a distribution (a portion of the reflected light where the illuminance is relatively high), a change in the inclination angle of the surface of the soldering portion 51 can be recognized according to the distribution state. That is, when the angle of the solder surface with respect to the vertical line of the incident illumination section optical axis is α and the angle of the solder surface with respect to the vertical line of the camera optical axis is β, the inclination of the portion (area) where the intensity of the reflected light is high This is because there is a relationship that the angle θ = α + (β−α) / 2.

For this reason, the illumination units 11, 13, 15,
That is, the inclination angle of the portion in the region where the reflected light from any one of the illumination units is relatively strong is found.

In the present embodiment, the above-mentioned code is used as data, and the height of each portion on the soldering surface is calculated.

FIG. 7 is a sectional view of a soldering portion for explaining a method for obtaining the shape height data from the shape inclination angle data of the solder shape information data by the camera 23 directly above, and FIG. Cameras 22, 23, 2
It is the figure which showed the soldering part side surface which shows the reflected light which injects into either 4 or 25. A method for obtaining the height of each portion of the soldering surface will be described based on these drawings.

In the shape data portions 7 and 7'of FIGS. 1 and 2, as can be seen from the shape inclination angle data of the solder shape code, corresponding to each pixel, the following relational expression Height ≈ coefficient x pixel length x tan (shape tilt angle) is obtained.

Here, the coefficient is a correction coefficient of the actually measured height value and the numerical value obtained by this method.

From the above relational expression, the height for each pixel, h
1, h2, h3 ... hn will be obtained.

Further, as cumulative shape height data, H1 = h1, H2 = H1 + h2, H3 = H2 + h3, ...
.., HN = HM + hn.

Further, as a result, the numerical value collated with the actually measured value is adjusted by the correction coefficient and then used as the value of the height of the data to be used.

At this time, the obtained numerical values can be divided into relative numerical values as parameters for feature extraction to obtain data, and the array of the data can be utilized.

Thus, by obtaining the height corresponding to each pixel, it becomes possible to calculate the sectional area of the solder on a certain side surface.

That is, the length and width of each pixel are obtained from the image pickup range and resolution of the image pickup camera. From this, the cross-sectional area for the pixel can be obtained by calculating the product of the height and the length or width of each pixel described above. For example, when it is desired to obtain the cross-sectional area of the solder on a certain side surface, the cross-sectional areas of the pixels may be summed over the area.

That is, the solder step area ≈ coefficient × solder shape height × pixel length (or width) S1 ≈ for each row
H1 × L, S2≈H2 × L, S3≈H3 × L, ..., S
N≈HN × L The M-th solder cross-sectional area is SM≈ΣSN≈ΣSN × L.

Further, by obtaining the height corresponding to each pixel, the volume of solder in a certain row can be calculated.

That is, the volume of the pixel can be obtained by calculating the product of the height and the area of each pixel. Further, when it is desired to obtain the total amount of solder, the volumes for the pixels may be summed over the entire area.

That is, the amount of solder ≈ coefficient × the height of solder shape × the area of the pixel V1 ≈ H1 x s, V2 ≈ H2 x s, V3 ≈ H for each row
3 × s, ..., VN≈HN × s The amount of solder in the Mth row is VM≈ΣVN≈ΣHN × s The total amount of solder is the sum of each row in the column direction V≈ΣV
It is M.

Further, as the area occupied by the solder shape at the height or angle at a certain level or higher in the entire soldering area, it is easy to obtain the area = number of pixels × area of pixels.

Further, as the entire soldering area, the steepness of the soldering state of height or angle above a certain level, that is, as the entire inclination angle, inclination angle = cumulative shape height / total length of row Ask for.

Further, as the shape of the steepness of the soldering state, in the explanatory views showing the side views of the soldering portion in FIGS. 7 and 8, whether the side surface of the M row is a straight line or a convex line, Most of the shape inclination angle data (N) =, assuming that the difference between each pixel in the Nth column and the Mth column of the shape inclination angle data is A = (N)-(M). If (M), A = 0 and straight line change (N)> (M) If A> 0, concave line change If steepness is large (N) <(M), A <0 and convex line Change Slowly or similarly, whether the shape of the side surface of the M row is a straight line, a convex line, or a concave line, the change difference for each pixel of the Nth column and the Mth column N is determined by the shape height data. , ΔA = hn-hm, most of the shape height data hn = hm, ΔA = 0
In the case of linear change hn> hm, ΔA> 0 is set. In the concave line change, steepness is large. In case of hn <hm, ΔA <0 is set and convex line change is calculated.

Furthermore, as the soldering state, in the height or angle at a certain level or higher, a region which can be regarded as relatively flat, for example, the data number of the shape inclination angle data region of the shape code, (or As the area of the portion occupied by the shape height data area at a certain level), area = number of pixels × area of pixels is obtained for feature extraction.

The recognition determination unit 8 compares each identification item obtained by each of the above-described calculations with a reference value to make a determination.

Next, as the judgment classification items, these values correspond to subtle changes in the soldering conditions and variations, and the judgment classification items for each solder state, for example, (1) Goodness of soldering, ( 2) Shortage, (3) Wetting failure, (4)
The classification N is set in advance in detail such as excess, (5) no solder, (6) lead misalignment, (7) lead floating, (8) lead not attached, and (9) missing item. With respect to each of these classifications, in the automatic classification of the soldering state, as the shape examples of the soldering state, in particular, here, the recognition determination of the soldering state of the soldered portion and the joining state of the lead state is performed. Here, as mentioned before, FIG. 5 shows an example of an isometric drawing of a non-defective product by the imaging camera 21 located directly above, and FIG. 6 shows imaging cameras 22, 23, 24 located obliquely above. Two
6 is an example of an isometric drawing of a non-defective product according to FIG.
Further, FIG. 7 shows an example of a side view of a non-defective product by the image pickup camera 21 directly above, and FIG. 8 shows an example of a side view of lead floating by the image pickup cameras 22, 23, 24, 25 diagonally above. is there. Further, FIG. 9 shows the diagonally upper imaging cameras 22 and 2.
It is an example of a side view with no lead attached, which can be detected by 3, 24, and 25. FIG. 10: is a figure which shows an example of the equiangular line of the example of a lead floating by the imaging cameras 22, 23, 24, and 25 of the diagonally upper direction. FIG. 11 is a diagram showing an example of equiangular lines when the leads are not attached by the imaging cameras 22, 23, 24, 25 diagonally above.

In the shape information data of the soldering state, shape data such as solder height, cross-sectional area, length, amount, real area, steepness, symmetry, central flatness (discontinuity) of special shape, etc. Is included. These are stacked from the shape of the solder surface.

Features can be extracted and classified by combining each identification item in the shape state with respect to each classification.

First, in the recognition determination unit 8, in order to determine the characteristics of the soldering state, the respective identification items of height, cross-sectional area, length, area, amount, inclination angle, steepness, and central flat area. The absolute value or relative value of, and further the shape etc. are created and classified.

From the above, in the shape comparison of soldering states, the judgment classification items are (1) solder height, cross-sectional area, length, area, quantity, reference value in inclination angle, large steepness (concave shape) If the characteristics of line change), no central flat area, and lead edge detection are extracted → Good in this case. (2) The solder height is very low, the cross-sectional area is very small, the length is very short, the area is very small, the amount is very small, the inclination angle is a little small, and the steepness is large ( Concave line change),
If the characteristics of the area without central flat area and the presence of lead edge detection are extracted → In this case, it is insufficient. (3) Solder height is very low, cross-sectional area is small, length is normal, area is normal, amount is small, tilt angle is very small, slow (convex line change), central flat If the characteristics of the part area is a little large and the lead end is detected,
In this case, insufficient wetting. (4) Solder height is very high, cross-sectional area is large, length is very long, area is very large, quantity is very large, slow (convex line change), central flat area is large If the characteristics of no lead end detection are further extracted → In this case, excessive solder. (5) If the characteristics of solder height, cross-sectional area, length, area, amount, inclination angle, steepness, and all values are not detected, and there is lead end detection, → No solder is used in this case. (6) Solder height is normal, cross-sectional area is normal, length is normal, area is very small, amount is small, inclination angle is normal value, steepness is large (concave line change), tip shape is If features such as asymmetric non-uniformity, no central flat area, and lead end detection are extracted → In this case, lead positions are misaligned. (7) The height, cross-sectional area, length, area, amount, and inclination angle of the solder are larger than the reference, slow (convex line change), no central flat area, and the solder enters from the lead end. If the characteristic of is extracted, in this case the lead floats. (8) The solder height is usually large, the cross-sectional area is large, the length is very long, the area is very large, the amount is very large, the matrix ratio is very large, the inclination angle is very small, If the characteristics are slow (convex line change), central flat area is rather large, matrix ratio is large, and solder gets in from the lead ends → In this case, no lead is attached. (9) The height of solder is usually large, the cross-sectional area is large, the length is very long, the area is very large, the amount is very large, the matrix ratio is very large, the inclination angle is very small, If the characteristics of slowness (convex line change), central flat area is rather large, matrix ratio is large, and lead end is not detected → In this case, it is out of stock.

Here, in particular, the phenomenon in which the flatness and flatness can be easily discriminated and judged by the image pickup camera 21 directly above is not only the position of the lead portion 53, but also the lead position is misaligned, no solder, lack of parts, insufficient solder. Poor wetting, good product, excess.

On the other hand, the diagonally upper image pickup cameras 22, 2
According to 3, 24 and 25, the phenomenon in which vertical discontinuity and steep inclination angle steepness can be easily discriminated and judged is lead floating, lead non-adhesion, solder shortage, wetting failure, non-defective product, and excess.

By combining the identification items by the method making full use of these characteristics, the identification determination suitable for each soldering state becomes possible.

Here, the description has been given as an example in which the identification item is determined and the determination classification item is determined by using the upper-right upper imaging camera 21 and the obliquely upper imaging cameras 22, 23, 24, and 25 at the same level together.

However, in the overhead camera 21 directly above, the identification and determination are shared mainly by utilizing the flatness characteristics such as lead position, lead position misalignment, no solder, and lack of parts. The upper imaging cameras 22, 23,
24 and 25 are identification judgments by utilizing the characteristics of vertical discontinuity and steepness (including 45 ° or more) of steepness, such as lead floating, lead not attached, lack, wetting, good product, and excess. It is also easy to share the configuration.

In order to shorten the appearance inspection time, one discrimination judgment is first performed, and when the corresponding judgment is accurately made, the next discrimination judgment is stopped. When it is not performed accurately, the other identification judgment is performed. Accordingly, it is easy to make a comprehensive identification determination from the viewpoint of the configuration.

The judgment criteria of the soldering state vary depending on the manufacturer and the process, and are set according to the quality criteria.

In addition, depending on the process, it may not be possible to clearly classify the items depending on the identification classification depending on the identification item, and it is natural to select the item having the identification effect.

Further, these identification items are given a clear and highly important priority order for identification, and a determination flow chart is provided.
It is a matter of course that the characteristics are extracted and can be classified and classified by the computer.

As described above, depending on the shape of the lead and the shape of the soldered state, an image is picked up by one of the image pickup cameras 21 and 22, 23, 24, 25, and this combination, that is, viewed from above. A more detailed and accurate determination can be performed by performing comprehensive identification determination based on the shape data and the shape data as seen from diagonally above.

In the present invention, in the recognition judgment, the embodiment has been described for the entire area of the soldering state, but the shape information data for several lines in the center direction of the soldering lead portion is mainly used. It is also possible to carry out the recognition judgment.

Further, in the present invention, in the recognition judgment, the embodiment has been described with respect to the entire area of the soldered state. However, for several lines in the central direction of the land portion of the copper foil pattern of the soldered portion. It is also possible to carry out the recognition determination mainly on the shape information data.

Further, in the present invention, the description has been made mainly by using the difference in the illumination angles of four steps, but the inclination angle direction is identified by the front and back illumination of the solder by halving the angle of the annular illumination around the solder. Further, by dividing into four equal parts, it is possible to improve the accuracy of identification in the inclination angle direction by illuminating the solder in the left-right direction, and to identify the influence of adjacent parts.

Further, it is needless to say that the present invention is not limited to the four-stage illumination, and the same effect can be obtained even when the number of stages is three or four or more.

It is needless to say that the lighting device may be moved in multiple stages as the one-stage lighting so that the same effect as that provided with the lighting devices in multiple stages may be obtained. In short, it suffices that the irradiation target can be irradiated by changing the incident angle in multiple stages.

Further, in this embodiment, the light emitted from the irradiation device is a single light. But,
Irradiation may be performed by changing the color for each stage.

The present invention replaces the means for sequentially switching the illumination by multi-stage and multiple illumination, and images the soldering surface to be inspected illuminated by using light sources of different hues from a plurality of angles,
It is also possible to obtain image information of each angle of this soldering surface. As a specific example, in the case of multiple stages, the respective stages,
In the case of multiple directions, the image distribution data can be extracted at a higher speed by emitting unique light corresponding to each angle of the illumination in each direction, that is, each irradiation angle of light. . For example, when the illuminating means has a plurality of hues such as red, green, and yellow, each irradiation angle can be specified by the difference or change in hue of reflected light, so that it is not necessary to switch or move the light source with time.

In the present invention, the appearance inspection method by the discrimination judgment about the soldering state of the electronic component of the lead of the one-piece flat package has been described, but the electronic component of the J-shaped lead is soldered. As for the state, the imaging camera 2 diagonally above
It is also very easy to take an image by any one of 2, 23, 24, and 25, and perform the visual inspection by the identification determination of the soldering state by the method already described.

Further, for the soldering area, clustering is performed on the pattern of the standard isometric diagram for each judgment classification item (for example, FIGS. 5 to 10), and the soldering state of the inspection object It is also possible to select a judgment classification item having a comparatively small difference by comparing the difference in pixel with the pattern No., and to judge and inspect.

As described above, it is possible to appropriately and accurately make a judgment in response to a slight change in the soldering condition, and the contents of the judgment can be easily enhanced. Check the measurement level accurately. The efficiency of measurement can be significantly improved.

[0080]

As described above, according to the present invention, in addition to the phenomenon in which the flatness and flatness can be easily discriminated and determined by the image pickup camera directly above, the diagonally upward image pickup camera can also provide discontinuity in the vertical direction and steep inclination. The sharpness of the angle is discriminated and judged, and in particular, lead floating, lead non-sticking, solder shortage, wetting failure, excess, etc. can be handled in response to subtle changes in soldering conditions, and the judgment can be made optimally and accurately. It can be easily expanded, and the soldering state inspection and measurement level can be made accurate.
The efficiency of inspection and measurement can be greatly improved.

[Brief description of drawings]

FIG. 1 is a simplified configuration diagram of main parts showing an embodiment of an appearance inspection device according to the present invention.

FIG. 2 is a functional block diagram showing an embodiment of the present invention.

FIG. 3 is a sectional view of an inspected portion according to the present invention.

FIG. 4 is a sectional view of an inspected portion according to the present invention.

FIG. 5 is a plan view showing knitting data and equiangular lines of a portion to be inspected according to the present invention.

FIG. 6 is a plan view showing knitting data and equiangular lines of a portion to be inspected according to the present invention.

FIG. 7 is a sectional view of an inspected portion according to the present invention.

FIG. 8 is a sectional view of an inspected portion according to the present invention.

FIG. 9 is a sectional view of an inspected portion according to the present invention.

FIG. 10 is a plan view showing knitting data and equiangular lines of a portion to be inspected according to the present invention.

FIG. 11 is a plan view showing knitting data and equiangular lines of a portion to be inspected according to the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Mechanism part 3 Inspection object 11, 13, 15, 17 Illumination device 21, 22, 23, 24, 25 Imaging camera 4 Illumination switching part 5, 5'Image memory part 6, 6'Image calculation processing part 7, 7 ' Shape data part 8 Recognition determination part 51 Soldering part 53 Lead part

Claims (6)

[Claims] 1. Light emitted from the surface of the inspection object by illuminating means arranged above the inspection object at different angles with respect to the inspection object. Is imaged from directly above and obliquely above, the image distribution data of the reflected light is arithmetically processed for each pixel from the output obtained from this imaging, organized as shape data, and the size and shape of the inspection object are obtained. A method for visually inspecting the state of an inspection object, characterized in that the characteristics of these are extracted together to recognize and determine the state of the inspection object. 2. An illuminating device which is arranged above the inspection object and irradiates the inspection object with light at different angles, and light reflected from the surface of the inspection object by the light irradiation of the illuminating section. An image capturing camera that captures the image from directly above and diagonally above, an image memory unit that stores the image distribution data output from the image capturing camera, an arithmetic processing unit that performs arithmetic processing for each pixel from the image distribution data, and the arithmetic processing unit. A shape data section that is organized as shape data based on the calculation result of
An appearance inspection apparatus for inspecting a condition of an inspection object, further comprising: a recognition determining unit that performs a process of calculating a size and a shape of the inspection object, extracts a feature of them, and determines a condition of the inspection object. 3. The illumination device according to claim 2, wherein the illumination device for irradiating light with different angles to the inspection object is composed of a plurality of illumination units sequentially provided in multiple stages above the inspection object. A visual inspection apparatus for inspecting an object under inspection. 4. The appearance inspection apparatus according to claim 3, wherein the respective stages of the plurality of illuminating units sequentially provided in multiple stages have mutually different hues. 5. The illumination device according to claim 2, wherein the illumination device that irradiates the inspection object with different angles emits light by sequentially switching in multiple stages and multiple directions. Appearance inspection device for the condition of the inspection target. 6. The invention according to claim 2, wherein the size and shape of the object to be inspected is calculated by creating shape inclination angle data, shape height data, volume capacity data, and sectional shape data, and further inspecting. An appearance inspection apparatus for an object to be inspected, characterized in that the height, length, area, capacity, inclination angle, cross-sectional area, steepness, and flatness of an object are obtained and the characteristics are extracted together.