JPH03225211A - Parts recognizing device - Google Patents

Abstract

PURPOSE:To precisely and rapidly recognize the shape and position of a part by forming a maximum value image constituted of picture elements having high brightness from two images obtained by successively turning on light sources for obtaining the images of side parts other than side parts to be recognized. CONSTITUTION:A printed substrate 1 arranged on a position to be photographed by a photoelectric converter 4 and a light source 3a is turned on to irradiate the substrate 1. The image on the irradiated face is picked up by the converter 4 and stored in an image memory 5a. The light source 3a irradiates parts 2 from the left and the shadow 8a of the part 2 is shown by slashes. The part 2 has four side parts 2a to 2d. Then, a light source 3a is turned off, a light source 3b is turned on so as to irradiate the part 2 from the side part and the image on the irradiated face is picked up by the converter 4 and stored in an image memory 5b. Then a light source 3c is turned on and the image on the irradiated face is picked up by the converter 4 and stored in an image memory 5c. Then, the light source 3c is turned off, a light source 3d is turned on so as to irradiate the part from the upper side and an image on the irradiated face is picked up by the converter 4 and stored in an image memory 5d.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention relates to a component recognition device, and in particular, extracts the shape of a component within the field of view of an imaging device by processing an image signal, and determines the location of the component. This relates to a device that recognizes.

[Prior Art] In order to inspect the mounting condition of electronic components mounted on a printed circuit board, a means as shown in FIG.
In Figure 0 proposed in Publication No. 206, (1) is a board such as a printed circuit board, (2) is a part to be tested having a side portion such as an electronic component, and (3a) and (3b) are electronic components (2). ) is a light source that irradiates light from two directions so that shadows can be formed on different sides of the light source (3a1. A photoelectric converter that converts into a signal, for example a television camera, (5a), (5bl) first and second image memories that store the image signal output by the photoelectric converter (4), (12) is an image to be processed. It is a processing device, and is equipped with a subtraction device U (Ill, operation W device ffi+63. determination device (7). A light source (3a1. An extension line connecting the electronic component (2) and the photoelectric converter (4) is provided so as to be inclined with respect to the direction in which the electronic component (2) is provided.

The conventional device is configured as described above, and detects the position, shape, etc. of a component by comparing the obtained image with a reference image. That is, first, install the part to be tested (2), turn on one light i (3a), and turn on the part to be tested (2).
irradiate. Next, an image of this light irradiation surface is taken with a television camera (4), converted into an electrical signal and stored in the first image memory (5a). The primary light source (3a) is turned off, and the other light source ( 3b) is turned on, and an image of the light irradiated surface is captured with a television camera (4). This is converted into an electrical signal and stored in the second image memory (5b). The difference between the output values of corresponding pixels of both image signals stored in these is calculated by a subtraction device (11) to obtain a difference image. From this difference image, calculate the position of part (2) by calculating JAiff (61),
The results are input to the judgment device (7) and compared and judged with those stored in the f-me.

[Problems to be Solved by the Invention] In the conventional component recognition device as described above, a reference image must be created in advance in order to recognize the position of the component from the difference image, but the component has different sizes, shapes, etc. It is virtually impossible to create a reference image that matches all target parts due to variations. Therefore, there is a problem that the reference image contains errors and parts cannot be recognized with high accuracy.

Furthermore, in the conventional apparatus, shadows for all sides of the target part had to be extracted. On the other hand, if there are other parts near the side of a part, there is mirror reflection in the background, or the height of the part is low, it may not be possible to extract a part of the shadow well, etc. There was a problem that it could not be recognized correctly.

This invention was made to solve the above-mentioned problems, and it is an object of the present invention to provide a component recognition device that can recognize the shape and position of a component at high speed and with good fi'f accuracy.

[Means for Solving the Problems] Part recognition according to the present invention is characterized by three or more light sources capable of forming shadows on different sides of a part whose sides are irradiated, and parts by irradiation with light sources. A photoelectric converter that converts the image of the side of the part into an electric signal using m images, an image memory that stores the image signal output by the photoelectric converter, and an image signal of the image of the side of the part other than the side to be recognized. A maximum value image calculation device that obtains a maximum value image signal by selecting two image signals, comparing the output values of corresponding pixels of the image signals, and leaving the one with higher luminance, the image signal of the side to be recognized and the maximum value image Difference image calculation device that calculates the difference in brightness from a signal to obtain a difference image; Shadow measurement that recognizes the side by measuring the length and width of a pair of opposing shadows on the side of the part from the difference image The system is equipped with a device and a determination unit A for recognizing the shape of a part from the shape of a set of shadows.

[Operation] In this invention, a maximum value image made up of pixels with high luminance is created from two images obtained by sequentially lighting up light sources that can obtain shadows of sides other than the side to be recognized. Accordingly, it is possible to obtain an image in which unevenness in image values due to unevenness on the surface of the component is eliminated. Furthermore, by taking the difference between this maximum value image and an image that is obliquely irradiated onto the side of the part to be recognized, the side of the part to be recognized can be measured with high accuracy. Furthermore, the shadow of the part is extracted from the difference image,
Since the length and width of the shadows of a pair of opposing sides are measured and the position of the part is determined from the shape of the shadow, there is no need to memorize a reference image in advance, and all sides of the part are The location, shape, or other geometric features of a part can be recognized without extracting the part.

[Example] An embodiment of the present invention will be described below with reference to FIG.

FIG. 1 is a block diagram showing the configuration of a component recognition device according to an embodiment of the present invention. This device is a mounting condition inspection device that recognizes components installed on printed circuit boards1.
In the figure, (1) is a printed circuit board, (2) is a test component having sides, which is mounted on the printed circuit board (11), and (3) is a light source that illuminates the test component (2). (3
a), (3b), (3c1.(3d) is the print substrate tM+1) at different angles, for example, the light source (
3a) and the light source (3C) are installed diagonally so as to be symmetrical with the component to be inspected (2) in between, and the light source (3b) is the light source (3C).
3a) and the light source (3C), respectively, in a horizontal direction of 90°, and at the same angle and distance from the component (2). Similarly, the light source (3d) is installed diagonally to be symmetrical to the light source (3b) with the part to be inspected (2) in between, and is located at 90° horizontally from the light source (3a) and light source (3C), respectively. They are placed in the same direction and at the same angle and distance from component (2). That is, four light sources (3a
l: (3b), (3c), (3dl is part (2)
are arranged so that shadows can be formed on different sides of the part (2), and when viewed from directly above part (2), they are 90 degrees apart from each other.
0@, and two sets of git products (2) are installed on opposite sides. (4) are light sources (3a), (3b
1. f3c), (A photoelectric converter that captures an image of the side of the component (2) by 3dl irradiation and converts it into an electrical signal, such as a television camera. (5) is a photoelectric converter (
a first image memory (5a) that stores the image signal output in step 4), for example, the image signal when the light source (3a) is irradiated;
A second image memory (5b) that stores the image signal when the light source (3b) is irradiated, a third image memory (5c) that stores the image signal when the light source (3c) is irradiated, and a third image memory (5c) that stores the image signal when the light source (3d) is irradiated. The fourth image memory (5d
), (6> is a calculation device that calculates the maximum value image and the difference image to recognize the side of part (2), and (7) is a determination illumination based on the shape signal calculated by calculation device (6). This is a determination device that outputs and displays the number.

The operation of the component recognition device configured as described above will be explained. First, the printed circuit board (1) is placed in a position where it can be imaged by the photoelectric converter (4), and the light source (3a) is turned on to illuminate the printed circuit board (1). An image of this irradiated surface is captured by a photoelectric converter (4) and stored in a first image memory (5a). The image at this time is shown in Figure 2 (a). This light source (3a) illuminates the component (2) from the left side, and the shadow (8a) of the component is shown by diagonal lines in the figure. . This part (2) has four sides (2a), (2b
) , (2c) , (2dl).

Next, the light source (3a) is turned off, the light source (3b) is illuminated from below toward the component (2), and an image of the irradiated surface is captured by the photoelectric converter (4), and the second image memory ( 5b). The image at this time is shown in Figure 2 (bl) with the zero-order light a (3bl turned off and the light source (3c) turned on from the right side toward the second part (2), and the photoelectric converter (which is the image of the irradiation surface) 4) and stored in the third image memory (5C).The image at this time is captured by the zero-order light source (3c) shown in FIG. 2(c).
), turn off the light source (3d
) is turned on, an image of the irradiated surface is captured by the photoelectric converter (4), and is stored in the fourth image memory (5d). The image at this time is shown in FIG. 2(d).

Next, a case will be described in which the side portion (2b) of the component (2) is recognized. l@W, device (5) selects two image signals for sides other than side (2b) 0 For example, each image signal in the images stored in the first image memory (5a) and third image memory (5C) A maximum value image is created by comparing the signal values corresponding to the pixels and taking the larger signal level representing brightness. This is shown in FIG. 3(a). In this maximum value image, part (2) is projected by the light source (3a) and the part where the shadow (8a) of the part is formed and the light source (
3C), the part where the shadow (8C) of the part was created in the image of the part (2) is erased, and the processed image (13
), it is possible to obtain a part image with no shadows within the 0-order component (2), and the unevenness that occurs on the 0-order component (2) can also be removed at this time.
The difference between the signal value and the signal value stored in the second image memory (5b), which is the image of the shadow, is determined and used as a difference image. This is the third
Figure (shown in bl.

That is, regarding the image in Fig. 2, the maximum values of image signal fa (x, y) when irradiated with light source (3a) and image signal fc (x, yl) when irradiated with light source (3C) are calculated by the arithmetic unit. [6) Ask for te. Next, find the maximum value and the light source (3b
)" r irradiation, the difference between the image signal fb (x, y) and the image signal fb (x, y) is determined by the arithmetic unit i (6).
x, y)) −fb(x, yl).

Here, when we examine the difference image g (x, y) shown in Figure 3(b), we find that when compared with the signal value of each pixel in the maximum value image shown in Figure 3(a), In the image of the part (2) irradiated, the part where the shadow (8b) of the part is formed is dark. Therefore, the (i4 value of the corresponding pixel is small, and g(x, yl
The value becomes a positive value and remains as a shadow (8e). but,
In the image of the part (2) irradiated by the light tA (3al), the part where the shadow (8a) of the part is formed and the light source (3C)
In the image of part (2) irradiated by
Since the portion where 8c) is generated is erased when obtaining the maximum value image, it is possible to obtain a shadow-free component image in the processed image (13), and the unevenness that occurs on the 0 component can also be eliminated at this time. In addition, the light source (3b)
) In the image (Fig. 2 fbl) illuminated by the light source (3a
) (Figure 2(a))
Or an image of the part (2) illuminated by the light source (3c) (
Similar specular reflection occurs in any of the images in FIG. 2(C)), so it remains in the maximum value image (FIG. 3(a)). Therefore, when the difference image (FIG. 3(b)) is obtained, the specular reflection portion is erased. In this way, the edges of the part (
Only the shaded part (8e) of 2b) can be extracted.

Next, measure the length and width of this shadow. An example of measurement will be explained based on FIG. 4. That is, the difference image is binarized using an appropriate threshold, the range in which the component exists is cut by a window (10), and the image values are projected in the horizontal and vertical directions of the image within the window (lO). In Figure 4 (1), (9a
) is a horizontal projection, (9b) is a vertical projection, the X direction is the position of the pixel, and the y direction is the number obtained by adding the values of the doubled pixels in the horizontal or vertical direction. This projection (9
a), (as shown in Figure 4(b) from 9bl,
Measure the vertical and horizontal distances of the shadow of the component within the window (IO), ie, the length (!4) and width (15). In this embodiment, the calculation of the maximum value image, the calculation of the difference image, and the measurement of shadows are performed by the calculation device (6).

Similarly, the shadow facing the shadow just obtained, that is, the part (2
) is measured by measuring the length and width of the shadow (8d) on the F side. The position or rotation calculated by the zero-order calculation device (6) that can determine the position of the side of part (2) or the center position or rotation angle of part (2) from the positions of the pair of opposing shadows. Data such as angles and other signals are compared with a preset reference value by a determining device (7) to determine whether they are acceptable or not, and the determination results are displayed. Also, if the correct part is within the window (10) based on the width and length of the shadow, a shadow that is longer and wider than the preset standard (+α) will be extracted, so it will be judged as a good product and the result will be displayed. The reference values stored in advance in this determination device (7) include, for example, the -L lower limit of the length of the part's shadow, the -L lower limit of the width of the shadow, the allowable deviation of the part, and the allowable rotation. quantity etc.

In this way, by using the maximum value image, it is possible to obtain an image in which unevenness in image values due to unevenness on the surface of component (2) is eliminated,
By taking the difference between the maximum value image and the image obliquely irradiated with respect to the side to be recognized of the part, it is possible to accurately measure the shadow of one side to be recognized of the part. Since the position, shape, and other geometric features of the part are recognized from this shadow, the part can be recognized reliably and with high precision. moreover,
The shadow of the part is extracted from the difference image, the length and width of the shadow of a pair of opposing sides are measured, and the position of part (2) is determined from the shape of the shadow. It is not necessary to memorize the sentence part (2), and the position, shape, or other geometric characteristics of the sentence part (2) can be recognized without extracting all the edges of the sentence part (2). Therefore, if there are other parts near the side of a part, the background is mirrored, or the height of the part is low, it may be difficult to extract a part of the shadow. Also, if part (2) has a certain height, the shadow is stable, and if you select two sides with stable shadows and recognize the part, the accuracy will be higher. I can recognize it well. In addition, the side to be focused on can be changed depending on the shape of the part, such as selecting a side where the contrast is more likely to appear in the background where the S part is placed.

In the above embodiment, the shadows of the opposing short sides of the component (2) were measured, but the long sides may also be measured.

Also, the number of light sources is not limited to four, and the positions where they are installed do not have to be at 90 degrees as in the embodiment described in F. ,
What is necessary is just to arrange it so that the side part can be easily recognized.

[Effects of the Invention] As described in 1- below, according to the present invention, there are three or more light sources capable of forming shadows on different sides of a component having side parts, and a side part of the part by irradiation from the light sources. A photoelectric converter that captures the image of the part and converts it into an electrical signal, an image memory that stores the image signal output by the light converter, and two image signals of images of sides of the part other than the side to be recognized. , the image (3
A maximum value image calculation device obtains a maximum value image signal of 1 [a] by comparing the output values of the corresponding pixels of each image and leaving the one with higher luminance.
11 with elephant signals! A difference image calculation device that calculates the difference in degree and obtains a difference image, and a shadow meter that recognizes the side by measuring the length and width of a pair of shadows facing each other among the sides of the part from the difference image ff11
By equipping one device and a determination device that recognizes the shape of a part from the shape of one set of shadows, it is possible to (i) create an image that eliminates unevenness in image values due to unevenness on the surface of the part; It can be measured with n accuracy. Furthermore, since the position, shape, or other geometrical features of the part are recognized from this shadow, the part can be recognized reliably and with high precision. moreover,
Since the position or shape of a component or other geometrical features are recognized from the length and width of the shadow in the direction in which it is easy to extract, it is possible to obtain a component recognition device that can recognize components quickly and reliably.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the configuration of a component recognition device according to an embodiment of the present invention, and FIGS. 2(a-d) are images of components irradiated with each light source according to an embodiment of the present invention. 2 (a) is an image when the part is irradiated with light #+3al, 1b) is an image when the part is irradiated with light source (3b), and 2 (C) is an explanatory diagram showing an image when a part is irradiated with a light source (3C), and FIG. 2(d) is an explanatory diagram showing an image when a part is irradiated with a light source (3d). Figure 3 (a
) is an explanatory diagram showing the maximum value image according to this example, FIG. 3(b) is an explanatory diagram showing the difference image, and FIG.
Fig. 4(b) is an explanatory diagram showing the projection of the part's shadow calculated from the image signal in Fig. 4(b), and Fig. It is a block diagram showing the configuration of a conventional component recognition device. (21--One component, (2a), (2bl, (2c)
, (2d) ---Side part, (3a), (3b1.
(3c), (3d)...Light source, (4)--
Photoelectric converter, (5a1. (5b), (5c),
(5dl--Image memory, (6)...Arithmetic unit, (
7)...determination device, (8a), (8b),
(8c), (8d), (8e)...shadow of part, (14)...length of shadow, (15)...width of shape. In addition, in the figures, the same reference numerals indicate the same or equivalent parts.

Claims (1)

[Claims] three or more light sources capable of forming shadows on different sides of a component having sides; a photoelectric converter that captures an image of the side of the component by irradiation with the light source and converts it into an electrical signal;
An image memory that stores the image signals output by the photoelectric converter, selects two image signals of images other than the side to be recognized among the sides of the above component, and compares the output values of the corresponding pixels of the image signals. a maximum value image calculation device which obtains a maximum value image signal by leaving the one with greater brightness; a computing device, a shadow measuring device that measures the length and width of a pair of opposing sides of the part from the difference image to recognize the side; and a shadow measuring device that recognizes the side from the shape of the pair of shadows of the part. A parts recognition device equipped with a determination device that recognizes the shape of.