JPH04269606A - Part detecting apparatus - Google Patents

Abstract

PURPOSE:To detect the position of a part quickly by shortening the image processing time of an image. CONSTITUTION:A part detecting apparatus is formed by including an image sensing means 1, an edge detecting means 3, a processing-region determining means 4 and a positioning output means 5. The processing-region determining means 4 determines the processing region on an image which is to be scanned at the next time with the edge detecting means 3 in consideration of the data of the outer configuration of the part. Therefore, it is possible to gradually narrowing the processing region. Thus, the image processing time is gradually shortened, and the detecting speed of the part is increased.

Description

[Detailed description of the invention]

0001

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a component detection device for detecting the position of a component by image processing.

0002

[Prior Art] Conventionally, as one method for detecting the position of minute parts such as electronic parts by image recognition, an image processing area is divided in advance into a plurality of small areas, and first, rough scanning is performed to detect the presence of the target object. A method has been proposed in which the position of a component is quickly detected by recognizing an area that exceeds a certain image density value as an area that exceeds a certain image density value, and then newly scanning only that small area densely. (Refer to Publication No.-240987).

0003

[Problem to be Solved by the Invention] However, in the above conventional method, since the size (area) of the small area to be scanned closely is determined in advance, it is actually necessary to scan even within the small area. There is a problem in that even areas without parts (areas where no parts exist) are scanned closely, resulting in wasted processing time.

The present invention has been made in view of the above problems, and an object thereof is to provide a component detection device that can quickly detect the position of a component by shortening the image processing time. be.

[0005]

[Means for Solving the Problems] In order to achieve the above object, the present invention provides an imaging means for taking an image of a part, and an image obtained by the imaging means that scans an image obtained by the imaging means within a designated area to capture the edge of the part. A process of determining an area on the screen to be detected next by the edge detection means based on the edge detection means to be detected and the position information of the component edge detected by the edge detection means and the external shape information of the component. A component detection device including an area determining means and a positioning output means for calculating the position of the component by scanning an image based on the position information of the end of the component obtained by the end detecting means and outputting the result. It is characterized by comprising the following.

[0006]

[Operation] According to the present invention, the processing area determining means gradually narrows this processing area because the edge detecting means determines the area on the screen to be scanned next by taking into account the external shape information of the part. As a result, the area of the area to be scanned on the screen can be kept smaller than that of the conventional method, and as a result, the image processing time is shortened and the speed of component position detection is increased.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the accompanying drawings.

FIG. 1 is a block diagram showing the configuration of a component detection device according to the present invention. In this embodiment, the position of a minute electronic component having a plurality of pins around it is detected.

First, the configuration of the component detection device will be explained based on FIG.
a storage means 2 for storing images obtained by the storage means 2; and an edge detection means 3 for detecting the edges (pin edges) of parts by scanning the images stored in the storage means 2 within a designated area on the screen. Based on the position information of the component edge (pin edge) detected by the edge detection means 3 and the known external shape information of the component, the edge detection means 3 determines the area on the screen to be detected next. It is composed of a processing area determining means 4 for determining the processing area, and a positioning output means 5.

The positioning output means 5 includes a pin array detection means 6 for detecting a pin array by scanning an image based on the positional information of the component edge (pin edge) obtained by the edge detection means 3; A calculation means 7 that calculates the position (center position) of the component based on the position information of the pin row obtained by the pin row detection means 6, and an output means 8 that outputs the result calculated by the calculation means 7. It is configured.

[0011] Here, the procedure for detecting the position of an electronic component will be specifically explained based on FIGS. 2 to 8. 2 is a diagram showing a processing screen, FIGS. 3 and 4 are explanatory diagrams showing a pin edge detection method, FIG. 5 is an explanatory diagram showing a pin row detection method, and FIG. FIG. 7 is an explanatory diagram showing a method of calculating the center position of a component, and FIG. 8 is a flowchart showing a position detection procedure.

The component imaged by the imaging means 1 is displayed as W on the processing screen shown in FIG. 2, and a plurality of pins 9 protrude around it.

First, the part image W displayed on the processing screen
The pin 9A on the upper left side of the screen is detected, but at the time of this detection, the processing area S1 in FIG. 2 is set (step 1 in FIG. 8).
, the pin 9A is detected by the end detection means 3 within this processing area S1. Note that the processing area S1 is determined by the distance range within which the component can move within a tray (not shown) in which the component is stored.

In the processing area S1, as shown in FIG. 3, the edge detecting means 3 scans in the right direction every four lines from point a at predetermined intervals (step 2 in FIG. 8). , in each scanning line L0, L4, L8, L12, scanning is performed to find the first point (point b in the example shown in FIG. 3) where the image density is above a certain threshold Th1 and the width is within a predetermined range. will be carried out. Then, the next secondary detection is performed using that detection point as the primary candidate point of the upper left pin edge.

In the secondary detection, as shown in FIG.
Returning three lines from the scanning line L12 passing through the next candidate point (point b), four lines are continuously scanned every line from the scanning line L9. For example, in the continuous scanning of four lines from scan line L9 to L12 in FIG.
In the illustrated example, the positions of pins 9C, 9D, 9E, 9F) change for each line L9, L10, L11, so these pins 9... (9C, 9D, 9E, 9F) are the same as the pin 9A on the upper left. is not recognized. In this case, the process returns to the primary detection and searches for candidate points again.

As shown in FIG. 4, the scanning line L
In the 4-line continuous scan from 13 to L16, the position A of the pin 9A is
, A', A'' points are within a predetermined width (for example, within a range of ±1 pixel), pin 9A is recognized as the top left pin, and the point on the topmost scanning line L14. Let A be the pin edge point to be detected.

As described above, when the edge point A of the upper left pin 9A is detected within the processing area S1, the processing area determining means 4 determines the position of this edge point A (x1, y1) and the component. In order for the edge detecting means 3 to detect the pin 9B on the upper right side based on the known external shape information of the component itself (in this embodiment, the distance d between the pins 9 at both ends on the same side of the component). The processing area S2 to be scanned is determined (step 4 in FIG. 8). The edge point B (x2, y2) of pin 9B is expressed by the maximum inclination angle θ of the component and the distance d as follows:

[0018]

[Math. 1] x1+d・cosθ≦x2≦x1+dy1−d
Since it is estimated that sin θ≦y2≦y1+d·sin θ, as shown in FIG. 2, the area of the processing region S2 including the edge point B is smaller than that of the processing region S1.

Thus, the processing area S by the edge detecting means 3
2 (step 5 in FIG. 8), the edge point B of the upper right pin 9B is detected (step 6 in FIG. 8) in the same manner as described above. Since the area is smaller than that of the processing area S1, the image processing time is shortened and the detection speed of the edge point B is increased.

When edge points A and B of pins 9A and 9B are determined in this way, points A and B are obtained as shown in FIG.
Scanning is performed using a straight line L, which is obtained by offsetting the straight line connecting the lines by a predetermined amount, as a scanning line, and by this scanning, an image density distribution along the scanning line L as shown in the figure is obtained (
Step 7 in Figure 8). Also, by taking a plurality of straight lines L (for example, in the case of three lines, one before and one before and after the straight line L) and adding up the image density distributions on those straight lines,
It is also possible to increase the accuracy.

Next, the edge point C of the lower left pin 9C and the edge point D of the lower right pin 9D (see FIG. 2) are detected by the same procedure as above (steps 8 to 13 in FIG. 8). ,
Obtain the image density distribution between pins 9C and 9D at the left and right ends (Figure 8
step 14). At this time, the end detection means 3 detects the pin 9.
Processing areas S3, S to be scanned to detect C, 9D
4 (see FIG. 2) is set by the processing area determining means 4 (steps 8 and 11 in FIG. 8), but the processing area S3 is set based on the position information of the edge points A and B that have already been found and the external shape information of the part. The processing area S4 is determined by the edge points A, B,
Since it is determined based on the position information of C and the external shape information of the part, the areas of these processing areas S3 and S4 gradually become smaller as shown in FIG.
The area of becomes smaller in this order. Therefore, edge points A, B
, C, and D is gradually reduced, and the detection speed is gradually increased.

As described above, the left and right end pins 9A of the upper and lower sides are
, 9B and between 9C and 9D, the pin array detecting means 6 detects the positions of the pin arrays 9 on the upper and lower sides based on this image density distribution (step 15 in FIG. 8). ), the calculating means 7 calculates the centers of the pin rows 9 on the upper and lower sides based on the positional information of the pin rows 9 detected by the pin row detecting means 6 (step 16 in FIG. 8).
.

[0023] Here, to explain the method of detecting the positions of the pin rows 9 on the upper side, four points g, h, i, and j that straddle a certain threshold Th2 in the image density distribution shown in Fig. 6 are found. Find each edge point m1, m2 on the rear, left side, and right side by interpolation,
Let the midpoint m of these be the midpoint of the pin 9. Then, if we calculate the center of gravity of the midpoint coordinates of all the pins 9... found in this way, that point becomes the midpoint M of the pin row 9... on the upper side.
1 (see FIGS. 5 and 7).

Similarly, the midpoint M of the pin row 9 on the lower side
2 (see FIG. 7) is obtained.

By the way, above has explained the procedure for finding the midpoints M1 and M2 of the pin rows 9 on the upper and lower sides, but the midpoints M3 and M4 of the pin rows 9 on the left and right sides (see FIG. 7) are obtained in exactly the same way (steps 17 and 18 in FIG. 8). That is, the edge points E, F, G, H (see FIGS. 2 and 7) in the pin rows 9... on the left and right sides are determined by the same procedure as steps 1 to 14 in FIG. 8, and these pin rows 9... However, since the processing area for detecting edge points E, F, G, and H is gradually narrowed for the same reason as mentioned above, the image processing time can be further shortened and detection can be performed at high speed. You will be able to do this. Also, edge points A, B,
Edge points E, F, G, based on C, D and the external shape information of the part.
It is also possible to obtain the image density distribution without detecting H, and in this way the image processing speed is further increased.

When the midpoints M1, M2, M3, and M4 of the upper, lower, left, and right pin rows 9 are determined, as shown in FIG. 7, the opposing midpoints M1 and M2, M3 and M4 By finding the intersection of each straight line connecting the , the center of gravity G of the whole part can be found, and the position and inclination of the part can be calculated from this (
In step 19) of FIG. 8, this result is output by the output means 8 of the positioning output means 5, and the electronic component is positioned based on this output result.

[0027]

As is clear from the above description, according to the present invention, an image capturing means for capturing an image of a part, and an image obtained by the image capturing means are scanned within a specified area to capture the edge of the part. A process of determining an area on the screen to be detected next by the edge detection means based on the edge detection means to be detected and the position information of the component edge detected by the edge detection means and the external shape information of the component. A component detection device including an area determining means and a positioning output means for calculating the position of the component by scanning an image based on the position information of the end of the component obtained by the end detecting means and outputting the result. Because of this configuration, it is possible to reduce the image processing time and quickly detect the position of the component.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the configuration of a component detection device according to the present invention.

FIG. 2 is a diagram showing a processing screen.

FIG. 3 is an explanatory diagram showing a pin edge detection method.

FIG. 4 is an explanatory diagram showing a pin edge detection method.

FIG. 5 is an explanatory diagram showing a method for detecting pin rows.

FIG. 6 is an enlarged view of part P (image density distribution) in FIG. 5;

FIG. 7 is an explanatory diagram showing a method of calculating the center position of a component.

FIG. 8 is a flowchart showing a position detection procedure.

[Explanation of symbols]

1 Imaging means 2. Storage means 3 End detection means 4 Processing area determining means 5 Positioning output means 6 Pin row detection means 7. Calculation means 8 Output means 9 Pin W Parts (image)

Claims (1)

[Claims] Claims: 1. An imaging means for taking an image of a part; an edge detection means for detecting an edge of the part by scanning an image obtained by the imaging means within a designated area; processing area determining means for determining an area on the screen to be detected next by the edge detecting means based on positional information of the detected component edge and external shape information of the component; A component detection device comprising a positioning output means for calculating the position of a component by scanning an image based on positional information of the end of the component and outputting the result.