JP3644272B2 - Image recognition method - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image recognition method for recognizing an image obtained by imaging an electronic component.
[0002]
[Prior art]
In a mounting process for mounting electronic components on a substrate, position correction using image recognition is widely used to improve mounting position accuracy. In this method, the position of the center of gravity and the inclination of the electronic component are obtained by recognizing an image obtained by imaging the electronic component held by the transfer nozzle with a camera. When an electronic component is imaged with a camera, it is necessary to illuminate the electronic component, and an illumination method is selected according to the type of electronic component and the purpose of recognition. For example, a method of illuminating an electronic component from below and recognizing reflected light with a camera is generally used for an electronic component having a glossy electrode formed on the lower surface.
[0003]
[Problems to be solved by the invention]
However, in the above-described method for recognizing reflected light, the amount of reflected light varies depending on various factors such as the amount of illumination light, the irradiation angle, and the properties of the imaging surface of the electronic component. Therefore, even when performing position recognition using images for the same type of electronic component, the amount of light that is reflected and incident on the camera varies due to slight differences in illumination conditions and the surface of the electronic component, and the recognition result does not stabilize due to this variation. There was a problem of causing misrecognition and unrecognition.
[0004]
Accordingly, an object of the present invention is to provide an image recognition method capable of performing stable position recognition.
[0005]
[Means for Solving the Problems]
In the image recognition method of the present invention, an electronic component in which a glossy part forming a part of an outline is formed on the lower surface is held by a nozzle, and the lower surface of the electronic component is imaged by a camera in a state where the electronic component is illuminated from below. An image recognition method for recognizing the position of the electronic component by recognizing an image obtained in this manner, the step of capturing the image by capturing the electronic component, and binarizing the image to obtain the glossy portion The image, scanning the image starting from a point inside the electronic component whose positional relationship with the glossy part is known, obtaining the farthest point of the glossy part, Estimating the contour of the electronic component.
[0006]
According to the present invention, a contour obtained by binarizing the captured image to extract a glossy portion, scanning from a known point inside the electronic component, and obtaining the farthest point of the glossy portion By estimating the contour of the electronic component based on the line, it is possible to eliminate the influence of the excessive glossy portion and perform stable position recognition.
[0007]
DETAILED DESCRIPTION OF THE INVENTION
Next, embodiments of the present invention will be described with reference to the drawings. 1 is a perspective view of an electronic component mounting apparatus according to an embodiment of the present invention, FIG. 2 is a plan view of the bottom surface of the electronic component, FIG. 3 is a flowchart of the image recognition method, and FIGS. ), (C) are image diagrams showing contour lines of the electronic component.
[0008]
First, with reference to FIG. 1, an electronic component mounting apparatus in which the image recognition apparatus of the present invention is incorporated will be described. In FIG. 1, the transfer head 3 is moved in the horizontal direction and the vertical direction by the transfer head movement control means 14. A suction nozzle N is attached to the lower end portion of the transfer head 3, and the electronic component 4 as the inspection object is sucked and held by vacuum suction from the suction nozzle N by suction means (not shown). The suction nozzle N is rotated in the θ direction about the central axis of the suction nozzle N by a motor M built in the transfer head 3. A camera 1 having a light source 2 is disposed below the suction nozzle N, and the camera 1 images the electronic component 4 illuminated by the light source 2.
[0009]
A parts feeder 12 is disposed on the side of the camera 1. A substrate holding table 11 is disposed on the opposite side of the parts feeder 12, and a substrate 10 having a circuit pattern L formed on the surface thereof is held on the substrate holding table 11. The electronic component 4 is picked up from the parts feeder 12 by the transfer head 3 and mounted on the substrate 10.
[0010]
The A / D converter 5 converts the image signal of the camera 1 into a digital signal. The frame memory 6 stores the converted digital image signal. The CPU 7 performs various calculations such as image processing in accordance with programs stored in the ROM 8. The RAM 9 stores these calculation results.
[0011]
The drive circuit 3 drives a motor M that rotates the suction nozzle N. The machine controller 15 controls the drive circuit 13 and the transfer head movement control means 14 and is controlled by the CPU 7. The electronic component 4 is imaged by the camera 1 and its position is recognized by the CPU 7, and the positional deviation of the electronic component 4 is corrected by controlling the drive circuit 13 and the transfer head movement control means 14 based on the recognition result. Can be mounted on the substrate 10.
[0012]
Next, the electronic component 4 to be recognized will be described with reference to FIG. As shown in FIG. 2, an electrode 4 a is formed on the lower surface of the electronic component 4 so as to form a part of the contour of the electronic component 4. The electrode 4a is a glossy part having a glossy surface that reflects the irradiated light. By positioning the electronic component 4 on the camera 1 and illuminating with the light source 2 and taking an image, a binary image can be obtained in which the portion of the electrode 4a is a bright image and the other non-glossy portion 4b is a dark image. it can.
[0013]
Next, the image recognition method will be described along the flow of FIG. In this method, the farthest point of the edge of the bright image portion is obtained by scanning a binarized image obtained by imaging the lower surface of the electronic component 4, and the shape of the electronic component 4 is specified from this farthest point. To do. First, the electronic component 4 is positioned on the camera 1 and picked up to capture an image of the lower surface of the electronic component 4 (ST1). Next, a scan length for scanning on the image is determined from the size of the electronic component 4 (ST2), and a threshold value for binarizing the obtained image is determined (ST3). The processes of ST2 and ST3 need only be performed once as an initial setting when the same type of electronic component is continuously recognized. Of course, it may be performed for each recognition.
[0014]
Next, the obtained image is binarized (ST4). As a result, as shown in FIG. 4A, a binarized image in which the electrode 4a formed on the lower surface of the electronic component 4 is a bright image and the background image or the non-glossy portion 4b of the electronic component 4 is a dark image is formed. Can be obtained. At this time, there may be a case where the bright image portion A is detected on the lower surface of the electronic component 4 in a range that is originally a non-glossy portion due to a slight difference in surface shape or illumination conditions. For this reason, if a method such as center-of-gravity detection is directly applied to the binarized image, the obtained position of the electronic component 4 causes an error due to the bright image portion A.
[0015]
Therefore, in order to eliminate the influence of such noise, processing for obtaining the contour of the electronic component 4 is performed by the method described below. In this method, scanning is performed linearly in the outer peripheral direction around a point having a known positional relationship with the electrode 4a inside the electronic component 4, and the farthest point of the edge of the bright image portion, that is, the bright image portion. Is detected, and the shape of the electronic component 4 is specified from this edge.
[0016]
Hereinafter, it demonstrates along a flow. First, it is determined whether or not scanning has been completed over the entire angle range, that is, whether or not the angle θ shown in FIG. 4B has been scanned over 0 to 360 degrees (ST5). If there is an unscanned range, scanning is performed linearly along the straight line 1 from the position of the nozzle N whose position is known, and processing for obtaining the farthest point of the edge of the bright image portion is performed (ST6). At this time, since the bright image portion A due to noise inside the electronic component 4 does not correspond to the farthest point, these portions are excluded, and the influence on the shape specification of the electronic component 4 is excluded.
[0017]
As a result of this processing, it is determined whether or not an edge is detected. If an edge is detected, the coordinate value of the detected point is recorded as position data (ST8). If no edge is detected, NG is recorded in the position data. Next, the angle θ in the scanning direction is increased by Δθ, and the processing from ST5 onward is repeated, the scanning of all angles (0 to 360 degrees) is completed, and the edge detection processing ends.
[0018]
Thereafter, a process of estimating the contour line from the farthest point detected in this way is performed. Here, only the farthest point detected in the range where the original electrode 4a exists is extracted, and the farthest point detected in the other extra range is regarded as noise and eliminated. Thereby, as shown in FIG.4 (c), the outline 4c of the electrode 4a which shows a part of external shape of the electronic component 4 is detected. Based on the contour line 4c thus determined, the position of the center of gravity of the electronic component 4 and the inclination in the horizontal plane are specified, and a positional deviation is detected. In this way, by detecting only the outline of the electrode 4a of the electronic component 4, it is possible to eliminate the influence of noise appearing inside the electronic component 4 and perform accurate position recognition.
[0019]
【The invention's effect】
According to the present invention, a contour obtained by binarizing the captured image to extract a glossy portion, scanning from a known point inside the electronic component, and obtaining the farthest point of the glossy portion Since the shape of the electronic component is estimated based on the line, it is possible to perform stable position recognition by eliminating the influence of an extra glossy portion that does not exist originally.
[Brief description of the drawings]
FIG. 1 is a perspective view of an electronic component mounting apparatus according to an embodiment of the present invention. FIG. 2 is a plan view of a lower surface of the electronic component according to an embodiment of the present invention. FIG. 4 is a flowchart of an image recognition method. FIG. 4A is an image diagram representing an outline of an electronic component according to an embodiment of the present invention. FIG. 4B is an image diagram representing an outline of an electronic component according to an embodiment of the present invention. (C) Image figure showing outline of electronic component of one embodiment of the present invention
DESCRIPTION OF SYMBOLS 1 Camera 2 Light source 3 Transfer head 4 Electronic component 4a Electrode 4c Contour line

Claims (2)

An electronic component in which a glossy part forming a part of the contour is formed on the lower surface is held by a nozzle, and an image obtained by imaging the lower surface of the electronic component with a camera while the electronic component is illuminated from below is recognized. An image recognition method for recognizing the position of the electronic component thereby capturing the electronic component and capturing the image, binarizing the image to extract the glossy portion, and the gloss Scanning the image starting from a point inside the electronic component whose positional relationship with the part is known, and obtaining the farthest point of the glossy part, and estimating the contour of the electronic component from these farthest points An image recognition method comprising: The image recognition method according to claim 1, wherein the starting point is the nozzle.

Images