JPH05296725A - Position detecting method - Google Patents

Abstract

PURPOSE:To provide an electrode position detecting method of high reliability free from a noise effect due to a background and a part body, regarding image recognition and processing in an electronic part packaging facility or the like. CONSTITUTION:An electronic part 1 is first photographed and an image pattern 4 is obtained. Then, the rough inclination and center of the image pattern 4 of the part 1 is obtained, thereby setting a processing area 6 for electrode position detection. A brightness change in the processing area 6 is projected, and brightness change data 8 as a reference is prepared on the basis of the projected data 7. While the reference brightness change data 8 is being moved, the degree of similarity to the projected data 7 is calculated, and a peak position over a threshold value is detected as an electrode position 11.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image recognition method of a visual recognition device required for mounting electronic parts at high speed and with high accuracy in electronic part mounting equipment and the like. The present invention relates to a method of accurately measuring the electrode position of the electrode according to an image pattern.

[0002]

2. Description of the Related Art In recent years, in the field of mounting electronic components, a technique for mounting electronic components on a circuit board at high speed and with high precision is required. Therefore, there is a tendency to utilize an image recognition technique that processes an image pattern obtained by capturing an image of an electronic component at high speed to detect the position / tilt of the electronic component at high speed and accurately. In addition, as electronic components are becoming finer, the number of pins of electrodes is increasing. Therefore, for electronic components having a large number of electrodes, it is desired to detect the position of each electrode.

Conventionally, as a method of recognizing an electronic component utilizing image recognition technology, a transparent recognition method of illuminating a target electronic component from behind and processing its silhouette to detect a center, an inclination, an electrode position, and the like, A reflection recognition method has been proposed in which light is applied from the front and the light reflected from the electrodes is processed to detect the center, inclination, electrode position, and the like.

A conventional component recognition method will be described below with reference to the drawings.

FIG. 4 is an example of a transmission recognition method and shows an example of detecting the tip position of the lead by illuminating the leaded electronic component 42 from behind (hereinafter referred to as transmission illumination). As shown in FIG. 4A, when the transmissive illumination 41 is applied to the leaded electronic component 42 and the video camera 43 captures an image, an image pattern 44 as shown in FIG. 4B is obtained. The silhouette of the image pattern 45 of the leaded electronic component 42 is displayed by transmitted illumination. The boundary between the image pattern 45 of the leaded electronic component 42 and the background is shown in FIG.
When the locus of the boundary tracking is obtained by the detection as shown in (c) of FIG. The position 46 at which this U-turn is made is detected as the electrode position to be detected. Since this transparent recognition method processes silhouettes,
The logic is simple and the processing is fast.

However, with the transmission recognition method, it is difficult to detect the electrode position of an electronic component (hereinafter referred to as a J-lead electronic component) in which the electrode is bent inward from the outer shape of the component. Therefore, a reflection recognition method has been proposed that can directly capture the electrodes. FIG. 5 shows an example of the reflection recognition method, in which the lead position of the J-lead electronic component 51 is detected. As shown in (a) of FIG. 5, when an illumination (hereinafter referred to as “reflected illumination”) 52 is applied from the front of the J-lead electronic component 51 and an image is taken by the video camera 43, an image pattern as shown in (b) of FIG. You get 53. In the image pattern 54 of the J-lead electronic component 51, the reflected light of the reflective illumination 52 is projected, so that the electrode portion is bright. As shown in (c) of FIG. 5, the electrode portion which shines brightly is detected as a rough position by scanning like S. The processing window 56 is provided based on the detected rough position, and the brightness distribution in the processing window 56 is set to 5
7 is projected and the extreme value 58 is detected. The electrode part is
Since the brightness is high, the detected extreme value 58 is detected as the electrode position to be detected.

Conventionally, the difference method has been used to detect the extreme value of the projection data 57. The difference method is for analyzing the displacement of the data before and after, and 59 is obtained by converting the projection data 57 into the difference data. At this time, the point where the difference data turns from positive to negative is detected as an extreme value.

[0008]

When detecting the electrode position by the above-mentioned conventional technique, as shown in FIG. 6, when there is a bright noise 61 in the background or a locally dark portion 62 in the component body, the difference data 59 is obtained. There is a point that changes from positive to negative at a position different from the electrode position of. For this reason, noise may be determined to be the electrode position, and correct component recognition may not be performed.

[0009]

In order to solve the above problems, the present invention uses the following means.

First, the target electronic component is imaged to obtain an image pattern. Utilizing conventional technology to detect the approximate center and tilt of parts. Next, a processing area for electrode detection is set using the detected center and inclination. The brightness change in the set processing area is projected to obtain projection data. Luminance change data serving as a reference is created based on the obtained projection data. The area where the reference brightness change data and the projection data do not overlap is calculated, and the reciprocal thereof is taken as the similarity. The reference luminance change data is sequentially shifted with respect to the projection data, the similarity at that time is obtained, and the similarity data is obtained. In the obtained similarity data, the peak position exceeding the threshold value is detected and used as the electrode position.

[0011]

With the above-described structure, the present invention is not affected by a significant change in brightness other than the position of the electrode such as the background or noise of the component body. Therefore, more reliable position detection can be realized.

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS As an embodiment of the present invention, a method for detecting the electrode position of a J-lead electronic component 1 will be described with reference to FIGS.
Will be explained.

In FIG. 3, the first step is an image pattern input step S1. As shown in (a) of FIG. 1, a video signal is obtained by capturing an image of the J-lead electronic component 1 that is a recognition target with an image capturing unit such as a video camera 3. The obtained video signal is digitized to form an image pattern 4 shown in FIG.

The second step is the processing area determining step S2. In the image pattern 4, conventional techniques such as edge detection are used to find the approximate center and inclination of the image pattern 5 corresponding to the J-lead electronic component 1. The processing area 6 is set by using the obtained rough center and inclination, and the external dimensions of the parts and the inter-electrode dimensions given in advance.

The third step is a brightness change projection step S3. As shown in FIG. 1C, the brightness change in the processing area 6 set in the second step is projected in the α direction to obtain projection data 7. As a projection method, there are a method of accumulating luminance on the same straight line in the α direction, a method of obtaining a maximum value, and the like.

The fourth step is a reference brightness change projection data creation step S4. Projection data 7 obtained in the third step
Based on, the luminance change data 8 to be the reference is created. For example, as shown in FIG. 1C, the width is set to the lead pitch d and the height is set to two levels.

The fifth step is the similarity calculation step S5.
The projection data 7 obtained in the third step and the reference luminance change data 8 obtained in the fourth step are compared to calculate the degree of similarity.
As a method of calculating the degree of similarity, for example, there is a method of using the reciprocal of the non-overlapping area (hatched portion in the figure) as shown in FIG. Reference brightness change data 8 for projection data 7
The similarity data 9 is obtained by shifting the distance and detecting the similarity each time. As shown in FIG. 2B, unlike the conventional difference method, the data change itself is compared, so that it is not affected by the background noise 21 or the component body noise 22.

The sixth step is an electrode position determining step S6. In the similarity data 9 obtained in the fifth step, as shown in FIG.
As shown in (c), the peak value exceeding the threshold value 10 is detected and the position 11 of the electrode is detected.

The process in the sixth step is repeated to detect all electrode positions, and the process is completed.

[0020]

According to the present invention, unlike the prior art, the change in the data value is compared, so there is little possibility of being affected by the noise of the background or the component body. Therefore, it is possible to detect the electrode position of the recognition target with higher reliability without being affected by the shape / state of the electronic component to be processed and the state of the background.

[Brief description of drawings]

FIG. 1 is an explanatory diagram showing a method for detecting an electrode position according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing in detail a method of detecting an electrode position according to an embodiment of the present invention.

FIG. 3 is a flowchart showing an outline of an embodiment of the present invention.

FIG. 4 is an explanatory diagram showing a conventional electronic position detection method.

FIG. 5 is an explanatory diagram showing another conventional electrode position detection method.

FIG. 6 is an explanatory diagram showing a problem of the conventional example.

[Explanation of symbols]

 1 J-lead electronic component (object to be recognized) 2 Reflective lighting 3 Video camera 4 Image pattern 5 Image pattern corresponding to J-lead electronic component 6 Electrode position detection processing area 7 Brightness change projection data 8 Reference brightness change data 9 Similarity data 10 Threshold 11 Electrode position 21 Background noise 22 Noise on component body

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁵ Identification number Reference number within the agency FI Technical display location H05K 13/08 B 8315-4E (72) Inventor Masao Iriya 1006 Kadoma, Kadoma, Osaka Prefecture Matsushita Electric Sangyo Co., Ltd.

Claims (1)

[Claims] 1. A first step for capturing an image of an object to be recognized to obtain an image pattern, a second step for setting a processing range by detecting a rough center and an inclination, and a processing range set by the second step. The third step of projecting the brightness change in the image, the fourth step of creating the reference brightness change data based on the brightness change projection data projected by the third step, and the brightness change projected by the third step The fifth step of calculating the similarity by sequentially comparing the data and the reference luminance change data created in the fourth step by one data, and the recognition object based on the similarity data calculated in the fifth step. A position detecting method including a sixth step of detecting the electrode position of.