JP4150262B2 - Component recognition method and apparatus - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a component recognition method and apparatus, and more specifically, processes a captured image of a component and recognizes the posture of the component, such as the component center and component tilt, based on the component terminal detected by the image processing. The present invention relates to a component recognition method and apparatus.
[0002]
[Prior art]
Conventionally, in order to accurately mount electronic components (hereinafter simply referred to as components) on a printed circuit board in a component mounting machine, the components are picked up by an image pickup device such as a CCD camera before the components sucked by the suction nozzle are mounted on the printed circuit board. The component is accurately mounted on the printed board by recognizing and calculating a suction posture at the time of suction, that is, a suction shift (a shift between the suction position and the center position of the component, a shift in the suction angle) and correcting it.
[0003]
When a part is imaged and its suction posture is recognized, since there are lead terminals on each side of the part, the terminal is detected for each side where the lead terminal exists as in Patent Document 1, and the detection result Based on the above, parts recognition is performed to calculate the adsorption deviation. In addition, processing for deleting objects other than terminals from the detection result and inspection such as detection of defective terminals are also performed for each side to increase detection accuracy.
[0004]
[Patent Document 1]
JP-A-6-223185 (Claim 1)
[0005]
[Problems to be solved by the invention]
However, since the detection lead inspection in the conventional lead recognition method is performed only on a side-by-side basis, the items that can be inspected are limited. In particular, the processing for deleting objects other than lead terminals from the detection results was only processing for deleting terminals that are not on the same straight line, and processing for deleting end leads when the pitches at both ends were abnormal. For this reason, when other than the leads exist on the same straight line at the same interval as the lead pitch, it is impossible to determine whether the lead terminal or not based only on the detection result of one side. Accordingly, there has been a problem that recognition of a part such as QFN in which terminals not related to centering of various shapes are present at the corners of the part is not stable in the conventional method.
[0006]
Accordingly, an object of the present invention is to provide a component recognition method and apparatus capable of improving the recognition accuracy for a component having a terminal that is not related to centering at the component corner.
[0007]
[Means for Solving the Problems]
In order to solve the above problems, in the present invention, in the component recognition method for processing the image of the imaged component and recognizing the orientation of the component based on the component terminal detected by the image processing, the imaged component Process the image with corner coordinates And lead terminal And based on the acquired corner coordinates Scan the image along the diagonal line, detect the corner terminal by this scan, perform different parts inspection to see if the part recognition for the specified part, Determine if a corner terminal exists, In the case of different parts, save the corner terminal position, When it is determined that a corner terminal exists From the image Delete the corner terminal, From the image After deleting the corner terminal Lead Terminal Conduct lead inspection on the lead terminals after inspection. A configuration that recognizes the posture of the component based on the above is adopted.
[0008]
Further, in the present invention, the captured component image is processed in the component recognition device that processes the captured component image and recognizes the orientation of the component based on the component terminal detected by the image processing. Have means to obtain corner coordinates and lead terminals Image processing apparatus and corner coordinates obtained from the image processing Means for scanning an image along a diagonal line, means for detecting a corner terminal by the scan, means for inspecting whether or not part recognition has been performed on a specified part, and in the case of a different part, Means for storing the corner terminal position; When it is determined that a corner terminal exists On the image Means to delete the corner terminal; On the image After deleting the corner terminal Lead Terminal For lead inspection and lead terminals after inspection A configuration having a component center and a means for calculating its inclination is also employed.
[0009]
In such a configuration, since the corner recognition unnecessary for the component recognition not related to the centering is deleted and the component recognition is performed, the component recognition accuracy can be improved and the component mounting accuracy can be improved.
[0010]
The corner terminal can be deleted by determining whether or not the corner terminal exists based on the terminal distance from the corner coordinates. If the corner terminal is close to the adjacent terminal depending on the part type, the corner terminal may not be recognized, so the image is scanned along the diagonal line obtained from the corner coordinates, and the corner terminal is detected by this scan. To do. The corner terminal detected in this way is deleted from the image by painting.
[0011]
By performing terminal fill processing in this way, terminals that you do not want to detect can be deleted from the image, so it is not only unnecessary to detect unnecessary terminals themselves, it also does not affect the detection of surrounding terminals, Only necessary terminals can be detected accurately, and accurate component recognition can be performed.
[0012]
Further, since the corner terminal can be reliably detected by the diagonal scan, it is possible to perform the different part inspection, that is, the inspection of whether or not the component recognition has been performed on the designated component.
[0013]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, the present invention will be described in detail based on embodiments shown in the drawings.
[0014]
<Configuration of component mounting apparatus and image processing apparatus>
FIG. 1 is a block diagram showing a control configuration of a component mounting apparatus (component mounting machine) to which the present invention is applied. The component mounting apparatus is a component (electronic component) 20 supplied from a component supply apparatus (not shown). The head portion 3 is provided with a suction nozzle 3a for sucking water. The head unit 3 is driven by an X-axis motor 11 and a Y-axis motor 12 driven by a controller 10 constituted by a CPU, and is configured to be movable in the XY-axis direction. Further, the head unit 3 is driven in the Z-axis direction by the Z-axis motor 13 at the time of component suction and component mounting and is moved up and down, and the suction nozzle 3a is configured to be rotated around the nozzle axis by the θ-axis motor 14.
[0015]
The component mounting apparatus includes an imaging device 5 including a lens 5a such as a CCD camera that captures an image of the component 20. The head unit 3 moves to the imaging device 5 after component adsorption, and the illumination device 15 The illuminated component 20 is imaged by the imaging device 5. The captured image of the component is input to an image processing apparatus 7 that includes a CPU 7a, an image memory 7b, an A / D converter 7c, and a component data memory 7d. The image processing device 7 captures an image of a set area, processes it by a known algorithm, recognizes the suction posture of the component, and calculates a positional shift between the component center and the suction center, and a suction angle shift. The controller 10 corrects this misalignment when driving the X-axis, Y-axis, and θ-axis motors 11, 12, and 14, and mounts the component 20 on the board (not shown) being conveyed.
[0016]
In addition, the component mounting apparatus is provided with input devices such as a keyboard 21 and a mouse 22 for inputting component data, and the generated component data is stored in a storage device 23 including a hard disk, a flash memory, or the like, or image recognition. It can be stored in the component data memory 7d in the apparatus 7. In this way, component data supplied from a host computer (not shown) connected to the component mounting apparatus may be stored in the storage device 23 or the component data memory 7d without using the input device. . In addition, a monitor (display device) 24 is provided, and on this screen, component data, calculation data, and a component image captured by the imaging device 5 can be displayed.
[0017]
FIG. 2 illustrates a state in which the component 20 a sucked by the suction nozzle 3 a is illuminated by the illumination device 15 and is imaged by the imaging device 5. The imaging device 5 captures an image of the set area by the control line 7d from the CPU 7a. The captured image is input to the image processing device 7 through the signal line 7e, converted into a digital signal through the A / D converter 7c, stored in the image memory 7b, and subjected to image processing to obtain a component signal. Posture is recognized. Further, the image to be processed can be displayed on the monitor 24.
[0018]
<Flow of parts recognition>
FIG. 3 shows a flow of calculating a suction deviation by recognizing a component posture when the component is a QFN component, for example.
[0019]
First, since there are various types of QFN parts as shown in FIG. 4, the types are classified according to the shape of the corner terminals, and are classified as type 0 to type 3 according to the shape of the corner terminals. In the future, if other corner terminal-shaped parts appear, it will be handled by adding more types. Further, in the following individual descriptions, description will be made on the component types (type, number of terminals, outer shape) suitable for the description.
[0020]
The part is expressed by data describing the vertical / horizontal dimensions of the part, the position where the corner terminal exists, the corner terminal shape existing there, and the terminal information of each of the four sides. The terminal information includes the number of terminals, pitch, terminal length, terminal width, chipping information, terminal bending determination rate, and the like. Using the above representation method, the position and shape of the corner terminal, and terminal information of each side are input using an input device such as the keyboard 21 or acquired from the host computer as part data. It is transmitted in advance to the component data memory 7d in the image processing apparatus 7 and managed for each component identification number (ID).
[0021]
At the time of recognition, the picked-up component is picked up by the image pickup device 5, the image is stored in the image memory 7b, the ID number of the component is designated, and the component data related to the component is stored from the component data memory 7d. The recognition process shown in FIG. 3 is started after reading.
[0022]
First, in step S1, scanning is performed from the outside to the inside of the image to detect an external contact of the component, and a circumscribed window W indicating the approximate position of the component is set based on the result. Subsequently, lead row windows W1 to W4 are set for each side (step S2), and an inspection region is set in the region where the lead exists. For each of the four sides, a DOG filter (Marr &Posio's Difference-Of-Gaussian filter) is applied to the lead row window to detect the edge of the lead terminal, and using that, the lead tip ("+" in the figure) is detected. Coordinates are detected (steps S3 and S4). At this time, if the detected number is less than the designated number, the recognition process is terminated as an under-number error at that time.
[0023]
Subsequently, a lead row straight line connecting the lead tips is obtained from the detected lead tip coordinates. As shown in FIG. 5A, when a straight line is obtained using all the detected leads, a straight line H ′ that is shifted when a corner terminal or a lead on the other side is detected is obtained. Therefore, in order to obtain an accurate lead row straight line, points that are not on the same straight line are deleted from the detected lead row coordinates.
[0024]
The method is illustrated in FIG. 6. First, as shown in FIG. 6A, the detection lead row is divided into two groups G 1 and G 2 on the left and right sides. To create a histogram. Then, in each group, an intermediate value is obtained from the obtained histogram, and a detection terminal having an intermediate value at the y coordinate is extracted. For example, in the group G1, the intermediate value is y4, and in the group G2, the intermediate value is y2, and all points having the respective intermediate values are obtained. The obtained points are indicated by “+” in FIG. 6B, and then, as shown in FIG. 6C, the average value of the extracted terminals is obtained, and two points having the average value are obtained. R1 and R2 are determined, and a straight line passing through the two points R1 and R2 is set as a reference straight line R as shown in FIG. Next, as shown in FIG. 6 (E), the detection terminal R3 having a certain distance or more from the reference straight line R is deleted.
[0025]
In this way, after deleting points that are not on the same straight line, as shown in FIG. 5B, a least-squares straight line is obtained with respect to the coordinates Rn of the remaining detection terminals, and this straight line is defined as a lead row straight line H.
[0026]
Subsequently, the lead row straight line is obtained at each side, and intersections of the lead row straight lines are obtained as component corner coordinates C1 to C4. This corresponds to step S5 in FIG.
[0027]
Terminals of various shapes exist at the component corners, and such corner terminals L1 to L4 are not necessary for centering (positioning). Therefore, when a corner terminal is detected at the component corner, a detailed description will be given below. As described above, the corner terminal is deleted based on the corner coordinates C1 to C4 (step S6).
[0028]
Since the method for deleting the corner terminal is different for each type of component shown in FIG. 4 or for each terminal shape, different deletion processing is performed for each type as described later. For example, in the case of a part belonging to type 3 as shown in FIG. 7A, when the lead terminal L11 adjacent to the corner terminal L10 is too close, the DOG filter is applied to detect the lead edge. As shown in FIG. 7B, the lead tip E10 may be detected for the two terminals L10 and L11. In this case, the presence of the corner terminal L10 affects the detection of the lead terminal. On the other hand, in the case of a part belonging to type 1 as shown in FIG. 7C, if the tip of the lead terminal L21 adjacent to the corner terminal L20 has a certain distance, a DOG filter may be applied. Two terminals are not detected as one. As shown in FIG. 7D, the lead tips E20, E21,. . . . . Even if the corner terminal L20 exists, the detection of the lead terminal is not affected.
[0029]
Therefore, when the corner terminal has a shape that does not affect the detection of the lead terminal as in types 1 and 2, it is determined whether or not the corner terminal is included in the detection result by looking at the distance from the corner. Since the corner terminal exists in the corner portion of the component, if the terminal closest to the corner exists within a predetermined distance from the corner, the corner terminal is determined to be a corner terminal. Since the corner terminal is unnecessary for centering, it is deleted from the detection result when it is determined that it is a corner terminal. If there is no corresponding terminal, it is not deleted. After the terminal is deleted, two diagonal lines are acquired from the corner coordinates, and the diagonal lines are scanned to check for the presence of the corner terminal. If the type and position of the component type are erroneously input at the time of inputting the component data, a difference from the terminal detection by scanning occurs, and different component inspection can be performed. For example, if a corner terminal cannot be found for a corner that should have a corner terminal on the part data, the part is recognized for a different part. In such a case, the process ends in error. .
[0030]
On the other hand, when the corner terminal has a shape such as type 3 that affects the detection of the lead terminal, a diagonal scan is first performed to detect the corner terminal. The contour of the corner terminal is detected, the corner terminal is painted out from the processed image, and the corner terminal is deleted. This is performed for each of the four corners, an image without corner terminals is created, and lead detection is performed again based on the image.
[0031]
The corner terminal deletion process and the different parts inspection performed in step S6 will be described in detail later for each type.
[0032]
As described above, after performing the corner terminal deletion process and the different part inspection, a lead inspection is performed on each side such as whether there is a defective terminal with respect to the remaining lead terminals detected (steps S7 and S8). If it is normal, the center and inclination of the component are calculated based on the lead terminal (step S9).
[0033]
<Detection of corner terminal by diagonal scan>
As described above, since it is necessary to perform image processing by painting a corner terminal depending on the type of inspection and whether it is a different part, detection of the corner terminal by diagonal scanning will be described below.
[0034]
First, a binarization threshold value for detecting a corner terminal is set. As shown in FIG. 8, the points on the lead row straight line H ″ of each side and the points in the vicinity thereof are sampled and used as sample points, a density histogram of the sample points is created, and a discriminant analysis method is used. The discriminant analysis method assumes that the set of density values is divided into two classes (greater than t and less than t) with a threshold value t. This is a general threshold selection method based on the concept of determining the parameter t so that the separation is the best, for example, the upper left corner threshold is obtained for the two sides that form the corner, that is, the upper side and the left side. The average value of the threshold values.
[0035]
Subsequently, the component image is processed along the flow shown in FIG. 9 to check whether a corner terminal exists.
[0036]
First, since the corner coordinates of the component image are acquired (step S5 in FIG. 3), a diagonal line connecting the diagonal corners is acquired (step S11), and the scan direction and range for detecting the terminal are determined. Set (step S12). As shown in FIG. 10A, the scan direction is made different depending on the slope of the diagonal line and the corner position in order to increase the detection sensitivity. As the scan range, ranges M1 and M2 having a length of 1/4 of the distance between corners before and after the corner coordinates are determined, and a scan start point m1 and an end point m2 are set.
[0037]
When the scan direction, the scan start point, and the end point are thus set, the scan is started (step S13). As shown in FIG. 10C, when the diagonal slope is gentler than 45 °, the diagonal point and the upper and lower points are scanned from the scan start point to the end point (y-direction scan), and the diagonal slope is obtained. When the angle is steeper than 45 °, the diagonal point and the left and right points are scanned in the x-axis direction.
[0038]
In step S14, the scan result is determined. When a point equal to or higher than the binarization threshold value for the corner terminal can be detected, the diagonal scan ends, and the process proceeds to step S15 to acquire the terminal outline. On the other hand, if a point equal to or higher than the binarization threshold is not found even after scanning up to the scan end point, it is determined that there is no corner terminal.
[0039]
If a terminal is detected in step S14, the contour is detected from the detection point (step S15). The state of acquiring this contour is shown in FIG. In FIG. 11A, Q1 is a point detected by the diagonal scan, and the surrounding eight neighborhoods excluding the detected point Q1 are investigated in numerical order. Since the threshold is detected at Q2 and the contour is detected, this is set as the next contour point. Subsequently, as shown in FIG. 11 (B), the investigation of 8 neighborhoods starting from Q2 is started, and the same processing is repeated until the initial start point is returned. Note that the survey direction in the vicinity of 8 is determined by the direction of the diagonal scan.
[0040]
The contour points thus detected are shown in FIG. 11C, and the information is stored in the array in the order of detection. Subsequently, in steps S16 and S17, edge pair coordinates in the X direction and edge pair coordinates in the y direction are obtained from the contour point array (FIGS. 11D and 11E). In step S18, centroids Xg and Yg of the detection terminal are obtained from the edge pair coordinates (FIGS. 11F and 11G). The calculation of the center of gravity is obtained according to the following formula.
[0041]
Lsum (y) = Edge2 (y) −Edge1 (y) +1
Ladr_sum (y) = Lsum (y) × (Edge1 (y) + Edge2 (y)) / 2
SUM = ΣLsum (y)
Ymom = Σ (Lsum (y) × y)
Xmom = ΣLadr_sum (y)
Xg = Ymom / Sum
Yg = Xmom / Sum
When the center of gravity of the obtained detection terminal exists in the vicinity of the diagonal line, the detected terminal can be regarded as a corner terminal. Conversely, if the center of gravity is far from the diagonal line, there is a possibility that the lead terminal has been detected by mistake, and it is considered that there is no corner terminal.
[0042]
The detection of the corner terminal by such a diagonal scan can be used for the corner terminal filling performed according to the different parts inspection or the type type as described below.
[0043]
<Corner terminal removal and inspection of different parts>
Here, details of the corner terminal deletion and the different parts inspection performed in step S6 of FIG. 3 will be described. As described above, this processing differs depending on the component type as shown in FIG.
[0044]
The type 0 component does not have a corner terminal, so the corner terminal deletion process is not performed. However, for the inspection of different parts, the above-described diagonal scan is performed to check for the presence of corner terminals. If no corner terminal is detected in all four corners, it is assumed to be normal. If a corner terminal is detected even at one corner, there is a possibility of a different part. Therefore, since the different part inspection is performed again after the lead inspection, the corner position where the corner terminal exists is remembered.
[0045]
FIG. 12 shows the flow of the corner terminal deletion and the different parts inspection process for the type 1 and type 2 parts.
[0046]
First, since the lead terminal is detected, the pitch is acquired (step S21), and the distance between the detected leads is obtained. In the case of a component having no missing lead as shown in FIG. 13A, the lead pitch Pn is obtained by averaging the distance between lead terminals other than the lead terminals L30 and L31 at both ends. On the other hand, as shown in FIG. 13B, when lead missing L32 and L33 exist, the minimum lead-to-lead distance is obtained from other than the terminal pitch at both ends, and the other lead-to-lead distances are divided by this minimum lead-to-lead distance. When the minimum distance between leads is P1, the distance between leads is expressed as an integer. From the lead missing information of the component data, an inter-lead distance row with one pitch as P1 is obtained.
[0047]
If there is a discrepancy between the detected distance between leads and the lead information acquired from the missing lead information, error processing is performed assuming that the parts are different parts. When normal, the average value is obtained by taking into account the number of chips at the distance between leads other than the distance between leads at both ends, and this is taken as the lead pitch.
[0048]
Next, when the distance between the leads at both ends is not within ± 30% of the detection pitch, the end leads are regarded as corner terminals and are deleted. However, if the lead bending determination rate is set to less than ± 30%, the detection pitch is within ± lead bending determination rate [%]. For example, as shown in FIG. 14A, since the distance P3 between the lead terminal L30 at the left end and the adjacent lead terminal is larger than the detection pitch + 30%, the terminal L30 is deleted as a corner terminal. On the other hand, since the distance P4 from the lead terminal L31 at the right end is within the detection pitch + 30%, this terminal is not deleted. This state is illustrated in FIG. Thus, when both end pitches are inconsistent and do not match, an abnormality process is performed (step S22), and one terminal is deleted.
[0049]
Next, when a detection terminal exists within one pitch from the corner coordinates, it is regarded as a corner terminal and deleted (step S23). However, this processing is not performed if the distance between the leads at both ends is deleted due to an abnormality. Therefore, this process is not performed for the left end L30 that has already been deleted. If there are a plurality of detection terminals within one pitch, the detection terminal closest to the corner coordinates is deleted.
[0050]
Note that the two values used for deletion determination here, the allowable value of the distance between leads at both ends, and the distance from the corner can be specified externally from component data or the like. The default values are used in the explanation.
[0051]
Finally, the above-described diagonal scan is performed (step S24), and the presence / absence of corner terminals on the four sides is checked (steps S25 and S27). If a corner terminal is detected at a corner designated as having a corner terminal, it is assumed to be normal. If the presence or absence of a corner terminal is different from the specified even at one corner, there is a possibility of a different part. Since the different part inspection is performed again after the lead inspection, the corner position where the corner terminal exists is remembered (step S26).
[0052]
The corner terminal deletion processing of the type 3 component is performed along the flow shown in FIG. In the case of type 3, since the corner terminal affects the detection of the lead terminal, a diagonal scan is performed, the corner terminal is detected, and the corner terminal is subjected to a painting process to delete the corner terminal.
[0053]
Therefore, first, the above-described diagonal scan is performed (step S31), and the presence / absence of a corner terminal is checked (step S32). If the terminal does not exist, it is impossible to perform the corner terminal filling process of the next process, so the process is skipped and the process proceeds to the next corner process. However, the absence of a corner terminal at a corner designated as having a corner terminal may be a different part. Therefore, since the different part inspection is performed again after the lead inspection, the corner position where the corner terminal is not detected is remembered (step S33).
[0054]
When it is determined by the diagonal scan that the corner terminal exists, the corner terminal is filled (step S34). This filling process is performed as shown in FIG. 16, and first, scanning is performed between two points X1 and X2 that are half a pitch outside the edge point in the x direction, and the positions of the points X3 and X4 having the lowest density are obtained. To do. This is a valley coordinate. Fill the space between the left and right valley coordinates so that the density change is constant.
[0055]
When the filling with the edge pair in the x direction is completed, the same processing is performed in the y direction. Since the density on the point on the edge has already been changed, the valley coordinates are obtained by scanning between the point outside the edge and the point outside the half pitch. The density is set so that the density change is constant between the upper and lower valley coordinates. Only apply if the new density is lower than the density already filled. By such processing, the corner terminal L can be painted, and the image of the corner terminal can be deleted.
[0056]
When all the detected corner terminals have been painted (step S35), lead detection is performed again (step S36), and the component center and inclination are calculated according to the detection result.
[0057]
By performing terminal fill processing in this way, terminals that you do not want to detect can be deleted from the image, so it is not only unnecessary to detect unnecessary terminals themselves, it also does not affect the detection of surrounding terminals, Only necessary terminals can be detected accurately, and accurate component recognition can be performed.
[0058]
It should be noted that the terminal filling process described with respect to type 3 may be performed not only on the components of type 3 but also on types 1 and 2 having other corner terminals.
[0059]
Further, in the diagonal scan performed in the corner terminal deletion and the different part inspection, the position of the corner terminal which may be a different part and has an error is stored (step S26 in FIG. 12). In step S33 in FIG. 15, the stored terminal is again scanned for the presence / absence of the corner terminal. This process is illustrated in FIG.
[0060]
Since the lead end coordinates are determined after the end of the lead inspection, as shown in FIG. 17A, the coordinates of the corner coordinates E40 and the coordinates of the edges E41 and E42 of the two lead terminals L41 and L42 adjacent thereto are determined. I understand. A rectangle A connecting these two lead terminals and corner coordinates is obtained. As shown in FIG. 17A, in the range of the rectangle A, part of the lead terminals L41 and L42 enters the side where the lead exists. In order to avoid the lead terminal portion, as shown in FIG. 17B, a scan for finding a point where no terminal exists from the side toward the inside is performed from the lead tip side to the lead root direction. As shown in FIG. 17C, in accordance with the point where the innermost lead terminal does not exist, a rectangle A ′ obtained by narrowing the previously obtained range is obtained.
[0061]
Then, the range A ′ set in FIG. 17C is scanned from the corner coordinate side, and if a point equal to or higher than the binarization threshold for the corner terminal is found in a block having a certain number of pixels, the corner terminal is Judge that it exists. If a predetermined number or more points are not found after scanning all within the range A ′, it is determined that there is no corner terminal. The number of pixels determined to be a certain number or more of chunks regarded as corner terminals is set for each resolution. Thereby, the detection accuracy of a corner terminal can be improved.
[0062]
【The invention's effect】
As described above, in the present invention, since the corner recognition unnecessary for the component recognition not related to the centering is deleted and the component recognition is performed, the component recognition accuracy can be improved and the component mounting accuracy can be improved. it can.
[0063]
Further, in the present invention, when the corner terminal is close to the adjacent terminal depending on the part type, the corner terminal may not be recognized, so the image is scanned along the diagonal line obtained from the corner coordinates, A corner terminal is detected by scanning, and the corner terminal is deleted by painting out the detected corner terminal. By performing terminal fill processing in this way, terminals that you do not want to detect can be deleted from the image, so it is not only unnecessary to detect unnecessary terminals themselves, it also does not affect the detection of surrounding terminals, Only necessary terminals can be detected accurately, and accurate component recognition can be performed.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a schematic configuration of a component mounting apparatus.
FIG. 2 is a configuration diagram illustrating configurations of a component imaging device and an image processing device.
FIG. 3 is a flowchart showing a flow of component recognition.
FIG. 4 is an explanatory diagram showing types of parts.
FIG. 5 is an explanatory diagram showing a flow for obtaining a lead row straight line;
FIG. 6 is an explanatory diagram showing a flow of obtaining a reference straight line for obtaining a lead row straight line.
FIG. 7 is an explanatory diagram for explaining the influence of a corner terminal on terminal detection according to a component type.
FIG. 8 is an explanatory diagram showing sampling points for obtaining a binarization threshold value.
FIG. 9 is a flowchart illustrating a flow of detecting whether or not a corner terminal exists in a component by diagonal scan.
FIG. 10 is an explanatory diagram for explaining a diagonal scan method;
FIG. 11 is an explanatory diagram showing a flow for obtaining a contour of a detected corner terminal.
FIG. 12 is a flowchart showing the flow of corner terminal deletion processing and different component inspection for types 1 and 2 components;
FIG. 13 is an explanatory diagram showing a state in which a lead pitch is determined.
FIG. 14 is an explanatory diagram showing a flow of corner terminal deletion.
FIG. 15 is a flowchart showing a flow of corner terminal deletion processing and different component inspection for a type 3 component.
FIG. 16 is an explanatory diagram showing a corner terminal deletion process for a type 3 component;
FIG. 17 is an explanatory diagram showing a process for enhancing corner terminal detection.
[Explanation of symbols]
5 Imaging device
7 Image processing device
7b Image memory
7d Component data memory

Claims (2)

In a component recognition method for processing an image of a captured component and recognizing the posture of the component based on a component terminal detected by the image processing,
Process the image of the imaged part to obtain the corner coordinates and lead terminals ,
Scan the image along a diagonal line based on the acquired corner coordinates ,
This scan detects corner terminals,
Inspect different parts to see if parts have been recognized for the specified parts,
Determine if a corner terminal exists,
In the case of different parts, save the corner terminal position,
If it is determined that a corner terminal exists, delete the corner terminal from the image ,
It performs a lead inspection against the lead terminal after deletion of the corner terminal from the image,
A component recognition method comprising recognizing a posture of a component based on a lead terminal after inspection . In a component recognition apparatus that processes an image of a captured component and recognizes the orientation of the component based on the terminal of the component detected by the image processing,
An image processing apparatus which have the means for obtaining a captured component image processing corner coordinates and lead terminals of,
Means for scanning an image along a diagonal line based on corner coordinates obtained from the image processing ;
Means for detecting a corner terminal by the scanning;
A means for inspecting different parts to determine whether parts have been recognized for the specified part;
In the case of different parts, means for storing the corner terminal position,
Means for deleting the corner terminal on the image when it is determined that the corner terminal exists;
And means for performing a lead test against the lead terminal after you delete a corner terminal on the image,
Means for calculating the center of the part and its inclination based on the lead terminal after inspection ;
A component recognition device comprising:

Images