JPH11142117A - Object measuring method and its equipment and storage medium of control program for object measurement - Google Patents

Abstract

PROBLEM TO BE SOLVED: To perform measuring process of high precision without being affected by noise. SOLUTION: In an equipment which processes an image obtained by sensing an object and measures the position and the direction of the object, the edge extraction result to an input image is displayed on a monitor image plate, and specified edge constituting points E0 -E6 are designated every contour line of the object. Coordinates of each designated point are recognized by a CPU, and edge intervals D1-D4 in the (x) and (y) axis directions are calculated. Each of the calculated values is compared with a previously stored reference edge interval. When the difference between each of the edge intervals D1-D6 and the corresponding reference edge interval is in the range of a threshold value, the edge extraction result is judged to be adequate, and measuring process is executed.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for measuring the position and orientation of an object by using an image obtained by imaging the object. The present invention relates to a recording medium on which a control program for causing a computer to execute the measurement processing is recorded.

[0002]

2. Description of the Related Art The above measurement processing is performed, for example, when inspecting the mounting position and mounting direction of a chip component on a substrate. The image processing apparatus for performing this inspection extracts an edge component from the image of the chip component to be measured, specifies a plurality of straight lines representing the contour of the component using the extracted positions of the edges, The coordinates indicating the mounting position of the component and the angle indicating the mounting direction are set to be calculated based on the position of the intersection of each straight line, the inclination of the straight line, and the like.

[0003]

However, in the course of this measurement processing, noise is mixed in the image data,
If there is a flaw or dirt on the substrate to be measured, an edge other than the contour of the original measurement object is extracted, and as a result, the position or orientation of the object may be erroneously measured.

The present invention has been made in view of the above problem, and it is determined whether or not an edge extracted on an image represents the contour of a measurement object, and is determined to represent the contour of the object. It is a technical object to perform high-precision measurement processing without being affected by noise by performing measurement processing using only edges that have been set.

[0005]

According to a first aspect of the present invention, there is provided an object measuring method, wherein each edge represents a contour of the object based on a positional relationship between the edges on an image obtained by imaging the object. Is determined, and when it is determined that each edge represents the contour of the object, the measurement process is performed using the position of each edge.

According to a second aspect of the present invention, there is provided an object measuring method comprising:
An edge representing the outline of the object is selected based on the positional relationship between the edges on the image obtained by imaging the object, and the measurement process is performed using only the selected edge position.

According to a third aspect of the present invention, there is provided an object measuring apparatus comprising:
2. An image input unit for inputting an image obtained by imaging an object, an edge extracting unit for extracting edges on the input image, and an edge extracting unit for performing the method of claim 1. Determination means for determining whether or not each edge represents the contour of the object, based on the positional relationship between the edges thus determined, and when the determination means determines that each edge represents the contour of the object. And measurement means for measuring the position and orientation of the object using the extracted position of each edge.

In the invention according to claim 4, the discriminating means recognizes the size of the object represented by each edge from the extraction position of each edge, and determines the size of the recognized object as the size of the object. If it corresponds, it is determined that each edge represents the contour of the object. According to a fifth aspect of the present invention, the discriminating means provisionally sets a contour of an object represented by each edge from an extraction position of each edge, and the provisionally set contour is a predetermined contour related to the contour shape of the object. When the condition is satisfied, it is determined that each edge represents the contour of the object.

An object measuring apparatus according to a sixth aspect of the present invention comprises:
Measurement condition setting means for setting predetermined measurement conditions for measuring the object, image input means for inputting an image obtained by imaging the object under the set measurement conditions, and Edge extracting means for extracting the edge of the edge, determining means for determining whether each edge represents the contour of the object based on the positional relationship of each edge extracted by the edge extracting means, Measuring means for measuring the position and orientation of the object by using the extracted position of each edge when it is determined that any of the edges represents the contour of the object; And measuring condition changing means for driving the measuring condition setting means to change the measuring condition of the object when it is determined that an edge other than the outline is included.

The object measuring apparatus according to the invention of claim 7 is:
In order to carry out the method according to the second aspect, in addition to the image input means and the edge extracting means similar to the third aspect of the invention, the contour of the object is determined by the positional relationship between the edges extracted by the edge extracting means. Edge selecting means for selecting an edge to be represented, measuring means for measuring the position and orientation of the object using the position of the edge selected by the edge selecting means,
Means are provided.

The invention of claim 8 relates to a recording medium on which a control program for causing a computer to execute the method of claim 1 is recorded, and an edge is extracted from an image obtained by imaging an object. Step, a step of determining whether or not each edge represents the contour of the target object, based on the positional relationship of the extracted edges, and that each edge represents the contour of the target object in the step of the determination processing. When it is determined, a control program for performing each of the steps of measuring the position and orientation of the object using the extracted position of each edge is recorded.

According to a ninth aspect of the present invention, there is provided a recording medium on which a control program for executing the method of the second aspect on a computer is recorded, and an edge is extracted from an image obtained by imaging an object. Performing the steps of: selecting an edge representing the outline of the target object based on the positional relationship between the extracted edges; and measuring the position and orientation of the target object using the position of the selected edge. A control program for performing the operation is recorded.

[0013]

According to the first, third and eighth aspects of the present invention, prior to the measurement processing, it is determined whether or not each edge represents the contour of the object based on the positional relationship between the edges on the image. Only when it is determined that the edge also represents the contour of the object, the measurement process using the extraction position of each edge is performed.
Thereby, even if the edge extraction result includes an edge other than the original contour of the measurement target, there is no risk of erroneous measurement of the position or orientation of the target, and the measurement accuracy is improved.

According to a fourth aspect of the present invention, each edge is targeted by the size of the object represented by each extracted edge, and in the fifth aspect of the present invention, each edge is determined by a contour of the object provisionally set by each edge. It is possible to determine whether or not it represents the outline of an object.

According to the sixth aspect of the present invention, when it is determined that an edge other than the contour of the object is included in the extracted edges, the measurement condition of the object is changed. It is possible to cope with a case where an edge is erroneously extracted.

According to the second, seventh, and ninth aspects of the present invention, an edge representing the contour of the object is selected based on the positional relationship between the edges on the image, and a measurement process is performed using the selected edge extraction position. Therefore, an edge corresponding to noise can be removed from the measurement target, and highly accurate measurement processing can be performed.

[0017]

FIG. 1 shows a configuration of an object measuring apparatus according to an embodiment of the present invention, in which a television camera 1 (hereinafter simply referred to as "camera 1"), an A / D converter 2, and a D / A converter. Device 3, monitor 4, image memory 5, character / graphic memory 6, CPU 7, memory 8, input unit 9, output unit 1
0, a lighting control unit 11 and the like.

This object measuring apparatus is used, for example, for inspecting a mounted component on a printed circuit board, and processes an image obtained by capturing an image of the board to be inspected by the camera 1.
Measure the mounting position and mounting direction of components. The measurement result is notified to the operator by a method such as displaying it on the monitor 4.

As shown in FIG. 2, the camera 1 is installed so as to image a component to be measured from an upper position. Further, the imaging area of the camera 1 is irradiated with coaxial illumination light from a half mirror 14 provided on the optical path of the camera and a light source 15 provided in a direction orthogonal to the optical path. Further, light sources 16 and 16 for diffused illumination are provided at a position obliquely above the imaging area.

Returning to FIG. 1, analog image data taken by the camera 1 is supplied to an A / D converter 2 and converted into digital image data.
Is stored in. The A / D converted image data is supplied to the D / A converter 3 via the image bus 12.
After being decoded into analog data, it is output to the monitor 4.

The character / graphic memory 6 is for storing character data and graphic data for monitor display. In this case, in addition to the position designation window shown in FIG. For displaying a user box, a cursor image, and the like.

In the memory 8, a control program recorded in advance on a storage medium such as a floppy disk or a CD-ROM is installed. In addition, various data generated when the control program is executed, a reference edge interval (details). Has a storage area for storing (described later). The CPU 7, which is the control subject, is a CPU bus 1
By accessing the image memory 5 via the control unit 3 and executing the processing based on the installed control program on the image data, a series of control processing relating to the measurement processing is performed.

The input unit 9 is used for inputting setting data of a measurement area prior to the processing, performing a process of confirming a measurement result, and the like. The output unit 10 is used when outputting a measurement result, an error message, or the like to the monitor 4 or an external device (not shown) according to a command from the CPU 7.
The illumination control unit 11 is for adjusting the illuminance of each of the light sources 15 and 16 for coaxial illumination and diffuse illumination in response to a command from the CPU 7.

The object measuring apparatus having the above configuration extracts edges on the image of the object captured by the camera 1 and then determines whether or not each of the extracted edges represents the contour of the object. When it is determined that only the edge representing the outline of the object is extracted, the position and orientation of the object are measured using the extracted position of each edge. On the other hand, when it is determined that components other than the outline of the object are included in the extracted edges, the measurement process is stopped, and an error message indicating that the image is defective is output from the output unit 10. I do.

For the sake of simplicity, a detailed procedure for judging the suitability of the edge extraction result will be described below, taking as an example the case of measuring an object having a rectangular contour.

FIG. 3 shows a first method for determining whether or not the result of edge extraction is appropriate. In this embodiment, the suitability of the edge extraction result is determined based on whether or not the size of the object represented by each extracted edge matches the size of the target object. ) Shows a binary image (edge image) showing the result of edge extraction.

This edge image is displayed on the monitor 4, and the operator specifies the positions of a plurality of edge constituent points (two points in the illustrated example) for each contour line.

The process of designating the edge composing points is performed using the above-described position designation windows 17a and 17b. These windows 17a and 17b are shown in FIG.
As shown in FIG. 3 (3), a vertically long window 17a shown in FIG. 3 (2) is provided for a horizontal contour line in a configuration having a + mark for alignment at the center position. For the contour, a horizontally long window 17b shown in FIG. 3 (3) is used.

That is, the windows 17a, 17a are arranged so that the + mark overlaps the position of the point to be designated by the operator.
When the determination operation is performed by aligning b, the CPU 7 takes in the coordinate position where the + mark is superimposed and recognizes it as the position of the designated point. In this embodiment, as shown in FIG. 3A, it is previously determined that an edge composing point at a position substantially opposite to each other in the vertical and horizontal directions is designated.

After recognizing each of the opposing designated points as a set, the CPU 7 recognizes each of the opposing sets (E ₀ , E ₂ ),
For (E ₁ , E ₃ ), the edge intervals D1 and D2 are calculated based on the difference between the y coordinate values. Similarly, for each pair (E ₄ , E ₆ ) and (E ₅ , E ₇ ) corresponding to the x-axis direction, the edge intervals D 3 and D 4 are calculated from the difference between the x coordinate values.

The edge intervals D1, D2, D3, D4
Corresponds to the sampling value of the width and length in each of the vertical and horizontal directions of the object. In the memory 8, reference edge intervals MD1, MD2, MD3 corresponding to the respective sampling values are stored.
MD4 is stored, and the sampling value Dn (n = 1 to 4) of each edge interval and the corresponding reference edge interval MDn
Are within a predetermined threshold th,
The CPU 7 determines that the size of the object represented by the outline is equal to the size of the target object, and recognizes that the edge extraction result is appropriate. Note that this threshold th
It is desirable that a predetermined allowable value be given in consideration of a case where the image of the measurement target is inclined at a predetermined angle with respect to the reference direction.

The reference edge intervals MD1 to MD4
Prior to the measurement processing, a model image obtained by capturing a target object in a good state is taken into the apparatus, its edge is extracted, and a predetermined edge composing point is designated in the same manner as in FIG. It is calculated, but it is also possible for the operator to input a specific numerical value.

In the above embodiment, each of the edge intervals D1 to D1
Although the edge composing points for obtaining D4 are manually specified by the operator, the coordinates of the edge composing points near the predetermined position may be automatically extracted by the CPU 7 instead.

FIG. 4 shows a series of procedures of the measurement process including the above-described determination process. First, in a state where the object is positioned in the imaging area, the above-described coaxial illumination light or diffuse illumination light is applied to perform imaging by the camera 1, and the image data becomes A
After being converted into digital quantity image data by the / D converter 2, it is stored in the image memory 5 (step 1). C
The PU 7 extracts an edge on the image by using a result of binarizing the image of the digital amount or scanning an edge extraction filter on the image (step 2).

Next, the result of this edge extraction is
Are displayed, and the edge configuration point for each contour line is designated by the designation operation by the operator, and the CPU 7 calculates the edge interval for each of the x and y axis directions using each designated position (step 3, 4).

Next, the CPU 7 calculates a reference edge interval MD corresponding to each of the calculated edge intervals Dn.
The absolute value of the difference from n is calculated. As a result, if all the difference absolute values | Dn−MDn | are equal to or smaller than the threshold th, step 5 becomes “YES”, and the CPU 7 determines that each edge extracted in step 2 is the contour of the object. And the process proceeds to step S6.

In step 6, the CPU 7 executes step 2
After applying the least squares method to the coordinates of each edge component point extracted in step 3, specify the equation of the straight line representing each contour line, calculate the intersection and slope of each straight line, and determine the position and orientation of the object. recognize. After this recognition result is output to the monitor 4 or an external device via the output unit 10, a series of processing ends.

On the other hand, when the difference absolute value for any of the edge intervals exceeds the threshold th, the CPU 7
It is determined that an edge other than the contour of the object has been extracted at the sampling position of the edge interval. In this case, step 5 becomes “NO”, and the output processing such as an error message is performed without performing the above-described measurement processing (step 7).

In the above embodiment, it is assumed that the object has a rectangular outline, but the shape of the object is not limited to this. When the lead portion of an actual IC component is to be measured, the width and length of each lead or the edge interval corresponding to the interval between leads is calculated from the edge extraction result to determine whether or not it is appropriate. become.

FIG. 5 shows a second method for judging whether the result of edge extraction is appropriate. In this method, as in the first embodiment, after specifying two or more edge constituent points for each contour line from the extracted edges, each contour line is designated using the coordinate points of these designated points. Are temporarily set.

If each extracted edge represents an object, the straight lines L1 and L3, L2 and L4 should be parallel to each other, and the straight lines L1 and L2 should intersect perpendicularly.
Therefore, the equation showing the straight line Lm (m = 1 to 4) is expressed as Amx
When + Bmy + cm = 0 is set, when each of the straight lines L1 to L4 satisfies the conditions of the following equations (1) to (3), it is determined that each extracted edge represents the contour of the target object ( However, th _p and th _v are threshold values approaching 0).

[0042]

(Equation 1)

[0043]

(Equation 2)

[0044]

(Equation 3)

FIG. 6 shows a series of procedures of the measurement processing including the above-described determination processing. First, similarly to the first embodiment, after the image of the object is captured and edge extraction processing is performed,
Two or more edge constituent points are designated for each contour line (steps 1 to 3). Next, the CPU 7 temporarily sets the equations of the straight lines L1 to L4 representing each contour line using the coordinates of each designated point (step 4).

Next, the CPU 7 sets each straight line L1
It is checked whether or not L4 satisfies the above conditions (1) to (3). As a result, when each condition is satisfied, step 5 becomes “YES”, and in step 6, measurement processing using the positions of the extracted edges is performed.

On the other hand, if there is a condition in which any one of the expressions (1) to (3) does not hold, it is determined that an edge other than the contour of the object has been extracted, and step 5
Becomes “NO”. In this case, the process proceeds to step 7 without performing the measurement process, and the error process is performed.

Since some of the noises on the image are caused by measurement conditions such as illumination, it is determined that components other than the contour of the object are included in the extracted edges. In such a case, the measurement conditions may be changed, and the processing may be performed again.

FIG. 7 shows a processing procedure when the illumination condition is changed when it is determined that an edge other than the contour of the object has been extracted. In addition, here, the first
Although the judgment processing of the edge extraction result is performed by the same method as that of the second embodiment, the present invention is not limited to this, and a similar method of the second embodiment may be used.

When an image obtained by capturing an image of an object under predetermined illumination conditions is captured in step 1, after the edge extraction processing is performed on the input image in the same manner as the procedure shown in FIG. An edge interval for each of the x and y axis directions is calculated according to the designation of an edge constituent point for each contour line (steps 1 to 4). In the next step 5, each edge interval Dn
And the reference edge interval MDn are sequentially checked. If each difference absolute value is equal to or smaller than the threshold th, the edge extraction result is determined to be appropriate, and the position and orientation of the object are measured. Processing is performed (step 6).

On the other hand, when the absolute value of the difference for any edge interval exceeds the threshold value th, the CPU 7
Determines that an edge other than the contour of the object has been extracted at the sampling position of the edge interval, shifts to step 7, and performs a lighting condition changing process via the lighting control unit. The change of the illumination condition performed here is performed by, for example, a method of fixing the illuminance of one of the coaxial illumination and the diffuse illumination and changing the other illuminance by a predetermined amount.

When the illumination conditions are changed in this way, the process returns to step 1 again, an image under illumination under the changed conditions is captured, and the same processing as described above is sequentially performed. As a result, the determination in step 5 is “YES”
Then, the measurement processing in step 6 is performed, and the processing ends.

In the embodiments described above, it is determined whether or not the extracted edge represents the outline of the object, and the measurement process is performed only when each edge represents the outline of the object. I am trying to implement, but not limited to this,
The extracted edge constituent points may be selected to represent the outline of the target object, and the measurement processing may be performed using the coordinates of the selected points.

FIGS. 8A and 8B show the principle of selecting the edge. In this case, a plurality of edges are specified for each contour line of the object.

FIG. 8A shows the same as in the first embodiment.
Monitor 4 position designation window 17a on the displayed edge image on, by determining the 17b, 5 pieces of edge control points E ₁₁ to E _15, respectively for each contour, E ₂₁ to E
Shows an example of specifying a _{25, E 31 ~E 35, E} 41 ~E 45. In this embodiment, since the number of designated points increases, the width of the position designation windows 17a and 17b is set smaller than that of the embodiment of FIG.

Here, for simplicity of description, five edges are specified for each contour line, but in actual processing, it is desirable to specify a larger number of edges. Also in this case, as described above, the position of each edge is
The automatic extraction may be performed by U7.

After recognizing the coordinates of the designated points for each contour line, the CPU 7 applies the coordinates of these designated points to the least squares method, and temporarily sets the equations of the straight lines L1 to L4 representing each contour line. Further, the CPU 7 selects an edge composing point to be used in the measurement processing based on the positional relationship between the designated points with reference to the straight lines L1 to L4.

FIG. 8B shows a straight line L1 in FIG. 8A.
And an enlarged view of a portion of the designated point E ₁₁ to E _15. Each designated point E ₁₁ to E _15, the distance to this straight line L1 is selected from short order. For example, if three points are selected from the designated five points, three points E ₁₃ , E ₁₂ , and E ₁₄ are sequentially selected, and the other two points E ₁₁ and E ₁₅ are removed as noise. .

FIG. 9 shows the procedure of the measurement process when the above-described selection process is incorporated. In order to execute this procedure, the device configuration shown in FIG. 1 is required.

In step 1, the image of the object is fetched into the apparatus, and in step 2, edge extraction processing is performed. In step 3, the operator moves to the position of the edge composing point to be designated on the monitor screen. Then, the position specifying windows 17a and 17b are sequentially determined, and a plurality of edge constituent points are specified for each contour line. After recognizing the coordinates of each of the designated points, the CPU 7 applies the coordinates of each of the designated points to each contour by the least squares method, and temporarily sets equations of straight lines representing the contours L1 to L4 (step 4). .

Next, the CPU 7 sets each straight line L1
Based on the principle shown in FIG. 8 (2), a distance from each specified point to a straight line is calculated for each of L4 to L4. A point is selected (step 5). Next, the CPU 7 resets the equations of the straight lines representing the respective contour lines using the selected edge composing points, and then measures the position of intersection, the inclination, etc. of each straight line with these equations, and calculates the position and orientation of the object. Is recognized (steps 6 and 7).

In the above procedure, the selection processing of the edge constituent points is performed only once. However, if a large number of points are specified and the selection processing is performed a plurality of times, more accurate measurement can be performed. Processing can be performed.

[0063]

According to the first, third, and eighth aspects of the present invention, when measuring the position and orientation of an object using edges on an image, these edges are determined by the positional relationship between the edges prior to the measurement processing. Determine whether or not it represents the outline of the object,
The measurement process is performed only when it is determined that both edges represent the outline of the target object.Therefore, the position and orientation of the target object are erroneously measured using edges other than the original outline of the target measurement object. There is no danger of performing the measurement, and highly accurate measurement processing can be performed.

According to the sixth aspect of the present invention, when it is determined that an edge other than the contour of the measurement target is extracted, the measurement condition of the target is changed. Measurement is eliminated, and accurate measurement processing can be performed using appropriate image data according to the object.

According to the second, seventh, and ninth aspects of the present invention, the edge representing the contour of the object is selected based on the positional relationship between the edges on the image, and the measurement process is performed using the selected edge. Edges corresponding to noise can be removed from the measurement target, and highly accurate measurement processing can be performed.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an object measuring device according to the present invention.

FIG. 2 is a front view showing an example of installation of a camera and a light source.

FIG. 3 is an explanatory diagram showing a method of determining whether or not an edge extraction result is appropriate.

FIG. 4 is a flowchart illustrating a measurement processing procedure using the determination method of FIG. 3;

FIG. 5 is an explanatory diagram showing a method for determining whether or not an edge extraction result is appropriate.

FIG. 6 is a flowchart illustrating a measurement processing procedure using the determination method of FIG. 5;

FIG. 7 is a flowchart illustrating a measurement procedure for changing an illumination condition when it is determined that an edge other than a contour of an object is extracted.

FIG. 8 is an explanatory diagram showing a method of selecting a designated edge composing point.

FIG. 9 is a flowchart illustrating a measurement processing procedure using the edge selection method of FIG. 8;

[Explanation of symbols]

 1 camera 7 CPU 11 lighting control unit

Claims (9)

[Claims] 1. A method for measuring a position and an orientation of an object using an edge position on an image obtained by imaging the object, wherein each edge is determined by a positional relationship between the edges on the image. It is characterized in that it is determined whether or not each edge represents the outline of the object, and when it is determined that each edge represents the outline of the object, the measurement process is performed using the position of each edge. Object measurement method. 2. A method of measuring a position and an orientation of an object using an edge position on an image obtained by imaging the object, wherein the contour of the object is determined based on a positional relationship of each edge on the image. An object measurement method comprising: selecting an edge representing an image; and performing the measurement process using only the selected edge position. 3. An image input unit for inputting an image obtained by imaging an object, an edge extracting unit for extracting an edge on the input image, and a positional relationship between the edges extracted by the edge extracting unit. A determining means for determining whether each edge represents the contour of the object, and extracting positions of the edges when the determining means determines that each edge represents the contour of the object. An object measuring device comprising: a measuring unit that measures a position and an orientation of an object by using the object. 4. The discriminating means recognizes a size of an object represented by each edge from an extraction position of each edge, and when the size of the recognized object corresponds to the size of a target object, 4. The object measuring apparatus according to claim 3, wherein each of the edges is determined to represent a contour of the object. 5. The discriminating means provisionally sets a contour of an object represented by each edge from an extraction position of each edge, and determines a predetermined condition according to which the provisionally set contour is related to a contour shape of an object. 4. The object measuring device according to claim 3, wherein when the condition is satisfied, each edge is determined to represent the contour of the object. 6. Measurement condition setting means for setting predetermined measurement conditions for measuring an object, and image input means for inputting an image obtained by imaging the object under the set measurement conditions. An edge extraction unit that extracts an edge on the input image, and a determination unit that determines whether each edge represents an outline of a target object based on a positional relationship between the edges extracted by the edge extraction unit, Measuring means for measuring the position and orientation of the object by using the extracted position of each edge when each of the edges indicates that the contour of the object is determined by the determining means; and An object comprising: a measurement condition changing unit that drives the measurement condition setting unit to change the measurement condition of the object when it is determined that the extraction result includes an edge other than the contour of the object. Measuring apparatus. 7. An image input unit for inputting an image obtained by capturing an image of an object, an edge extracting unit for extracting edges on the input image, and a positional relationship between the edges extracted by the edge extracting unit. Object measuring apparatus comprising: an edge selecting unit that selects an edge representing an outline of an object by using the method; and a measuring unit that measures the position and orientation of the object using the position of the edge selected by the edge selecting unit. . 8. A step of extracting edges on an image obtained by imaging the object, and a step of judging whether each edge represents the outline of the object based on the positional relationship between the extracted edges. Performing each step of measuring the position and orientation of the object using the extracted position of each edge when it is determined in the step of the determination process that each edge represents the contour of the object. Recording medium for a control program for measuring an object, in which a control program for recording is recorded. 9. A step of extracting an edge on an image obtained by imaging the object, a step of selecting an edge representing an outline of the object based on a positional relationship between the extracted edges, A step of measuring the position and orientation of the target object using the position; a recording medium of a control program for object measurement, which records a control program for performing each step.